Merge branch 'master' into pr/10068

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -77,3 +77,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -89,3 +89,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -85,3 +85,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -70,3 +70,11 @@ body:
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -64,3 +64,11 @@ body:
         [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc
         <more lines>
       render: shell
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/ISSUE_TEMPLATE/6_question.yml

@@ -70,3 +70,11 @@ body:
         [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc
         <more lines>
       render: shell
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.

.github/workflows/build.yml

@@ -266,7 +266,7 @@ jobs:
           # We need to ignore wheels otherwise we break universal2 builds
           python3 -m pip install -U --no-binary :all: -r requirements.txt
           # We need to fuse our own universal2 wheels for curl_cffi
-          python3 -m pip install -U delocate
+          python3 -m pip install -U 'delocate==0.11.0'
           mkdir curl_cffi_whls curl_cffi_universal2
           python3 devscripts/install_deps.py --print -o --include curl-cffi > requirements.txt
           for platform in "macosx_11_0_arm64" "macosx_11_0_x86_64"; do
@@ -409,7 +409,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.7.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -469,7 +469,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.7.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl"
 
       - name: Prepare
         run: |

.github/workflows/core.yml

@@ -55,7 +55,8 @@ jobs:
     - name: Install test requirements
       run: python3 ./devscripts/install_deps.py --include test --include curl-cffi
     - name: Run tests
+      timeout-minutes: 15
       continue-on-error: False
       run: |
         python3 -m yt_dlp -v || true  # Print debug head
-        python3 ./devscripts/run_tests.py core
+        python3 ./devscripts/run_tests.py --pytest-args '--reruns 2 --reruns-delay 3.0' core

.github/workflows/issue-lockdown.yml

@@ -0,0 +1,21 @@
+name: Issue Lockdown
+on:
+  issues:
+    types: [opened]
+
+permissions:
+  issues: write
+
+jobs:
+  lockdown:
+    name: Issue Lockdown
+    if: vars.ISSUE_LOCKDOWN
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Lock new issue"
+        env:
+          GH_TOKEN: ${{ github.token }}
+          ISSUE_NUMBER: ${{ github.event.issue.number }}
+          REPOSITORY: ${{ github.repository }}
+        run: |
+          gh issue lock "${ISSUE_NUMBER}" -R "${REPOSITORY}"

.github/workflows/quick-test.yml

@@ -15,11 +15,12 @@ jobs:
       with:
         python-version: '3.8'
     - name: Install test requirements
-      run: python3 ./devscripts/install_deps.py --include test
+      run: python3 ./devscripts/install_deps.py -o --include test
     - name: Run tests
+      timeout-minutes: 15
       run: |
         python3 -m yt_dlp -v || true
-        python3 ./devscripts/run_tests.py core
+        python3 ./devscripts/run_tests.py --pytest-args '--reruns 2 --reruns-delay 3.0' core
   check:
     name: Code check
     if: "!contains(github.event.head_commit.message, 'ci skip all')"

.github/workflows/release.yml

@@ -204,7 +204,7 @@ jobs:
           git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
           git add -u
           git commit -m "Release ${{ env.version }}" \
-            -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all :ci run dl"
+            -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all"
           git push origin --force ${{ github.event.ref }}:release
 
       - name: Get target commitish
@@ -325,7 +325,7 @@ jobs:
               "(https://github.com/yt-dlp/yt-dlp-master-builds/releases/latest \"Master builds\")"' || '' }} > ./RELEASE_NOTES
           printf '\n\n' >> ./RELEASE_NOTES
           cat >> ./RELEASE_NOTES << EOF
-          #### A description of the various files are in the [README](https://github.com/${{ github.repository }}#release-files)
+          #### A description of the various files is in the [README](https://github.com/${{ github.repository }}#release-files)
           ---
           $(python ./devscripts/make_changelog.py -vv --collapsible)
           EOF

.github/workflows/sanitize-comment.yml

@@ -0,0 +1,17 @@
+name: Sanitize comment
+
+on:
+  issue_comment:
+    types: [created, edited]
+
+permissions:
+  issues: write
+
+jobs:
+  sanitize-comment:
+    name: Sanitize comment
+    if: vars.SANITIZE_COMMENT && !github.event.issue.pull_request
+    runs-on: ubuntu-latest
+    steps:
+      - name: Sanitize comment
+        uses: yt-dlp/sanitize-comment@v1

CONTRIBUTORS

@@ -646,3 +646,35 @@ tippfehlr
 varunchopra
 DrakoCpp
 PatrykMis
+DinhHuy2010
+exterrestris
+harbhim
+LeSuisse
+DunnesH
+iancmy
+mokrueger
+luvyana
+szantnerb
+hugepower
+scribblemaniac
+Codenade
+Demon000
+Deukhoofd
+grqz
+hibes
+Khaoklong51
+kieraneglin
+lengzuo
+naglis
+ndyanx
+otovalek
+quad
+rakslice
+sahilsinghss73
+tony-hn
+xingchensong
+BallzCrasher
+coreywright
+eric321
+poyhen
+tetra-fox

Changelog.md

@@ -4,6 +4,249 @@ # Changelog
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2024.10.07
+
+#### Core changes
+- **cookies**: [Fix cookie load error handling](https://github.com/yt-dlp/yt-dlp/commit/e59c82a74cda5139eb3928c75b0bd45484dbe7f0) ([#11140](https://github.com/yt-dlp/yt-dlp/issues/11140)) by [Grub4K](https://github.com/Grub4K)
+
+#### Extractor changes
+- **applepodcasts**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6328e2e67a4e126e08af382e6a387073082d5c5f) ([#10903](https://github.com/yt-dlp/yt-dlp/issues/10903)) by [coreywright](https://github.com/coreywright)
+- **cwtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4b7bec66d8100978b82bb24110ed44e2a7749931) ([#11135](https://github.com/yt-dlp/yt-dlp/issues/11135)) by [kclauhk](https://github.com/kclauhk)
+- **instagram**
+    - [Do not hardcode user-agent](https://github.com/yt-dlp/yt-dlp/commit/079a7bc334281d3c13d347770ae5f9f2b7da471a) ([#11155](https://github.com/yt-dlp/yt-dlp/issues/11155)) by [poyhen](https://github.com/poyhen)
+    - [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/cf85cba5d9496bd2689e1070005b4d1b4cd3dc6d) ([#11156](https://github.com/yt-dlp/yt-dlp/issues/11156)) by [tetra-fox](https://github.com/tetra-fox)
+- **noodlemagazine**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/ccb23e1bac9768d1c70535beb744e668ed4a2720) ([#11144](https://github.com/yt-dlp/yt-dlp/issues/11144)) by [BallzCrasher](https://github.com/BallzCrasher)
+- **patreon**: [Extract all m3u8 formats for locked posts](https://github.com/yt-dlp/yt-dlp/commit/f91645aceaf13926cf35be2c1dfef61b3aab97fb) ([#11138](https://github.com/yt-dlp/yt-dlp/issues/11138)) by [bashonly](https://github.com/bashonly)
+- **youtube**: [Change default player clients to `ios,mweb`](https://github.com/yt-dlp/yt-dlp/commit/de2062753a188060d76f587e45becce61fe399f9) ([#11190](https://github.com/yt-dlp/yt-dlp/issues/11190)) by [seproDev](https://github.com/seproDev)
+
+#### Postprocessor changes
+- **xattrmetadata**: [Try to write each attribute](https://github.com/yt-dlp/yt-dlp/commit/3a193346eeb27ac2959ff30c370adb899ec94732) ([#11115](https://github.com/yt-dlp/yt-dlp/issues/11115)) by [eric321](https://github.com/eric321)
+
+#### Misc. changes
+- **ci**: [Rerun failed tests](https://github.com/yt-dlp/yt-dlp/commit/b31b81d85f00601710d4fac590c3e4efb4133283) ([#11143](https://github.com/yt-dlp/yt-dlp/issues/11143)) by [Grub4K](https://github.com/Grub4K)
+- **cleanup**: Miscellaneous: [1a176d8](https://github.com/yt-dlp/yt-dlp/commit/1a176d874e6772cd898ce507379ea388e96ee3f7) by [bashonly](https://github.com/bashonly)
+
+### 2024.09.27
+
+#### Important changes
+- **The minimum *recommended* Python version has been raised to 3.9**
+Since Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)
+
+#### Core changes
+- [Allow `none` arg to negate `--convert-subs` and `--convert-thumbnails`](https://github.com/yt-dlp/yt-dlp/commit/c08e0b20b5edd8957b8318716bc14e896d1b96f4) ([#11066](https://github.com/yt-dlp/yt-dlp/issues/11066)) by [kieraneglin](https://github.com/kieraneglin)
+- [Fix format sorting bug with vp9.2 vcodec](https://github.com/yt-dlp/yt-dlp/commit/8f4ea14680c7865d8ffac10a9174205d1d84ada7) ([#10884](https://github.com/yt-dlp/yt-dlp/issues/10884)) by [rakslice](https://github.com/rakslice)
+- [Raise minimum recommended Python version to 3.9](https://github.com/yt-dlp/yt-dlp/commit/cca534cd9e6850c70244f225a4a1895ef4bcdbec) ([#11098](https://github.com/yt-dlp/yt-dlp/issues/11098)) by [bashonly](https://github.com/bashonly)
+- **cookies**: [Improve error message for Windows `--cookies-from-browser chrome` issue](https://github.com/yt-dlp/yt-dlp/commit/b397a64691421ace5df09457c2a764821a2dc6f2) ([#11090](https://github.com/yt-dlp/yt-dlp/issues/11090)) by [seproDev](https://github.com/seproDev)
+- **utils**: `mimetype2ext`: [Recognize `aacp` as `aac`](https://github.com/yt-dlp/yt-dlp/commit/cc85596d5b59f0c14e9381b3675f619c1e12e597) ([#10860](https://github.com/yt-dlp/yt-dlp/issues/10860)) by [bashonly](https://github.com/bashonly)
+
+#### Extractor changes
+- [Fix JW Player format parsing](https://github.com/yt-dlp/yt-dlp/commit/409f8e9e3b4bde81ef76fc563256f876d2ff8099) ([#10956](https://github.com/yt-dlp/yt-dlp/issues/10956)) by [seproDev](https://github.com/seproDev)
+- [Handle decode errors when reading responses](https://github.com/yt-dlp/yt-dlp/commit/325001317d97f4545d66fac44c4ba772c6f45f22) ([#10868](https://github.com/yt-dlp/yt-dlp/issues/10868)) by [bashonly](https://github.com/bashonly)
+- **abc.net.au**: iview, showseries: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/7f909046f4dc0fba472b4963145aef6e0d42491b) ([#11101](https://github.com/yt-dlp/yt-dlp/issues/11101)) by [bashonly](https://github.com/bashonly)
+- **adn**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/cc88a54bb1ef285154775f8a6a413335ce4c71ce) ([#10749](https://github.com/yt-dlp/yt-dlp/issues/10749)) by [infanf](https://github.com/infanf)
+- **asobistage**: [Support redirected URLs](https://github.com/yt-dlp/yt-dlp/commit/a7d3235c84dac57a127cbe0ff38f7f7c2fdd8fa0) ([#10768](https://github.com/yt-dlp/yt-dlp/issues/10768)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **bandcamp**: user: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/5d0176547f16a3642cd71627126e9dfc24981e20) ([#10328](https://github.com/yt-dlp/yt-dlp/issues/10328)) by [bashonly](https://github.com/bashonly), [quad](https://github.com/quad)
+- **beacon**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b4760c778d0c92c6e3f2bc8346cd72c8f08595ae) ([#9901](https://github.com/yt-dlp/yt-dlp/issues/9901)) by [Deukhoofd](https://github.com/Deukhoofd)
+- **bilibili**
+    - [Fix chapters and subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/a2000bc85730c950351d78bb818493dc39dca3cb) ([#11099](https://github.com/yt-dlp/yt-dlp/issues/11099)) by [bashonly](https://github.com/bashonly)
+    - [Fix festival URL support](https://github.com/yt-dlp/yt-dlp/commit/b43bd864851f2862e26caa85461c5d825d49d463) ([#10740](https://github.com/yt-dlp/yt-dlp/issues/10740)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz)
+- **biliintl**: [Fix referer header](https://github.com/yt-dlp/yt-dlp/commit/a06bb586795ebab87a2356923acfc674d6f0e152) ([#11003](https://github.com/yt-dlp/yt-dlp/issues/11003)) by [Khaoklong51](https://github.com/Khaoklong51)
+- **dropbox**: [Fix password-protected video support](https://github.com/yt-dlp/yt-dlp/commit/63da31b3b29af90062d8a72a905ffe4b5e499042) ([#10735](https://github.com/yt-dlp/yt-dlp/issues/10735)) by [ndyanx](https://github.com/ndyanx)
+- **ertgr**: [Fix video extraction](https://github.com/yt-dlp/yt-dlp/commit/416686ed0cf792ec44ab059f3b229dd776077e14) ([#11091](https://github.com/yt-dlp/yt-dlp/issues/11091)) by [seproDev](https://github.com/seproDev)
+- **eurosport**: [Support local URL variants](https://github.com/yt-dlp/yt-dlp/commit/f0bb28504c8c2b75ee3e5796aed50de2a7f90a1b) ([#10785](https://github.com/yt-dlp/yt-dlp/issues/10785)) by [seproDev](https://github.com/seproDev)
+- **facebook**
+    - ads: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d62fef7e07d454c0d2ba2d69fb96d691dba1ded0) ([#10704](https://github.com/yt-dlp/yt-dlp/issues/10704)) by [kclauhk](https://github.com/kclauhk)
+    - reel: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0e1b941c6b2caa688b0d3332e723d16dbafa4311) by [lengzuo](https://github.com/lengzuo)
+- **germanupa**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/124f058b546d652a359c67025bb479789bfbef0b) ([#10538](https://github.com/yt-dlp/yt-dlp/issues/10538)) by [grqz](https://github.com/grqz)
+- **hgtvde**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a555389c9bb32e589e00b4664974423fb7b04dcd) ([#10992](https://github.com/yt-dlp/yt-dlp/issues/10992)) by [bashonly](https://github.com/bashonly), [rdamas](https://github.com/rdamas)
+- **huya**: video: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/25c1cdaa2650563494d3bf00a38f72d0d9486bff) ([#10686](https://github.com/yt-dlp/yt-dlp/issues/10686)) by [hugepower](https://github.com/hugepower)
+- **iprima**: [Fix zoom URL support](https://github.com/yt-dlp/yt-dlp/commit/4a27b8f092f7f7c10b7a334d3535c97c2af02f0a) ([#10959](https://github.com/yt-dlp/yt-dlp/issues/10959)) by [otovalek](https://github.com/otovalek)
+- **khanacademy**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0fba08485b6445b72b5b63ae23ca2a73fa5d967f) ([#10913](https://github.com/yt-dlp/yt-dlp/issues/10913)) by [seproDev](https://github.com/seproDev)
+- **kick**
+    - clips: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/0aa4426e9a35f7f8e184f1f2082b3b313c1448f7) ([#11107](https://github.com/yt-dlp/yt-dlp/issues/11107)) by [bashonly](https://github.com/bashonly)
+    - vod: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/173d54c151b987409e3eb09552d8d89ed8fc50f7) ([#10988](https://github.com/yt-dlp/yt-dlp/issues/10988)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz)
+- **kika**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e6f48ca80821939c1fd11ec2a0cdbf2fba9b258a) ([#5788](https://github.com/yt-dlp/yt-dlp/issues/5788)) by [1100101](https://github.com/1100101)
+- **lnkgo**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/fa83d0b36bc43d30fe9241c1e923f4614864b758) ([#10904](https://github.com/yt-dlp/yt-dlp/issues/10904)) by [naglis](https://github.com/naglis)
+- **loom**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/7509d692b37a7ec6230ea75bfe1e44a8de5eefce) ([#10760](https://github.com/yt-dlp/yt-dlp/issues/10760)) by [kclauhk](https://github.com/kclauhk)
+- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e2b3634e299be9c16a247ece3b1858d83889c324) ([#11083](https://github.com/yt-dlp/yt-dlp/issues/11083)) by [szantnerb](https://github.com/szantnerb)
+- **mojevideo**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/28b0ecba2af5b4919f198474b3d00a76ef322c31) ([#11019](https://github.com/yt-dlp/yt-dlp/issues/11019)) by [04-pasha-04](https://github.com/04-pasha-04), [pzhlkj6612](https://github.com/pzhlkj6612)
+- **niconico**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/eabb4680fdb09ba1f48d174a700a2e3b43f82add) ([#11103](https://github.com/yt-dlp/yt-dlp/issues/11103)) by [bashonly](https://github.com/bashonly)
+- **nzz**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4a9bc8c3630378bc29f0266126b503f6190c0430) ([#10461](https://github.com/yt-dlp/yt-dlp/issues/10461)) by [1-Byte](https://github.com/1-Byte)
+- **patreoncampaign**: [Support API URLs](https://github.com/yt-dlp/yt-dlp/commit/232e6db30c474d1b387e405342f34173ceeaf832) ([#10734](https://github.com/yt-dlp/yt-dlp/issues/10734)) by [bashonly](https://github.com/bashonly), [hibes](https://github.com/hibes)
+- **pinterest**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/c8c078fe28b0ffc15ef9646346c00c592fe71a78) ([#10867](https://github.com/yt-dlp/yt-dlp/issues/10867)) by [bashonly](https://github.com/bashonly), [sahilsinghss73](https://github.com/sahilsinghss73)
+- **radiko**: [Extract unique `id` values](https://github.com/yt-dlp/yt-dlp/commit/c8d096c5ce111411fbdbe2abb8fed54f317a6182) ([#10726](https://github.com/yt-dlp/yt-dlp/issues/10726)) by [garret1317](https://github.com/garret1317)
+- **rtp**: [Support more subpages](https://github.com/yt-dlp/yt-dlp/commit/d02df303d8e49390599db9f34482697e4d1cf5b2) ([#10787](https://github.com/yt-dlp/yt-dlp/issues/10787)) by [Demon000](https://github.com/Demon000)
+- **rumblechannel**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/ad0b857f459a6d390fbf124183916218c52f223a) ([#11049](https://github.com/yt-dlp/yt-dlp/issues/11049)) by [tony-hn](https://github.com/tony-hn)
+- **rutube**: [Support livestreams](https://github.com/yt-dlp/yt-dlp/commit/41be32e78c3845000dbac188ffb90ea3ea7c4dfa) ([#10844](https://github.com/yt-dlp/yt-dlp/issues/10844)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **samplefocus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/46f4c80bc363ee8116c33d37f65202e6c3470954) ([#10947](https://github.com/yt-dlp/yt-dlp/issues/10947)) by [seproDev](https://github.com/seproDev)
+- **screenrec**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/36f9e602ad55679764bc75a4f67f7562b1d6adcf) ([#10917](https://github.com/yt-dlp/yt-dlp/issues/10917)) by [naglis](https://github.com/naglis)
+- **sen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/41a241ca6ffb95b3d9aaf4f42106ca8cba9af1a6) ([#10952](https://github.com/yt-dlp/yt-dlp/issues/10952)) by [seproDev](https://github.com/seproDev)
+- **servus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/300c91274f7ea5b1b0528fc5ee11cf1a61d4079e) ([#10944](https://github.com/yt-dlp/yt-dlp/issues/10944)) by [seproDev](https://github.com/seproDev)
+- **snapchatspotlight**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b37417e4f934fd8909788b493d017777155b0ae5) ([#11030](https://github.com/yt-dlp/yt-dlp/issues/11030)) by [seproDev](https://github.com/seproDev)
+- **svtpage**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/5a8a05aebb49693e78e1123015837ed5e961ff76) ([#11010](https://github.com/yt-dlp/yt-dlp/issues/11010)) by [diman8](https://github.com/diman8)
+- **tenplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d8d473002b654ab0e7b97ead869f58b4361eeae1) ([#10928](https://github.com/yt-dlp/yt-dlp/issues/10928)) by [aarubui](https://github.com/aarubui)
+- **tiktok**: [Fix web formats extraction](https://github.com/yt-dlp/yt-dlp/commit/3ad0b7f422d547204df687b6d0b2d9110fff3990) ([#11074](https://github.com/yt-dlp/yt-dlp/issues/11074)) by [bashonly](https://github.com/bashonly)
+- **twitter**: spaces: [Support video spaces](https://github.com/yt-dlp/yt-dlp/commit/bef1d4d6fc9493fda7f75e2289c07c507d10092f) ([#10789](https://github.com/yt-dlp/yt-dlp/issues/10789)) by [bashonly](https://github.com/bashonly)
+- **vidflex**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e978c312d6550a6ae4c9df18001afb1b420cb72f) ([#10002](https://github.com/yt-dlp/yt-dlp/issues/10002)) by [pzhlkj6612](https://github.com/pzhlkj6612)
+- **vimeo**
+    - [Always try to extract original format](https://github.com/yt-dlp/yt-dlp/commit/4115c24d157c5b5f63089d75c4e0f51d1f8b4489) ([#10721](https://github.com/yt-dlp/yt-dlp/issues/10721)) by [bashonly](https://github.com/bashonly) (With fixes in [e8e6a98](https://github.com/yt-dlp/yt-dlp/commit/e8e6a982a1b659eed434d225d7922f632bac6568) by [seproDev](https://github.com/seproDev))
+    - [Fix HLS audio format sorting](https://github.com/yt-dlp/yt-dlp/commit/a1b4ac2b8ed8e6eaa56044d439f1e0d00c2ba218) ([#11082](https://github.com/yt-dlp/yt-dlp/issues/11082)) by [fireattack](https://github.com/fireattack)
+- **watchespn**: [Improve auth support](https://github.com/yt-dlp/yt-dlp/commit/7adff8caf152dcf96d03aff69ed8545c0a63567c) ([#10910](https://github.com/yt-dlp/yt-dlp/issues/10910)) by [ischmidt20](https://github.com/ischmidt20)
+- **wistia**: [Support password-protected videos](https://github.com/yt-dlp/yt-dlp/commit/9f5c9a90898c5a1e672922d9cd799716c73cee34) ([#11100](https://github.com/yt-dlp/yt-dlp/issues/11100)) by [bashonly](https://github.com/bashonly)
+- **ximalaya**: [Add VIP support](https://github.com/yt-dlp/yt-dlp/commit/3dfd720d098b4d49d69cfc77e6376f22bcd90934) ([#10832](https://github.com/yt-dlp/yt-dlp/issues/10832)) by [seproDev](https://github.com/seproDev), [xingchensong](https://github.com/xingchensong)
+- **xinpianchang**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3aa0156e05662923d130ddbc1c82596e38c01a00) ([#10950](https://github.com/yt-dlp/yt-dlp/issues/10950)) by [seproDev](https://github.com/seproDev)
+- **yleareena**: [Support podcasts](https://github.com/yt-dlp/yt-dlp/commit/48d629d461e05b1b19f5e53dc959bb9ebe95da42) ([#11104](https://github.com/yt-dlp/yt-dlp/issues/11104)) by [bashonly](https://github.com/bashonly)
+- **youtube**
+    - [Add `po_token`, `visitor_data`, `data_sync_id` extractor args](https://github.com/yt-dlp/yt-dlp/commit/3a3bd00037e9908e87da4fa9f2ad772aa34dc60e) ([#10648](https://github.com/yt-dlp/yt-dlp/issues/10648)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz), [seproDev](https://github.com/seproDev) (With fixes in [fa2be9a](https://github.com/yt-dlp/yt-dlp/commit/fa2be9a7c63babede07480151363e54eee5702bd) by [bashonly](https://github.com/bashonly))
+    - [Support excluding `player_client`s in extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/49f3741a820ed142f6866317c2e7d247b130960e) ([#10710](https://github.com/yt-dlp/yt-dlp/issues/10710)) by [bashonly](https://github.com/bashonly)
+    - clip: [Prioritize `https` formats](https://github.com/yt-dlp/yt-dlp/commit/1d84b780cf33a1d84756825ac23f990a905703df) ([#11102](https://github.com/yt-dlp/yt-dlp/issues/11102)) by [bashonly](https://github.com/bashonly)
+    - tab: [Fix shorts tab extraction](https://github.com/yt-dlp/yt-dlp/commit/9431777b4c37129a6093080c77ca59960afbb9d7) ([#10938](https://github.com/yt-dlp/yt-dlp/issues/10938)) by [seproDev](https://github.com/seproDev)
+
+#### Networking changes
+- [Fix handler not being added to RequestError](https://github.com/yt-dlp/yt-dlp/commit/d1c4d88b2d912e8da5e76db455562ca63b1af690) ([#10955](https://github.com/yt-dlp/yt-dlp/issues/10955)) by [coletdjnz](https://github.com/coletdjnz)
+- [Pin `curl-cffi` version to < 0.7.2](https://github.com/yt-dlp/yt-dlp/commit/5bb1aa04dafce13ba9de707ea53169fab58b5207) ([#11092](https://github.com/yt-dlp/yt-dlp/issues/11092)) by [bashonly](https://github.com/bashonly)
+- **Request Handler**: websockets: [Upgrade websockets to 13.0](https://github.com/yt-dlp/yt-dlp/commit/6f9e6537434562d513d0c9b68ced8a61ade94a64) ([#10815](https://github.com/yt-dlp/yt-dlp/issues/10815)) by [coletdjnz](https://github.com/coletdjnz)
+
+#### Misc. changes
+- **build**
+    - [Bump PyInstaller version pin to `>=6.10.0`](https://github.com/yt-dlp/yt-dlp/commit/fb8b7f226d251e521a89b23c415e249e5b788e5c) ([#10709](https://github.com/yt-dlp/yt-dlp/issues/10709)) by [bashonly](https://github.com/bashonly)
+    - [Pin `delocate` version for `macos`](https://github.com/yt-dlp/yt-dlp/commit/7e41628ff523b3fe373b0981a5db441358980dab) ([#10901](https://github.com/yt-dlp/yt-dlp/issues/10901)) by [bashonly](https://github.com/bashonly)
+- **ci**
+    - [Add comment sanitization workflow](https://github.com/yt-dlp/yt-dlp/commit/b6200bdcf3a9415ae36859188f9a57e3e461c696) ([#10915](https://github.com/yt-dlp/yt-dlp/issues/10915)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+    - [Add issue tracker anti-spam protection](https://github.com/yt-dlp/yt-dlp/commit/ad9a8115aa29a1a95c961b16fcf129a228d98f50) ([#10861](https://github.com/yt-dlp/yt-dlp/issues/10861)) by [bashonly](https://github.com/bashonly)
+- **cleanup**: Miscellaneous: [c6387ab](https://github.com/yt-dlp/yt-dlp/commit/c6387abc1af9842bb0541288a5610abba9b1ab51) by [bashonly](https://github.com/bashonly), [Codenade](https://github.com/Codenade), [coletdjnz](https://github.com/coletdjnz), [grqz](https://github.com/grqz), [Grub4K](https://github.com/Grub4K), [pzhlkj6612](https://github.com/pzhlkj6612), [seproDev](https://github.com/seproDev)
+
+### 2024.08.06
+
+#### Core changes
+- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly)
+- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac)
+- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly)
+- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly)
+- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower)
+- **youtube**
+    - [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly)
+    - [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev)
+
+### 2024.08.01
+
+#### Core changes
+- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly)
+
+#### Extractor changes
+- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys)
+- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261)
+- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly)
+- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana)
+- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb)
+- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly)
+- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly)
+- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly)
+- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33)
+- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly)
+- **youtube**
+    - [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev)
+    - [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly)
+    - [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+    - [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly)
+
+### 2024.07.25
+
+#### Extractor changes
+- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
+- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
+- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
+- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
+- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
+- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
+
+#### Misc. changes
+- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
+
+### 2024.07.16
+
+#### Core changes
+- [Fix `noprogress` if `test=True` with `--quiet` and `--verbose`](https://github.com/yt-dlp/yt-dlp/commit/66ce3d76d87af3f81cc9dfec4be4704016cb1cdb) ([#10454](https://github.com/yt-dlp/yt-dlp/issues/10454)) by [Grub4K](https://github.com/Grub4K)
+- [Support `auto-tty` and `no_color-tty` for `--color`](https://github.com/yt-dlp/yt-dlp/commit/d9cbced493cae2008508d94a2db5dd98be7c01fc) ([#10453](https://github.com/yt-dlp/yt-dlp/issues/10453)) by [Grub4K](https://github.com/Grub4K)
+- **update**: [Fix network error handling](https://github.com/yt-dlp/yt-dlp/commit/ed1b9ed93dd90d2cc960c0d8eaa9d919db224203) ([#10486](https://github.com/yt-dlp/yt-dlp/issues/10486)) by [bashonly](https://github.com/bashonly)
+- **utils**: `parse_codecs`: [Fix parsing of mixed case codec strings](https://github.com/yt-dlp/yt-dlp/commit/cc0070f6496e501d77352bad475fb02d6a86846a) by [bashonly](https://github.com/bashonly)
+
+#### Extractor changes
+- **adn**: [Adjust for .com domain change](https://github.com/yt-dlp/yt-dlp/commit/959b7a379b8e5da059d110a63339c964b6265736) ([#10399](https://github.com/yt-dlp/yt-dlp/issues/10399)) by [infanf](https://github.com/infanf)
+- **afreecatv**: [Fix login and use `legacy_ssl`](https://github.com/yt-dlp/yt-dlp/commit/4cd41469243624d90b7a2009b95cbe0609343efe) ([#10440](https://github.com/yt-dlp/yt-dlp/issues/10440)) by [bashonly](https://github.com/bashonly)
+- **box**: [Support enterprise URLs](https://github.com/yt-dlp/yt-dlp/commit/705f5b84dec75cc7af97f42fd1530e8062735970) ([#10419](https://github.com/yt-dlp/yt-dlp/issues/10419)) by [seproDev](https://github.com/seproDev)
+- **digitalconcerthall**: [Extract HEVC and FLAC formats](https://github.com/yt-dlp/yt-dlp/commit/e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1) ([#10470](https://github.com/yt-dlp/yt-dlp/issues/10470)) by [bashonly](https://github.com/bashonly)
+- **dplay**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f) ([#10471](https://github.com/yt-dlp/yt-dlp/issues/10471)) by [bashonly](https://github.com/bashonly)
+- **epidemicsound**: [Support sound effects URLs](https://github.com/yt-dlp/yt-dlp/commit/8531d2b03bac9cc746f2ee8098aaf8f115505f5b) ([#10436](https://github.com/yt-dlp/yt-dlp/issues/10436)) by [iancmy](https://github.com/iancmy)
+- **generic**: [Fix direct video link extensions](https://github.com/yt-dlp/yt-dlp/commit/b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e) ([#10468](https://github.com/yt-dlp/yt-dlp/issues/10468)) by [bashonly](https://github.com/bashonly)
+- **picarto**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bacd18b7df08b4995644fd12cee1f8c8e8636bc7) ([#10414](https://github.com/yt-dlp/yt-dlp/issues/10414)) by [Frankgoji](https://github.com/Frankgoji)
+- **soundcloud**: permalink, user: [Extract tracks only](https://github.com/yt-dlp/yt-dlp/commit/22870b81bad97dfa6307a7add44753b2dffc76a9) ([#10463](https://github.com/yt-dlp/yt-dlp/issues/10463)) by [DunnesH](https://github.com/DunnesH)
+- **tiktok**: live: [Fix room ID extraction](https://github.com/yt-dlp/yt-dlp/commit/d2189d3d36987ebeac426fd70a60a5fe86325a2b) ([#10408](https://github.com/yt-dlp/yt-dlp/issues/10408)) by [mokrueger](https://github.com/mokrueger)
+- **tv5monde**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/9b95a6765a5f6325af99c4aca961587f0c426e8c) ([#10417](https://github.com/yt-dlp/yt-dlp/issues/10417)) by [bashonly](https://github.com/bashonly) (With fixes in [cc1a309](https://github.com/yt-dlp/yt-dlp/commit/cc1a3098c00995c6aebc2a16bd1050a66bad64db))
+- **youtube**
+    - [Avoid poToken experiment player responses](https://github.com/yt-dlp/yt-dlp/commit/8b8b442cb005a8d85315f301615f83fb736b967a) ([#10456](https://github.com/yt-dlp/yt-dlp/issues/10456)) by [seproDev](https://github.com/seproDev) (With fixes in [16da8ef](https://github.com/yt-dlp/yt-dlp/commit/16da8ef9937ff76632dfef02e5062c5ba99c8ea2))
+    - [Invalidate nsig cache from < 2024.07.09](https://github.com/yt-dlp/yt-dlp/commit/04e17ba20a139f1b3e30ec4bafa3fba26888f0b3) ([#10401](https://github.com/yt-dlp/yt-dlp/issues/10401)) by [bashonly](https://github.com/bashonly)
+    - [Reduce android client priority](https://github.com/yt-dlp/yt-dlp/commit/b85eef0a615a01304f88a3847309c667e09a20df) ([#10467](https://github.com/yt-dlp/yt-dlp/issues/10467)) by [seproDev](https://github.com/seproDev)
+
+#### Networking changes
+- [Add `legacy_ssl` request extension](https://github.com/yt-dlp/yt-dlp/commit/150ecc45d9cacc919550c13b04fd998ac5103a6b) ([#10448](https://github.com/yt-dlp/yt-dlp/issues/10448)) by [coletdjnz](https://github.com/coletdjnz)
+- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.7.X](https://github.com/yt-dlp/yt-dlp/commit/42bfca00a6b460fc053514cdd7ac6f5b5daddf0c) by [coletdjnz](https://github.com/coletdjnz)
+
+#### Misc. changes
+- **build**
+    - [Include `curl_cffi` in `yt-dlp_linux`](https://github.com/yt-dlp/yt-dlp/commit/4521f30d1479315cd5c3bf4abdad19391952df98) by [bashonly](https://github.com/bashonly)
+    - [Pin `curl-cffi` to 0.5.10 for Windows](https://github.com/yt-dlp/yt-dlp/commit/ac30941ae682f71eab010877c9a977736a61d3cf) by [bashonly](https://github.com/bashonly)
+- **cleanup**: Miscellaneous: [89a161e](https://github.com/yt-dlp/yt-dlp/commit/89a161e8c62569a662deda1c948664152efcb6b4) by [bashonly](https://github.com/bashonly)
+
+### 2024.07.09
+
+#### Core changes
+- [Do not alter default format selection when simulated](https://github.com/yt-dlp/yt-dlp/commit/0b570f2a90ce2363ba06089217514d644e7be2e0) ([#9862](https://github.com/yt-dlp/yt-dlp/issues/9862)) by [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **youtube**: [Remove broken `n` function extraction fallback](https://github.com/yt-dlp/yt-dlp/commit/7ead7332af69422cee931aec3faa277288e9e212) ([#10396](https://github.com/yt-dlp/yt-dlp/issues/10396)) by [pukkandan](https://github.com/pukkandan), [seproDev](https://github.com/seproDev)
+
+### 2024.07.08
+
+#### Core changes
+- **jsinterp**: [Implement `Function.prototype` resolving for `call` and `apply`](https://github.com/yt-dlp/yt-dlp/commit/6c056ea7aeb03660281653a9668547f2548f194f) ([#10392](https://github.com/yt-dlp/yt-dlp/issues/10392)) by [Grub4K](https://github.com/Grub4K)
+
+#### Extractor changes
+- **soundcloud**: [Fix rate-limit handling](https://github.com/yt-dlp/yt-dlp/commit/4b50b292cc98534fb8c7cdf0ae5cb85862f7ebfc) ([#10389](https://github.com/yt-dlp/yt-dlp/issues/10389)) by [bashonly](https://github.com/bashonly)
+- **youtube**: [Fix JS `n` function name extraction](https://github.com/yt-dlp/yt-dlp/commit/297b0a379282a15c80d82d51f3757c961db2dae1) ([#10390](https://github.com/yt-dlp/yt-dlp/issues/10390)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
+
+### 2024.07.07
+
+#### Important changes
+- Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)
+    - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors
+
+#### Core changes
+- [Address gaps in allowed extensions](https://github.com/yt-dlp/yt-dlp/commit/2469119490d7e0397ebbf5c5ae327316f955eef2) ([#10362](https://github.com/yt-dlp/yt-dlp/issues/10362)) by [bashonly](https://github.com/bashonly)
+- [Fix `--ignore-no-formats-error`](https://github.com/yt-dlp/yt-dlp/commit/cc767e9490056efaaa11c186b0d032e4b4969180) ([#10345](https://github.com/yt-dlp/yt-dlp/issues/10345)) by [Grub4K](https://github.com/Grub4K)
+
+#### Extractor changes
+- **abematv**: [Extract availability](https://github.com/yt-dlp/yt-dlp/commit/2a1a1b8e67e864289ac7ba5d05ec63dbb19a639f) ([#10348](https://github.com/yt-dlp/yt-dlp/issues/10348)) by [middlingphys](https://github.com/middlingphys)
+- **chzzk**: [Extract with API v3](https://github.com/yt-dlp/yt-dlp/commit/4862a29854d4044120e3f97b52199711ad04bee1) ([#10363](https://github.com/yt-dlp/yt-dlp/issues/10363)) by [hui1601](https://github.com/hui1601)
+- **douyutv**: [Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/commit/6075a029dba70a89675ae1250e7cdfd91f0eba41) ([#10347](https://github.com/yt-dlp/yt-dlp/issues/10347)) by [LeSuisse](https://github.com/LeSuisse)
+- **jiosaavn**: playlist: [Support featured playlists](https://github.com/yt-dlp/yt-dlp/commit/f0f867f008a1728f5f6ac1224b9e014b5d27f817) ([#10382](https://github.com/yt-dlp/yt-dlp/issues/10382)) by [harbhim](https://github.com/harbhim)
+- **vidyard**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/00766ece0c5c7a80781a4ff677198c5fb69d9dc0) ([#10155](https://github.com/yt-dlp/yt-dlp/issues/10155)) by [exterrestris](https://github.com/exterrestris)
+- **vimeo**: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/c1c9bb4adb42d0d93a2fb5d93a7de0a87b6ba884) ([#10341](https://github.com/yt-dlp/yt-dlp/issues/10341)) by [bashonly](https://github.com/bashonly)
+- **vtv**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/987a1f94c24275f2b0cd82e719956687415dd732) ([#10173](https://github.com/yt-dlp/yt-dlp/issues/10173)) by [DinhHuy2010](https://github.com/DinhHuy2010)
+- **yle_areena**
+    - [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/4cdc976bd861b5835601ae402bef543eacd88f3d) ([#10380](https://github.com/yt-dlp/yt-dlp/issues/10380)) by [seproDev](https://github.com/seproDev)
+    - [Fix subtitle extraction](https://github.com/yt-dlp/yt-dlp/commit/0d174e8bed32081eb38ef7f5d1a1282ae154f517) ([#10379](https://github.com/yt-dlp/yt-dlp/issues/10379)) by [Grub4K](https://github.com/Grub4K)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [b337d29](https://github.com/yt-dlp/yt-dlp/commit/b337d2989ce0614651d363383f6f743d977248ef) by [bashonly](https://github.com/bashonly)
+
 ### 2024.07.02
 
 #### Core changes

README.md

@@ -200,9 +200,9 @@ #### Impersonation
 
 The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting.
 
-* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
+* [**curl_cffi**](https://github.com/lexiforest/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lexiforest/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/lexiforest/curl_cffi/blob/main/LICENSE)
   * Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"`
-  * Currently only included in `yt-dlp.exe` and `yt-dlp_macos` builds
+  * Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds
 
 
 ### Metadata
@@ -278,7 +278,7 @@ ### Related scripts
 * **`devscripts/update-version.py`** - Update the version number based on the current date.
 * **`devscripts/set-variant.py`** - Set the build variant of the executable.
 * **`devscripts/make_changelog.py`** - Create a markdown changelog using short commit messages and update `CONTRIBUTORS` file.
-* **`devscripts/make_lazy_extractors.py`** - Create lazy extractors. Running this before building the binaries (any variant) will improve their startup performance. Set the environment variable `YTDLP_NO_LAZY_EXTRACTORS=1` if you wish to forcefully disable lazy extractor loading.
+* **`devscripts/make_lazy_extractors.py`** - Create lazy extractors. Running this before building the binaries (any variant) will improve their startup performance. Set the environment variable `YTDLP_NO_LAZY_EXTRACTORS` to something nonempty to forcefully disable lazy extractor loading.
 
 Note: See their `--help` for more info.
 
@@ -368,7 +368,9 @@ ## General Options:
                                     stderr) to apply the setting to. Can be one
                                     of "always", "auto" (default), "never", or
                                     "no_color" (use non color terminal
-                                    sequences). Can be used multiple times
+                                    sequences). Use "auto-tty" or "no_color-tty"
+                                    to decide based on terminal support only.
+                                    Can be used multiple times
     --compat-options OPTS           Options that can help keep compatibility
                                     with youtube-dl or youtube-dlc
                                     configurations by reverting some of the
@@ -457,17 +459,17 @@ ## Video Selection:
                                     conditions. Use a "\" to escape "&" or
                                     quotes if needed. If used multiple times,
                                     the filter matches if at least one of the
-                                    conditions is met. E.g. --match-filter
+                                    conditions is met. E.g. --match-filters
-                                    !is_live --match-filter "like_count>?100 &
+                                    !is_live --match-filters "like_count>?100 &
                                     description~='(?i)\bcats \& dogs\b'" matches
                                     only videos that are not live OR those that
                                     have a like count more than 100 (or the like
                                     field is not available) and also has a
                                     description that contains the phrase "cats &
-                                    dogs" (caseless). Use "--match-filter -" to
+                                    dogs" (caseless). Use "--match-filters -" to
                                     interactively ask whether to download each
                                     video
-    --no-match-filters              Do not use any --match-filter (default)
+    --no-match-filters              Do not use any --match-filters (default)
     --break-match-filters FILTER    Same as "--match-filters" but stops the
                                     download process when a video is rejected
     --no-break-match-filters        Do not use any --break-match-filters (default)
@@ -488,7 +490,7 @@ ## Video Selection:
                                     encountering a file that is in the archive
                                     (default)
     --break-per-input               Alters --max-downloads, --break-on-existing,
-                                    --break-match-filter, and autonumber to
+                                    --break-match-filters, and autonumber to
                                     reset per input URL
     --no-break-per-input            --break-on-existing and similar options
                                     terminates the entire download queue
@@ -997,12 +999,16 @@ ## Post-Processing Options:
                                     be used multiple times
     --no-exec                       Remove any previously defined --exec
     --convert-subs FORMAT           Convert the subtitles to another format
-                                    (currently supported: ass, lrc, srt, vtt)
+                                    (currently supported: ass, lrc, srt, vtt).
-                                    (Alias: --convert-subtitles)
+                                    Use "--convert-subs none" to disable
+                                    conversion (default) (Alias: --convert-
+                                    subtitles)
     --convert-thumbnails FORMAT     Convert the thumbnails to another format
                                     (currently supported: jpg, png, webp). You
                                     can specify multiple rules using similar
-                                    syntax as --remux-video
+                                    syntax as "--remux-video". Use "--convert-
+                                    thumbnails none" to disable conversion
+                                    (default)
     --split-chapters                Split video into multiple files based on
                                     internal chapters. The "chapter:" prefix can
                                     be used with "--paths" and "--output" to set
@@ -1756,7 +1762,7 @@ # Replace all spaces and "_" in title and uploader with a `-`
 
 # EXTRACTOR ARGUMENTS
 
-Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
+Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
 
 Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
 
@@ -1765,7 +1771,7 @@ # EXTRACTOR ARGUMENTS
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
+* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,mweb` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@@ -1773,8 +1779,11 @@ #### youtube
     * E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
 * `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
 * `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
-* `innertube_key`: Innertube API key to use for all API requests
+* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
 * `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
+* `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage`
+* `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID)
+* `po_token`:  Proof of Origin (PO) Token(s) to use for requesting video playback. Comma seperated list of PO Tokens in the format `CLIENT+PO_TOKEN`, e.g. `youtube:po_token=web+XXX,android+YYY`
 
 #### youtubetab (YouTube playlists, channels, feeds, etc.)
 * `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)
@@ -1786,6 +1795,7 @@ #### generic
 * `key_query`: Passthrough the master m3u8 URL query to its HLS AES-128 decryption key URI if no value is provided, or else apply the query string given as `key_query=VALUE`. Note that this will have no effect if the key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg
 * `hls_key`: An HLS AES-128 key URI *or* key (as hex), and optionally the IV (as hex), in the form of `(URI|KEY)[,IV]`; e.g. `generic:hls_key=ABCDEF1234567980,0xFEDCBA0987654321`. Passing any of these values will force usage of the native HLS downloader and override the corresponding values found in the m3u8 playlist
 * `is_live`: Bypass live HLS detection and manually set `live_status` - a value of `false` will set `not_live`, any other value (or no value) will set `is_live`
+* `impersonate`: Target(s) to try and impersonate with the initial webpage request; e.g. `safari,chrome-110`. By default any available target will be used. Use `false` to disable impersonation
 
 #### funimation
 * `language`: Audio languages to extract, e.g. `funimation:language=english,japanese`
@@ -1859,6 +1869,9 @@ #### orfon (orf:on)
 #### bilibili
 * `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats
 
+#### digitalconcerthall
+* `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility
 
 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
@@ -1885,6 +1898,7 @@ # PLUGINS
                 myplugin.py
 
 yt-dlp looks for these `yt_dlp_plugins` namespace folders in many locations (see below) and loads in plugins from **all** of them.
+Set the environment variable `YTDLP_NO_PLUGINS` to something nonempty to disable loading plugins entirely.
 
 See the [wiki for some known plugins](https://github.com/yt-dlp/yt-dlp/wiki/Plugins)
 
@@ -2172,9 +2186,9 @@ ### New features
 
 * **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata`
 
-* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filter` etc
+* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filters` etc
 
-* **Improvements**: Regex and other operators in `--format`/`--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
+* **Improvements**: Regex and other operators in `--format`/`--match-filters`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
 
 * **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details
 
@@ -2215,10 +2229,11 @@ ### Differences in default behavior
 * `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi`
 * yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
 * ~~yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [aria2c](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is~~
-* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
+* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filters` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
 * yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
 * yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
 * The sub-modules `swfinterp`, `casefold` are removed.
+* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
 
 For ease of use, a few more compat options are available:
 
@@ -2260,11 +2275,11 @@ #### Redundant options
     --get-thumbnail                  --print thumbnail
     -e, --get-title                  --print title
     -g, --get-url                    --print urls
-    --match-title REGEX              --match-filter "title ~= (?i)REGEX"
+    --match-title REGEX              --match-filters "title ~= (?i)REGEX"
-    --reject-title REGEX             --match-filter "title !~= (?i)REGEX"
+    --reject-title REGEX             --match-filters "title !~= (?i)REGEX"
-    --min-views COUNT                --match-filter "view_count >=? COUNT"
+    --min-views COUNT                --match-filters "view_count >=? COUNT"
-    --max-views COUNT                --match-filter "view_count <=? COUNT"
+    --max-views COUNT                --match-filters "view_count <=? COUNT"
-    --break-on-reject                Use --break-match-filter
+    --break-on-reject                Use --break-match-filters
     --user-agent UA                  --add-header "User-Agent:UA"
     --referer URL                    --add-header "Referer:URL"
     --playlist-start NUMBER          -I NUMBER:

bundle/docker/static/entrypoint.sh

@@ -2,7 +2,7 @@
 set -e
 
 source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
-python -m devscripts.install_deps --include secretstorage
+python -m devscripts.install_deps --include secretstorage --include curl-cffi
 python -m devscripts.make_lazy_extractors
 python devscripts/update-version.py -c "${channel}" -r "${origin}" "${version}"
 python -m bundle.pyinstaller

devscripts/changelog_override.json

@@ -180,5 +180,21 @@
         "action": "add",
         "when": "6aaf96a3d6e7d0d426e97e11a2fcf52fda00e733",
         "short": "[priority] Security: [[CVE-2024-38519](https://nvd.nist.gov/vuln/detail/CVE-2024-38519)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)\n    - Unsafe extensions are now blocked from being downloaded"
+    },
+    {
+        "action": "add",
+        "when": "6075a029dba70a89675ae1250e7cdfd91f0eba41",
+        "short": "[priority] Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)\n    - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors"
+    },
+    {
+        "action": "add",
+        "when": "fb8b7f226d251e521a89b23c415e249e5b788e5c",
+        "short": "[priority] **The minimum *recommended* Python version has been raised to 3.9**\nSince Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)"
+    },
+    {
+        "action": "change",
+        "when": "b31b81d85f00601710d4fac590c3e4efb4133283",
+        "short": "[ci] Rerun failed tests (#11143)",
+        "authors": ["Grub4K"]
     }
 ]

devscripts/make_issue_template.py

@@ -46,6 +46,14 @@
       render: shell
     validations:
       required: true
+  - type: markdown
+    attributes:
+      value: |
+        > [!CAUTION]
+        > ### GitHub is experiencing a high volume of malicious spam comments.
+        > ### If you receive any replies asking you download a file, do NOT follow the download links!
+        >
+        > Note that this issue may be temporarily locked as an anti-spam measure after it is opened.
 '''.strip()
 
 NO_SKIP = '''

devscripts/make_lazy_extractors.py

@@ -2,7 +2,6 @@
 
 # Allow direct execution
 import os
-import shutil
 import sys
 
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -34,18 +33,14 @@ class {name}({bases}):
 
 
 def main():
+    os.environ['YTDLP_NO_PLUGINS'] = 'true'
+    os.environ['YTDLP_NO_LAZY_EXTRACTORS'] = 'true'
+
     lazy_extractors_filename = get_filename_args(default_outfile='yt_dlp/extractor/lazy_extractors.py')
-    if os.path.exists(lazy_extractors_filename):
-        os.remove(lazy_extractors_filename)
 
-    _ALL_CLASSES = get_all_ies()  # Must be before import
+    from yt_dlp.extractor.extractors import _ALL_CLASSES
-
-    import yt_dlp.plugins
     from yt_dlp.extractor.common import InfoExtractor, SearchInfoExtractor
 
-    # Filter out plugins
-    _ALL_CLASSES = [cls for cls in _ALL_CLASSES if not cls.__module__.startswith(f'{yt_dlp.plugins.PACKAGE_NAME}.')]
-
     DummyInfoExtractor = type('InfoExtractor', (InfoExtractor,), {'IE_NAME': NO_ATTR})
     module_src = '\n'.join((
         MODULE_TEMPLATE,
@@ -58,20 +53,6 @@ def main():
     write_file(lazy_extractors_filename, f'{module_src}\n')
 
 
-def get_all_ies():
-    PLUGINS_DIRNAME = 'ytdlp_plugins'
-    BLOCKED_DIRNAME = f'{PLUGINS_DIRNAME}_blocked'
-    if os.path.exists(PLUGINS_DIRNAME):
-        # os.rename cannot be used, e.g. in Docker. See https://github.com/yt-dlp/yt-dlp/pull/4958
-        shutil.move(PLUGINS_DIRNAME, BLOCKED_DIRNAME)
-    try:
-        from yt_dlp.extractor.extractors import _ALL_CLASSES
-    finally:
-        if os.path.exists(BLOCKED_DIRNAME):
-            shutil.move(BLOCKED_DIRNAME, PLUGINS_DIRNAME)
-    return _ALL_CLASSES
-
-
 def extra_ie_code(ie, base=None):
     for var in STATIC_CLASS_PROPERTIES:
         val = getattr(ie, var)

devscripts/run_tests.py

@@ -16,7 +16,7 @@
 def parse_args():
     parser = argparse.ArgumentParser(description='Run selected yt-dlp tests')
     parser.add_argument(
-        'test', help='a extractor tests, or one of "core" or "download"', nargs='*')
+        'test', help='an extractor test, test path, or one of "core" or "download"', nargs='*')
     parser.add_argument(
         '-k', help='run a test matching EXPRESSION. Same as "pytest -k"', metavar='EXPRESSION')
     parser.add_argument(
@@ -27,7 +27,6 @@ def parse_args():
 def run_tests(*tests, pattern=None, ci=False):
     run_core = 'core' in tests or (not pattern and not tests)
     run_download = 'download' in tests
-    tests = list(map(fix_test_name, tests))
 
     pytest_args = args.pytest_args or os.getenv('HATCH_TEST_ARGS', '')
     arguments = ['pytest', '-Werror', '--tb=short', *shlex.split(pytest_args)]
@@ -41,7 +40,9 @@ def run_tests(*tests, pattern=None, ci=False):
         arguments.extend(['-m', 'download'])
     else:
         arguments.extend(
-            f'test/test_download.py::TestDownload::test_{test}' for test in tests)
+            test if '/' in test
+            else f'test/test_download.py::TestDownload::test_{fix_test_name(test)}'
+            for test in tests)
 
     print(f'Running {arguments}', flush=True)
     try:

pyproject.toml

@@ -9,6 +9,7 @@ maintainers = [
     {name = "Grub4K", email = "contact@grub4k.xyz"},
     {name = "bashonly", email = "bashonly@protonmail.com"},
     {name = "coletdjnz", email = "coletdjnz@protonmail.com"},
+    {name = "sepro", email = "sepro@sepr0.com"},
 ]
 description = "A feature-rich command-line audio/video downloader"
 readme = "README.md"
@@ -48,12 +49,15 @@ dependencies = [
     "pycryptodomex",
     "requests>=2.32.2,<3",
     "urllib3>=1.26.17,<3",
-    "websockets>=12.0",
+    "websockets>=13.0",
 ]
 
 [project.optional-dependencies]
 default = []
-curl-cffi = ["curl-cffi==0.5.10; implementation_name=='cpython'"]
+curl-cffi = [
+    "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
+    "curl-cffi>=0.5.10,!=0.6.*,<0.7.2; os_name!='nt' and implementation_name=='cpython'",
+]
 secretstorage = [
     "cffi",
     "secretstorage",
@@ -62,7 +66,7 @@ build = [
     "build",
     "hatchling",
     "pip",
-    "setuptools",
+    "setuptools>=71.0.2",  # 71.0.0 broke pyinstaller
     "wheel",
 ]
 dev = [
@@ -72,13 +76,14 @@ dev = [
 ]
 static-analysis = [
     "autopep8~=2.0",
-    "ruff~=0.5.0",
+    "ruff~=0.6.0",
 ]
 test = [
     "pytest~=8.1",
+    "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.7.0",  # for compat with setuptools>=70
+    "pyinstaller>=6.10.0",  # Windows temp cleanup fixed in 6.10.0
 ]
 py2exe = [
     "py2exe>=0.12",
@@ -158,7 +163,6 @@ lint-fix = "ruff check --fix {args:.}"
 features = ["test"]
 dependencies = [
     "pytest-randomly~=3.15",
-    "pytest-rerunfailures~=14.0",
     "pytest-xdist[psutil]~=3.5",
 ]
 

supportedsites.md

@@ -143,6 +143,7 @@ # Supported sites
  - **BBVTV**: [*bbvtv*](## "netrc machine")
  - **BBVTVLive**: [*bbvtv*](## "netrc machine")
  - **BBVTVRecordings**: [*bbvtv*](## "netrc machine")
+ - **BeaconTv**
  - **BeatBumpPlaylist**
  - **BeatBumpVideo**
  - **Beatport**
@@ -354,7 +355,6 @@ # Supported sites
  - **DigitallySpeaking**
  - **Digiteka**
  - **DiscogsReleasePlaylist**
- - **Discovery**
  - **DiscoveryLife**
  - **DiscoveryNetworksDe**
  - **DiscoveryPlus**
@@ -363,7 +363,6 @@ # Supported sites
  - **DiscoveryPlusItaly**
  - **DiscoveryPlusItalyShow**
  - **Disney**
- - **DIYNetwork**
  - **dlf**
  - **dlf:corpus**: DLF Multi-feed Archives
  - **dlive:stream**
@@ -507,6 +506,7 @@ # Supported sites
  - **gem.cbc.ca:playlist**
  - **Genius**
  - **GeniusLyrics**
+ - **Germanupa**: germanupa.de
  - **GetCourseRu**: [*getcourseru*](## "netrc machine")
  - **GetCourseRuPlayer**
  - **Gettr**
@@ -516,7 +516,6 @@ # Supported sites
  - **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine")
  - **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine")
  - **Glide**: Glide mobile video messages (glide.me)
- - **GlobalCyclingNetworkPlus**
  - **GlobalPlayerAudio**
  - **GlobalPlayerAudioEpisode**
  - **GlobalPlayerLive**
@@ -583,6 +582,7 @@ # Supported sites
  - **HungamaAlbumPlaylist**
  - **HungamaSong**
  - **huya:live**: huya.com
+ - **huya:video**: 虎牙视频
  - **Hypem**
  - **Hytale**
  - **Icareus**
@@ -658,10 +658,12 @@ # Supported sites
  - **Ketnet**
  - **khanacademy**
  - **khanacademy:unit**
- - **Kick**
+ - **kick:clips**
+ - **kick:live**
+ - **kick:vod**
  - **Kicker**
  - **KickStarter**
- - **KickVOD**
+ - **Kika**: KiKA.de
  - **kinja:embed**
  - **KinoPoisk**
  - **Kommunetv**
@@ -693,6 +695,7 @@ # Supported sites
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
+ - **LearningOnScreen**
  - **Lecture2Go**: (**Currently broken**)
  - **Lecturio**: [*lecturio*](## "netrc machine")
  - **LecturioCourse**: [*lecturio*](## "netrc machine")
@@ -723,7 +726,6 @@ # Supported sites
  - **livestream:original**
  - **Livestreamfails**
  - **Lnk**
- - **LnkGo**
  - **loc**: Library of Congress
  - **loom**
  - **loom:folder**
@@ -757,7 +759,7 @@ # Supported sites
  - **Masters**
  - **MatchTV**
  - **MBN**: mbn.co.kr (매일방송)
- - **MDR**: MDR.DE and KiKA
+ - **MDR**: MDR.DE
  - **MedalTV**
  - **media.ccc.de**
  - **media.ccc.de:lists**
@@ -812,6 +814,7 @@ # Supported sites
  - **MNetTVLive**: [*mnettv*](## "netrc machine")
  - **MNetTVRecordings**: [*mnettv*](## "netrc machine")
  - **MochaVideo**
+ - **Mojevideo**: mojevideo.sk
  - **Mojvideo**
  - **Monstercat**
  - **MonsterSirenHypergryphMusic**
@@ -820,8 +823,6 @@ # Supported sites
  - **MotherlessGroup**
  - **MotherlessUploader**
  - **Motorsport**: motorsport.com (**Currently broken**)
- - **MotorTrend**
- - **MotorTrendOnDemand**
  - **MovieFap**
  - **Moviepilot**
  - **MoviewPlay**
@@ -1145,7 +1146,6 @@ # Supported sites
  - **QuantumTV**: [*quantumtv*](## "netrc machine")
  - **QuantumTVLive**: [*quantumtv*](## "netrc machine")
  - **QuantumTVRecordings**: [*quantumtv*](## "netrc machine")
- - **Qub**
  - **R7**: (**Currently broken**)
  - **R7Article**: (**Currently broken**)
  - **Radiko**
@@ -1289,12 +1289,14 @@ # Supported sites
  - **Screencast**
  - **Screencastify**
  - **ScreencastOMatic**
+ - **ScreenRec**
  - **ScrippsNetworks**
  - **scrippsnetworks:watch**
  - **Scrolller**
  - **SCTE**: [*scte*](## "netrc machine") (**Currently broken**)
  - **SCTECourse**: [*scte*](## "netrc machine") (**Currently broken**)
  - **sejm**
+ - **Sen**
  - **SenalColombiaLive**: (**Currently broken**)
  - **SenateGov**
  - **SenateISVP**
@@ -1331,6 +1333,7 @@ # Supported sites
  - **SlidesLive**
  - **Slutload**
  - **Smotrim**
+ - **SnapchatSpotlight**
  - **Snotr**
  - **Sohu**
  - **SohuV**
@@ -1522,9 +1525,9 @@ # Supported sites
  - **tv5unis**
  - **tv5unis:video**
  - **tv8.it**
- - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
+ - **tvaplus**: TVA+
  - **TVC**
  - **TVCArticle**
  - **TVer**
@@ -1612,12 +1615,14 @@ # Supported sites
  - **videomore:season**
  - **videomore:video**
  - **VideoPress**
+ - **Vidflex**
  - **Vidio**: [*vidio*](## "netrc machine")
  - **VidioLive**: [*vidio*](## "netrc machine")
  - **VidioPremier**: [*vidio*](## "netrc machine")
  - **VidLii**
  - **Vidly**
  - **vids.io**
+ - **Vidyard**
  - **viewlift**
  - **viewlift:embed**
  - **Viidea**
@@ -1665,6 +1670,8 @@ # Supported sites
  - **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
  - **VrtNU**: [*vrtnu*](## "netrc machine") VRT MAX
  - **VTM**: (**Currently broken**)
+ - **VTV**
+ - **VTVGo**
  - **VTXTV**: [*vtxtv*](## "netrc machine")
  - **VTXTVLive**: [*vtxtv*](## "netrc machine")
  - **VTXTVRecordings**: [*vtxtv*](## "netrc machine")
@@ -1737,7 +1744,7 @@ # Supported sites
  - **XiaoHongShu**: 小红书
  - **ximalaya**: 喜马拉雅FM
  - **ximalaya:album**: 喜马拉雅FM 专辑
- - **xinpianchang**: xinpianchang.com (**Currently broken**)
+ - **Xinpianchang**: 新片场
  - **XMinus**: (**Currently broken**)
  - **XNXX**
  - **Xstream**

test/test_YoutubeDL.py

@@ -4,6 +4,7 @@
 import os
 import sys
 import unittest
+from unittest.mock import patch
 
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
@@ -235,6 +236,35 @@ def test_format_selection_video(self):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
 
+    def test_format_selection_by_vcodec_sort(self):
+        formats = [
+            {'format_id': 'av1-format', 'ext': 'mp4', 'vcodec': 'av1', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vp9-hdr-format', 'ext': 'mp4', 'vcodec': 'vp09.02.50.10.01.09.18.09.00', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vp9-sdr-format', 'ext': 'mp4', 'vcodec': 'vp09.00.50.08', 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'h265-format', 'ext': 'mp4', 'vcodec': 'h265', 'acodec': 'none', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9.2']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-hdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-sdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9.2']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-hdr-format')
+
+        ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9']})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vp9-sdr-format')
+
     def test_format_selection_string_ops(self):
         formats = [
             {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
@@ -520,7 +550,33 @@ def test_format_filtering(self):
             ydl.process_ie_result(info_dict)
         self.assertEqual(ydl.downloaded_info_dicts, [])
 
-    def test_default_format_spec(self):
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
+    def test_default_format_spec_without_ffmpeg(self):
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'simulate': True})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'simulate': True})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'outtmpl': '-'})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', True)
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.can_merge', lambda _: True)
+    def test_default_format_spec_with_ffmpeg(self):
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
+
         ydl = YDL({'simulate': True})
         self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
 
@@ -528,13 +584,13 @@ def test_default_format_spec(self):
         self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({'simulate': True})
-        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({'outtmpl': '-'})
         self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({})
-        self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
+        self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
         self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
 

test/test_jsinterp.py

@@ -376,6 +376,61 @@ def test_packed(self):
         jsi = JSInterpreter('''function f(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}''')
         self.assertEqual(jsi.call_function('f', '''h 7=g("1j");7.7h({7g:[{33:"w://7f-7e-7d-7c.v.7b/7a/79/78/77/76.74?t=73&s=2s&e=72&f=2t&71=70.0.0.1&6z=6y&6x=6w"}],6v:"w://32.v.u/6u.31",16:"r%",15:"r%",6t:"6s",6r:"",6q:"l",6p:"l",6o:"6n",6m:\'6l\',6k:"6j",9:[{33:"/2u?b=6i&n=50&6h=w://32.v.u/6g.31",6f:"6e"}],1y:{6d:1,6c:\'#6b\',6a:\'#69\',68:"67",66:30,65:r,},"64":{63:"%62 2m%m%61%5z%5y%5x.u%5w%5v%5u.2y%22 2k%m%1o%22 5t%m%1o%22 5s%m%1o%22 2j%m%5r%22 16%m%5q%22 15%m%5p%22 5o%2z%5n%5m%2z",5l:"w://v.u/d/1k/5k.2y",5j:[]},\'5i\':{"5h":"5g"},5f:"5e",5d:"w://v.u",5c:{},5b:l,1x:[0.25,0.50,0.75,1,1.25,1.5,2]});h 1m,1n,5a;h 59=0,58=0;h 7=g("1j");h 2x=0,57=0,56=0;$.55({54:{\'53-52\':\'2i-51\'}});7.j(\'4z\',6(x){c(5>0&&x.1l>=5&&1n!=1){1n=1;$(\'q.4y\').4x(\'4w\')}});7.j(\'13\',6(x){2x=x.1l});7.j(\'2g\',6(x){2w(x)});7.j(\'4v\',6(){$(\'q.2v\').4u()});6 2w(x){$(\'q.2v\').4t();c(1m)19;1m=1;17=0;c(4s.4r===l){17=1}$.4q(\'/2u?b=4p&2l=1k&4o=2t-4n-4m-2s-4l&4k=&4j=&4i=&17=\'+17,6(2r){$(\'#4h\').4g(2r)});$(\'.3-8-4f-4e:4d("4c")\').2h(6(e){2q();g().4b(0);g().4a(l)});6 2q(){h $14=$("<q />").2p({1l:"49",16:"r%",15:"r%",48:0,2n:0,2o:47,46:"45(10%, 10%, 10%, 0.4)","44-43":"42"});$("<41 />").2p({16:"60%",15:"60%",2o:40,"3z-2n":"3y"}).3x({\'2m\':\'/?b=3w&2l=1k\',\'2k\':\'0\',\'2j\':\'2i\'}).2f($14);$14.2h(6(){$(3v).3u();g().2g()});$14.2f($(\'#1j\'))}g().13(0);}6 3t(){h 9=7.1b(2e);2d.2c(9);c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==2e){2d.2c(\'!!=\'+i);7.1p(i)}}}}7.j(\'3s\',6(){g().1h("/2a/3r.29","3q 10 28",6(){g().13(g().27()+10)},"2b");$("q[26=2b]").23().21(\'.3-20-1z\');g().1h("/2a/3p.29","3o 10 28",6(){h 12=g().27()-10;c(12<0)12=0;g().13(12)},"24");$("q[26=24]").23().21(\'.3-20-1z\');});6 1i(){}7.j(\'3n\',6(){1i()});7.j(\'3m\',6(){1i()});7.j("k",6(y){h 9=7.1b();c(9.n<2)19;$(\'.3-8-3l-3k\').3j(6(){$(\'#3-8-a-k\').1e(\'3-8-a-z\');$(\'.3-a-k\').p(\'o-1f\',\'11\')});7.1h("/3i/3h.3g","3f 3e",6(){$(\'.3-1w\').3d(\'3-8-1v\');$(\'.3-8-1y, .3-8-1x\').p(\'o-1g\',\'11\');c($(\'.3-1w\').3c(\'3-8-1v\')){$(\'.3-a-k\').p(\'o-1g\',\'l\');$(\'.3-a-k\').p(\'o-1f\',\'l\');$(\'.3-8-a\').1e(\'3-8-a-z\');$(\'.3-8-a:1u\').3b(\'3-8-a-z\')}3a{$(\'.3-a-k\').p(\'o-1g\',\'11\');$(\'.3-a-k\').p(\'o-1f\',\'11\');$(\'.3-8-a:1u\').1e(\'3-8-a-z\')}},"39");7.j("38",6(y){1d.37(\'1c\',y.9[y.36].1a)});c(1d.1t(\'1c\')){35("1s(1d.1t(\'1c\'));",34)}});h 18;6 1s(1q){h 9=7.1b();c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==1q){c(i==18){19}18=i;7.1p(i)}}}}',36,270,'|||jw|||function|player|settings|tracks|submenu||if||||jwplayer|var||on|audioTracks|true|3D|length|aria|attr|div|100|||sx|filemoon|https||event|active||false|tt|seek|dd|height|width|adb|current_audio|return|name|getAudioTracks|default_audio|localStorage|removeClass|expanded|checked|addButton|callMeMaybe|vplayer|0fxcyc2ajhp1|position|vvplay|vvad|220|setCurrentAudioTrack|audio_name|for|audio_set|getItem|last|open|controls|playbackRates|captions|rewind|icon|insertAfter||detach|ff00||button|getPosition|sec|png|player8|ff11|log|console|track_name|appendTo|play|click|no|scrolling|frameborder|file_code|src|top|zIndex|css|showCCform|data|1662367683|383371|dl|video_ad|doPlay|prevt|mp4|3E||jpg|thumbs|file|300|setTimeout|currentTrack|setItem|audioTrackChanged|dualSound|else|addClass|hasClass|toggleClass|Track|Audio|svg|dualy|images|mousedown|buttons|topbar|playAttemptFailed|beforePlay|Rewind|fr|Forward|ff|ready|set_audio_track|remove|this|upload_srt|prop|50px|margin|1000001|iframe|center|align|text|rgba|background|1000000|left|absolute|pause|setCurrentCaptions|Upload|contains|item|content|html|fviews|referer|prem|embed|3e57249ef633e0d03bf76ceb8d8a4b65|216|83|hash|view|get|TokenZir|window|hide|show|complete|slow|fadeIn|video_ad_fadein|time||cache|Cache|Content|headers|ajaxSetup|v2done|tott|vastdone2|vastdone1|vvbefore|playbackRateControls|cast|aboutlink|FileMoon|abouttext|UHD|1870|qualityLabels|sites|GNOME_POWER|link|2Fiframe|3C|allowfullscreen|22360|22640|22no|marginheight|marginwidth|2FGNOME_POWER|2F0fxcyc2ajhp1|2Fe|2Ffilemoon|2F|3A||22https|3Ciframe|code|sharing|fontOpacity|backgroundOpacity|Tahoma|fontFamily|303030|backgroundColor|FFFFFF|color|userFontScale|thumbnails|kind|0fxcyc2ajhp10000|url|get_slides|start|startparam|none|preload|html5|primary|hlshtml|androidhls|duration|uniform|stretching|0fxcyc2ajhp1_xt|image|2048|sp|6871|asn|127|srv|43200|_g3XlBcu2lmD9oDexD2NLWSmah2Nu3XcDrl93m9PwXY|m3u8||master|0fxcyc2ajhp1_x|00076|01|hls2|to|s01|delivery|storage|moon|sources|setup'''.split('|')))
 
+    def test_join(self):
+        test_input = list('test')
+        tests = [
+            'function f(a, b){return a.join(b)}',
+            'function f(a, b){return Array.prototype.join.call(a, b)}',
+            'function f(a, b){return Array.prototype.join.apply(a, [b])}',
+        ]
+        for test in tests:
+            jsi = JSInterpreter(test)
+            self._test(jsi, 'test', args=[test_input, ''])
+            self._test(jsi, 't-e-s-t', args=[test_input, '-'])
+            self._test(jsi, '', args=[[], '-'])
+
+    def test_split(self):
+        test_result = list('test')
+        tests = [
+            'function f(a, b){return a.split(b)}',
+            'function f(a, b){return String.prototype.split.call(a, b)}',
+            'function f(a, b){return String.prototype.split.apply(a, [b])}',
+        ]
+        for test in tests:
+            jsi = JSInterpreter(test)
+            self._test(jsi, test_result, args=['test', ''])
+            self._test(jsi, test_result, args=['t-e-s-t', '-'])
+            self._test(jsi, [''], args=['', '-'])
+            self._test(jsi, [], args=['', ''])
+
+    def test_slice(self):
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
+        self._test('function f(){return "012345678".slice()}', '012345678')
+        self._test('function f(){return "012345678".slice(0)}', '012345678')
+        self._test('function f(){return "012345678".slice(5)}', '5678')
+        self._test('function f(){return "012345678".slice(99)}', '')
+        self._test('function f(){return "012345678".slice(-2)}', '78')
+        self._test('function f(){return "012345678".slice(-99)}', '012345678')
+        self._test('function f(){return "012345678".slice(0, 0)}', '')
+        self._test('function f(){return "012345678".slice(1, 0)}', '')
+        self._test('function f(){return "012345678".slice(0, 1)}', '0')
+        self._test('function f(){return "012345678".slice(3, 6)}', '345')
+        self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
+        self._test('function f(){return "012345678".slice(-1, 1)}', '')
+        self._test('function f(){return "012345678".slice(-3, -1)}', '67')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_networking.py

@@ -265,6 +265,11 @@ def do_GET(self):
             self.end_headers()
             self.wfile.write(payload)
             self.finish()
+        elif self.path == '/get_cookie':
+            self.send_response(200)
+            self.send_header('Set-Cookie', 'test=ytdlp; path=/')
+            self.end_headers()
+            self.finish()
         else:
             self._status(404)
 
@@ -338,6 +343,52 @@ def test_ssl_error(self, handler):
                 validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 
+    @pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
+    def test_legacy_ssl_extension(self, handler):
+        # HTTPS server with old ciphers
+        # XXX: is there a better way to test this than to create a new server?
+        https_httpd = http.server.ThreadingHTTPServer(
+            ('127.0.0.1', 0), HTTPTestRequestHandler)
+        sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+        sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
+        sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
+        sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
+        https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
+        https_port = http_server_port(https_httpd)
+        https_server_thread = threading.Thread(target=https_httpd.serve_forever)
+        https_server_thread.daemon = True
+        https_server_thread.start()
+
+        with handler(verify=False) as rh:
+            res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers', extensions={'legacy_ssl': True}))
+            assert res.status == 200
+            res.close()
+
+            # Ensure only applies to request extension
+            with pytest.raises(SSLError):
+                validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
+
+    @pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
+    def test_legacy_ssl_support(self, handler):
+        # HTTPS server with old ciphers
+        # XXX: is there a better way to test this than to create a new server?
+        https_httpd = http.server.ThreadingHTTPServer(
+            ('127.0.0.1', 0), HTTPTestRequestHandler)
+        sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+        sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
+        sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
+        sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
+        https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
+        https_port = http_server_port(https_httpd)
+        https_server_thread = threading.Thread(target=https_httpd.serve_forever)
+        https_server_thread.daemon = True
+        https_server_thread.start()
+
+        with handler(verify=False, legacy_ssl_support=True) as rh:
+            res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
+            assert res.status == 200
+            res.close()
+
     def test_percent_encode(self, handler):
         with handler() as rh:
             # Unicode characters should be encoded with uppercase percent-encoding
@@ -490,6 +541,24 @@ def test_cookies(self, handler):
                 rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': cookiejar})).read()
             assert b'cookie: test=ytdlp' in data.lower()
 
+    def test_cookie_sync_only_cookiejar(self, handler):
+        # Ensure that cookies are ONLY being handled by the cookiejar
+        with handler() as rh:
+            validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
+            data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': YoutubeDLCookieJar()})).read()
+            assert b'cookie: test=ytdlp' not in data.lower()
+
+    def test_cookie_sync_delete_cookie(self, handler):
+        # Ensure that cookies are ONLY being handled by the cookiejar
+        cookiejar = YoutubeDLCookieJar()
+        with handler(cookiejar=cookiejar) as rh:
+            validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie'))
+            data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
+            assert b'cookie: test=ytdlp' in data.lower()
+            cookiejar.clear_session_cookies()
+            data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
+            assert b'cookie: test=ytdlp' not in data.lower()
+
     def test_headers(self, handler):
 
         with handler(headers=HTTPHeaderDict({'test1': 'test', 'test2': 'test2'})) as rh:
@@ -753,6 +822,24 @@ def test_remove_logging_handler(self, handler, logger_name):
         rh.close()
         assert len(logging_handlers) == before_count
 
+    def test_wrap_request_errors(self):
+        class TestRequestHandler(RequestHandler):
+            def _validate(self, request):
+                if request.headers.get('x-fail'):
+                    raise UnsupportedRequest('test error')
+
+            def _send(self, request: Request):
+                raise RequestError('test error')
+
+        with TestRequestHandler(logger=FakeLogger()) as rh:
+            with pytest.raises(UnsupportedRequest, match='test error') as exc_info:
+                rh.validate(Request('http://example.com', headers={'x-fail': '1'}))
+            assert exc_info.value.handler is rh
+
+            with pytest.raises(RequestError, match='test error') as exc_info:
+                rh.send(Request('http://example.com'))
+            assert exc_info.value.handler is rh
+
 
 @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
 class TestUrllibRequestHandler(TestRequestHandlerBase):
@@ -914,7 +1001,6 @@ def mock_close(*args, **kwargs):
 class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
 
     @pytest.mark.parametrize('params,extensions', [
-        ({}, {'impersonate': ImpersonateTarget('chrome')}),
         ({'impersonate': ImpersonateTarget('chrome', '110')}, {}),
         ({'impersonate': ImpersonateTarget('chrome', '99')}, {'impersonate': ImpersonateTarget('chrome', '110')}),
     ])
@@ -1200,6 +1286,9 @@ class HTTPSupportedRH(ValidationRH):
             ({'timeout': 1}, False),
             ({'timeout': 'notatimeout'}, AssertionError),
             ({'unsupported': 'value'}, UnsupportedRequest),
+            ({'legacy_ssl': False}, False),
+            ({'legacy_ssl': True}, False),
+            ({'legacy_ssl': 'notabool'}, AssertionError),
         ]),
         ('Requests', 'http', [
             ({'cookiejar': 'notacookiejar'}, AssertionError),
@@ -1207,6 +1296,9 @@ class HTTPSupportedRH(ValidationRH):
             ({'timeout': 1}, False),
             ({'timeout': 'notatimeout'}, AssertionError),
             ({'unsupported': 'value'}, UnsupportedRequest),
+            ({'legacy_ssl': False}, False),
+            ({'legacy_ssl': True}, False),
+            ({'legacy_ssl': 'notabool'}, AssertionError),
         ]),
         ('CurlCFFI', 'http', [
             ({'cookiejar': 'notacookiejar'}, AssertionError),
@@ -1220,6 +1312,9 @@ class HTTPSupportedRH(ValidationRH):
             ({'impersonate': ImpersonateTarget(None, None, None, None)}, False),
             ({'impersonate': ImpersonateTarget()}, False),
             ({'impersonate': 'chrome'}, AssertionError),
+            ({'legacy_ssl': False}, False),
+            ({'legacy_ssl': True}, False),
+            ({'legacy_ssl': 'notabool'}, AssertionError),
         ]),
         (NoCheckRH, 'http', [
             ({'cookiejar': 'notacookiejar'}, False),
@@ -1228,6 +1323,9 @@ class HTTPSupportedRH(ValidationRH):
         ('Websockets', 'ws', [
             ({'cookiejar': YoutubeDLCookieJar()}, False),
             ({'timeout': 2}, False),
+            ({'legacy_ssl': False}, False),
+            ({'legacy_ssl': True}, False),
+            ({'legacy_ssl': 'notabool'}, AssertionError),
         ]),
     ]
 

test/test_traversal.py

@@ -4,8 +4,18 @@
 
 import pytest
 
-from yt_dlp.utils import dict_get, int_or_none, str_or_none
+from yt_dlp.utils import (
-from yt_dlp.utils.traversal import traverse_obj
+    ExtractorError,
+    determine_ext,
+    dict_get,
+    int_or_none,
+    str_or_none,
+)
+from yt_dlp.utils.traversal import (
+    traverse_obj,
+    require,
+    subs_list_to_dict,
+)
 
 _TEST_DATA = {
     100: 100,
@@ -420,6 +430,71 @@ def test_traversal_morsel(self):
         assert traverse_obj(morsel, [(None,), any]) == morsel, \
             'Morsel should not be implicitly changed to dict on usage'
 
+    def test_traversal_filter(self):
+        data = [None, False, True, 0, 1, 0.0, 1.1, '', 'str', {}, {0: 0}, [], [1]]
+
+        assert traverse_obj(data, [..., filter]) == [True, 1, 1.1, 'str', {0: 0}, [1]], \
+            '`filter` should filter falsy values'
+
+
+class TestTraversalHelpers:
+    def test_traversal_require(self):
+        with pytest.raises(ExtractorError):
+            traverse_obj(_TEST_DATA, ['None', {require('value')}])
+        assert traverse_obj(_TEST_DATA, ['str', {require('value')}]) == 'str', \
+            '`require` should pass through non `None` values'
+
+    def test_subs_list_to_dict(self):
+        assert traverse_obj([
+            {'name': 'de', 'url': 'https://example.com/subs/de.vtt'},
+            {'name': 'en', 'url': 'https://example.com/subs/en1.ass'},
+            {'name': 'en', 'url': 'https://example.com/subs/en2.ass'},
+        ], [..., {
+            'id': 'name',
+            'url': 'url',
+        }, all, {subs_list_to_dict}]) == {
+            'de': [{'url': 'https://example.com/subs/de.vtt'}],
+            'en': [
+                {'url': 'https://example.com/subs/en1.ass'},
+                {'url': 'https://example.com/subs/en2.ass'},
+            ],
+        }, 'function should build subtitle dict from list of subtitles'
+        assert traverse_obj([
+            {'name': 'de', 'url': 'https://example.com/subs/de.ass'},
+            {'name': 'de'},
+            {'name': 'en', 'content': 'content'},
+            {'url': 'https://example.com/subs/en'},
+        ], [..., {
+            'id': 'name',
+            'data': 'content',
+            'url': 'url',
+        }, all, {subs_list_to_dict}]) == {
+            'de': [{'url': 'https://example.com/subs/de.ass'}],
+            'en': [{'data': 'content'}],
+        }, 'subs with mandatory items missing should be filtered'
+        assert traverse_obj([
+            {'url': 'https://example.com/subs/de.ass', 'name': 'de'},
+            {'url': 'https://example.com/subs/en', 'name': 'en'},
+        ], [..., {
+            'id': 'name',
+            'ext': ['url', {lambda x: determine_ext(x, default_ext=None)}],
+            'url': 'url',
+        }, all, {subs_list_to_dict(ext='ext')}]) == {
+            'de': [{'url': 'https://example.com/subs/de.ass', 'ext': 'ass'}],
+            'en': [{'url': 'https://example.com/subs/en', 'ext': 'ext'}],
+        }, '`ext` should set default ext but leave existing value untouched'
+        assert traverse_obj([
+            {'name': 'en', 'url': 'https://example.com/subs/en2', 'prio': True},
+            {'name': 'en', 'url': 'https://example.com/subs/en1', 'prio': False},
+        ], [..., {
+            'id': 'name',
+            'quality': ['prio', {int}],
+            'url': 'url',
+        }, all, {subs_list_to_dict(ext='ext')}]) == {'en': [
+            {'url': 'https://example.com/subs/en1', 'ext': 'ext'},
+            {'url': 'https://example.com/subs/en2', 'ext': 'ext'},
+        ]}, '`quality` key should sort subtitle list accordingly'
+
 
 class TestDictGet:
     def test_dict_get(self):

test/test_utils.py

@@ -221,9 +221,10 @@ def test_sanitize_ids(self):
         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 
     def test_sanitize_path(self):
-        if sys.platform != 'win32':
+        with unittest.mock.patch('sys.platform', 'win32'):
-            return
+            self._test_sanitize_path()
 
+    def _test_sanitize_path(self):
         self.assertEqual(sanitize_path('abc'), 'abc')
         self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
         self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
@@ -256,6 +257,11 @@ def test_sanitize_path(self):
         self.assertEqual(sanitize_path('./abc'), 'abc')
         self.assertEqual(sanitize_path('./../abc'), '..\\abc')
 
+        self.assertEqual(sanitize_path('\\abc'), '\\abc')
+        self.assertEqual(sanitize_path('C:abc'), 'C:abc')
+        self.assertEqual(sanitize_path('C:abc\\..\\'), 'C:..')
+        self.assertEqual(sanitize_path('C:\\abc:%(title)s.%(ext)s'), 'C:\\abc#%(title)s.%(ext)s')
+
     def test_sanitize_url(self):
         self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
         self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
@@ -444,6 +450,8 @@ def test_unified_timestamps(self):
         self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
         self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
         self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
+        self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600)
+        self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200)
 
         self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
         self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
@@ -919,6 +927,11 @@ def test_parse_codecs(self):
             'acodec': 'none',
             'dynamic_range': 'HDR10',
         })
+        self.assertEqual(parse_codecs('vp09.02.50.10.01.09.18.09.00'), {
+            'vcodec': 'vp09.02.50.10.01.09.18.09.00',
+            'acodec': 'none',
+            'dynamic_range': 'HDR10',
+        })
         self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), {
             'vcodec': 'av01.0.12M.10.0.110.09.16.09.0',
             'acodec': 'none',
@@ -929,6 +942,11 @@ def test_parse_codecs(self):
             'acodec': 'none',
             'dynamic_range': 'DV',
         })
+        self.assertEqual(parse_codecs('fLaC'), {
+            'vcodec': 'none',
+            'acodec': 'flac',
+            'dynamic_range': None,
+        })
         self.assertEqual(parse_codecs('theora, vorbis'), {
             'vcodec': 'theora',
             'acodec': 'vorbis',

test/test_websockets.py

@@ -61,6 +61,10 @@ def process_request(self, request):
             return websockets.http11.Response(
                 status.value, status.phrase, websockets.datastructures.Headers([('Location', '/')]), b'')
         return self.protocol.reject(status.value, status.phrase)
+    elif request.path.startswith('/get_cookie'):
+        response = self.protocol.accept(request)
+        response.headers['Set-Cookie'] = 'test=ytdlp'
+        return response
     return self.protocol.accept(request)
 
 
@@ -84,7 +88,7 @@ def create_wss_websocket_server():
     certfn = os.path.join(TEST_DIR, 'testcert.pem')
     sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
     sslctx.load_cert_chain(certfn, None)
-    return create_websocket_server(ssl_context=sslctx)
+    return create_websocket_server(ssl=sslctx)
 
 
 MTLS_CERT_DIR = os.path.join(TEST_DIR, 'testdata', 'certificate')
@@ -99,7 +103,16 @@ def create_mtls_wss_websocket_server():
     sslctx.load_verify_locations(cafile=cacertfn)
     sslctx.load_cert_chain(certfn, None)
 
-    return create_websocket_server(ssl_context=sslctx)
+    return create_websocket_server(ssl=sslctx)
+
+
+def create_legacy_wss_websocket_server():
+    certfn = os.path.join(TEST_DIR, 'testcert.pem')
+    sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+    sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
+    sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
+    sslctx.load_cert_chain(certfn, None)
+    return create_websocket_server(ssl=sslctx)
 
 
 def ws_validate_and_send(rh, req):
@@ -126,12 +139,15 @@ def setup_class(cls):
         cls.wss_thread, cls.wss_port = create_wss_websocket_server()
         cls.wss_base_url = f'wss://127.0.0.1:{cls.wss_port}'
 
-        cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl_context=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER))
+        cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER))
         cls.bad_wss_host = f'wss://127.0.0.1:{cls.bad_wss_port}'
 
         cls.mtls_wss_thread, cls.mtls_wss_port = create_mtls_wss_websocket_server()
         cls.mtls_wss_base_url = f'wss://127.0.0.1:{cls.mtls_wss_port}'
 
+        cls.legacy_wss_thread, cls.legacy_wss_port = create_legacy_wss_websocket_server()
+        cls.legacy_wss_host = f'wss://127.0.0.1:{cls.legacy_wss_port}'
+
     def test_basic_websockets(self, handler):
         with handler() as rh:
             ws = ws_validate_and_send(rh, Request(self.ws_base_url))
@@ -166,6 +182,22 @@ def test_ssl_error(self, handler):
                 ws_validate_and_send(rh, Request(self.bad_wss_host))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 
+    def test_legacy_ssl_extension(self, handler):
+        with handler(verify=False) as rh:
+            ws = ws_validate_and_send(rh, Request(self.legacy_wss_host, extensions={'legacy_ssl': True}))
+            assert ws.status == 101
+            ws.close()
+
+            # Ensure only applies to request extension
+            with pytest.raises(SSLError):
+                ws_validate_and_send(rh, Request(self.legacy_wss_host))
+
+    def test_legacy_ssl_support(self, handler):
+        with handler(verify=False, legacy_ssl_support=True) as rh:
+            ws = ws_validate_and_send(rh, Request(self.legacy_wss_host))
+            assert ws.status == 101
+            ws.close()
+
     @pytest.mark.parametrize('path,expected', [
         # Unicode characters should be encoded with uppercase percent-encoding
         ('/中文', '/%E4%B8%AD%E6%96%87'),
@@ -248,6 +280,32 @@ def test_cookies(self, handler):
             assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
             ws.close()
 
+    @pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
+    def test_cookie_sync_only_cookiejar(self, handler):
+        # Ensure that cookies are ONLY being handled by the cookiejar
+        with handler() as rh:
+            ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
+            ws = ws_validate_and_send(rh, Request(self.ws_base_url, extensions={'cookiejar': YoutubeDLCookieJar()}))
+            ws.send('headers')
+            assert 'cookie' not in json.loads(ws.recv())
+            ws.close()
+
+    @pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
+    def test_cookie_sync_delete_cookie(self, handler):
+        # Ensure that cookies are ONLY being handled by the cookiejar
+        cookiejar = YoutubeDLCookieJar()
+        with handler(verbose=True, cookiejar=cookiejar) as rh:
+            ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie'))
+            ws = ws_validate_and_send(rh, Request(self.ws_base_url))
+            ws.send('headers')
+            assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
+            ws.close()
+            cookiejar.clear_session_cookies()
+            ws = ws_validate_and_send(rh, Request(self.ws_base_url))
+            ws.send('headers')
+            assert 'cookie' not in json.loads(ws.recv())
+            ws.close()
+
     def test_source_address(self, handler):
         source_address = f'127.0.0.{random.randint(5, 255)}'
         verify_address_availability(source_address)

test/test_youtube_signature.py

@@ -167,6 +167,22 @@
         'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
         '1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
     ),
+    (
+        'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
+        'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
+    ),
+    (
+        'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
+        'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
+    ),
+    (
+        'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
+        '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
+    ),
+    (
+        'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
+        'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
+    ),
 ]
 
 

yt_dlp/YoutubeDL.py

@@ -27,7 +27,7 @@
 from .cache import Cache
 from .compat import urllib  # isort: split
 from .compat import compat_os_name, urllib_req_to_req
-from .cookies import LenientSimpleCookie, load_cookies
+from .cookies import CookieLoadError, LenientSimpleCookie, load_cookies
 from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
 from .downloader.rtmp import rtmpdump_version
 from .extractor import gen_extractor_classes, get_info_extractor
@@ -452,7 +452,8 @@ class YoutubeDL:
                        Can also just be a single color policy,
                        in which case it applies to all outputs.
                        Valid stream names are 'stdout' and 'stderr'.
-                       Valid color policies are one of 'always', 'auto', 'no_color' or 'never'.
+                       Valid color policies are one of 'always', 'auto',
+                       'no_color', 'never', 'auto-tty' or 'no_color-tty'.
     geo_bypass:        Bypass geographic restriction via faking X-Forwarded-For
                        HTTP header
     geo_bypass_country:
@@ -659,12 +660,15 @@ def __init__(self, params=None, auto_init=True):
             self.params['color'] = 'no_color'
 
         term_allow_color = os.getenv('TERM', '').lower() != 'dumb'
-        no_color = bool(os.getenv('NO_COLOR'))
+        base_no_color = bool(os.getenv('NO_COLOR'))
 
         def process_color_policy(stream):
             stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream]
-            policy = traverse_obj(self.params, ('color', (stream_name, None), {str}), get_all=False)
+            policy = traverse_obj(self.params, ('color', (stream_name, None), {str}, any)) or 'auto'
-            if policy in ('auto', None):
+            if policy in ('auto', 'auto-tty', 'no_color-tty'):
+                no_color = base_no_color
+                if policy.endswith('tty'):
+                    no_color = policy.startswith('no_color')
                 if term_allow_color and supports_terminal_sequences(stream):
                     return 'no_color' if no_color else True
                 return False
@@ -1621,7 +1625,7 @@ def wrapper(self, *args, **kwargs):
             while True:
                 try:
                     return func(self, *args, **kwargs)
-                except (DownloadCancelled, LazyList.IndexError, PagedList.IndexError):
+                except (CookieLoadError, DownloadCancelled, LazyList.IndexError, PagedList.IndexError):
                     raise
                 except ReExtractInfo as e:
                     if e.expected:
@@ -2191,9 +2195,8 @@ def _select_formats(self, formats, selector):
                                    or all(f.get('acodec') == 'none' for f in formats)),  # OR, No formats with audio
         }))
 
-    def _default_format_spec(self, info_dict, download=True):
+    def _default_format_spec(self, info_dict):
-        download = download and not self.params.get('simulate')
+        prefer_best = (
-        prefer_best = download and (
             self.params['outtmpl']['default'] == '-'
             or info_dict.get('is_live') and not self.params.get('live_from_start'))
 
@@ -2201,7 +2204,7 @@ def can_merge():
             merger = FFmpegMergerPP(self)
             return merger.available and merger.can_merge()
 
-        if not prefer_best and download and not can_merge():
+        if not prefer_best and not can_merge():
             prefer_best = True
             formats = self._get_formats(info_dict)
             evaluate_formats = lambda spec: self._select_formats(formats, self.build_format_selector(spec))
@@ -2960,7 +2963,7 @@ def is_wellformed(f):
                     continue
 
             if format_selector is None:
-                req_format = self._default_format_spec(info_dict, download=download)
+                req_format = self._default_format_spec(info_dict)
                 self.write_debug(f'Default format spec: {req_format}')
                 format_selector = self.build_format_selector(req_format)
 
@@ -3170,11 +3173,12 @@ def dl(self, name, info, subtitle=False, test=False):
 
         if test:
             verbose = self.params.get('verbose')
+            quiet = self.params.get('quiet') or not verbose
             params = {
                 'test': True,
-                'quiet': self.params.get('quiet') or not verbose,
+                'quiet': quiet,
                 'verbose': verbose,
-                'noprogress': not verbose,
+                'noprogress': quiet,
                 'nopart': True,
                 'skip_unavailable_fragments': False,
                 'keep_fragments': False,
@@ -3577,6 +3581,8 @@ def __download_wrapper(self, func):
         def wrapper(*args, **kwargs):
             try:
                 res = func(*args, **kwargs)
+            except CookieLoadError:
+                raise
             except UnavailableVideoError as e:
                 self.report_error(e)
             except DownloadCancelled as e:
@@ -4065,6 +4071,10 @@ def get_encoding(stream):
 
         write_debug(f'Proxy map: {self.proxies}')
         write_debug(f'Request Handlers: {", ".join(rh.RH_NAME for rh in self._request_director.handlers.values())}')
+        if os.environ.get('YTDLP_NO_PLUGINS'):
+            write_debug('Plugins are forcibly disabled')
+            return
+
         for plugin_type, plugins in {'Extractor': plugin_ies, 'Post-Processor': plugin_pps}.items():
             display_list = ['{}{}'.format(
                 klass.__name__, '' if klass.__name__ == name else f' as {name}')
@@ -4110,8 +4120,14 @@ def proxies(self):
     @functools.cached_property
     def cookiejar(self):
         """Global cookiejar instance"""
-        return load_cookies(
+        try:
-            self.params.get('cookiefile'), self.params.get('cookiesfrombrowser'), self)
+            return load_cookies(
+                self.params.get('cookiefile'), self.params.get('cookiesfrombrowser'), self)
+        except CookieLoadError as error:
+            cause = error.__context__
+            # compat: <=py3.9: `traceback.format_exception` has a different signature
+            self.report_error(str(cause), tb=''.join(traceback.format_exception(None, cause, cause.__traceback__)))
+            raise
 
     @property
     def _opener(self):

yt_dlp/__init__.py

@@ -15,7 +15,7 @@
 import traceback
 
 from .compat import compat_os_name
-from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
+from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS, CookieLoadError
 from .downloader.external import get_external_downloader
 from .extractor import list_extractor_classes
 from .extractor.adobepass import MSO_INFO
@@ -235,6 +235,11 @@ def validate_minmax(min_val, max_val, min_name, max_name=None):
         validate_regex('format sorting', f, FormatSorter.regex)
 
     # Postprocessor formats
+    if opts.convertsubtitles == 'none':
+        opts.convertsubtitles = None
+    if opts.convertthumbnails == 'none':
+        opts.convertthumbnails = None
+
     validate_regex('merge output format', opts.merge_output_format,
                    r'({0})(/({0}))*'.format('|'.join(map(re.escape, FFmpegMergerPP.SUPPORTED_EXTS))))
     validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE)
@@ -468,7 +473,7 @@ def metadataparser_actions(f):
             default_downloader = ed.get_basename()
 
     for policy in opts.color.values():
-        if policy not in ('always', 'auto', 'no_color', 'never'):
+        if policy not in ('always', 'auto', 'auto-tty', 'no_color', 'no_color-tty', 'never'):
             raise ValueError(f'"{policy}" is not a valid color policy')
 
     warnings, deprecation_warnings = [], []
@@ -1079,7 +1084,7 @@ def main(argv=None):
     _IN_CLI = True
     try:
         _exit(*variadic(_real_main(argv)))
-    except DownloadError:
+    except (CookieLoadError, DownloadError):
         _exit(1)
     except SameFileError as e:
         _exit(f'ERROR: {e}')

yt_dlp/cookies.py

@@ -34,6 +34,7 @@
 from .minicurses import MultilinePrinter, QuietMultilinePrinter
 from .utils import (
     DownloadError,
+    YoutubeDLError,
     Popen,
     error_to_str,
     expand_path,
@@ -86,24 +87,31 @@ def _create_progress_bar(logger):
     return printer
 
 
+class CookieLoadError(YoutubeDLError):
+    pass
+
+
 def load_cookies(cookie_file, browser_specification, ydl):
-    cookie_jars = []
+    try:
-    if browser_specification is not None:
+        cookie_jars = []
-        browser_name, profile, keyring, container = _parse_browser_specification(*browser_specification)
+        if browser_specification is not None:
-        cookie_jars.append(
+            browser_name, profile, keyring, container = _parse_browser_specification(*browser_specification)
-            extract_cookies_from_browser(browser_name, profile, YDLLogger(ydl), keyring=keyring, container=container))
+            cookie_jars.append(
+                extract_cookies_from_browser(browser_name, profile, YDLLogger(ydl), keyring=keyring, container=container))
 
-    if cookie_file is not None:
+        if cookie_file is not None:
-        is_filename = is_path_like(cookie_file)
+            is_filename = is_path_like(cookie_file)
-        if is_filename:
+            if is_filename:
-            cookie_file = expand_path(cookie_file)
+                cookie_file = expand_path(cookie_file)
 
-        jar = YoutubeDLCookieJar(cookie_file)
+            jar = YoutubeDLCookieJar(cookie_file)
-        if not is_filename or os.access(cookie_file, os.R_OK):
+            if not is_filename or os.access(cookie_file, os.R_OK):
-            jar.load()
+                jar.load()
-        cookie_jars.append(jar)
+            cookie_jars.append(jar)
 
-    return _merge_cookie_jars(cookie_jars)
+        return _merge_cookie_jars(cookie_jars)
+    except Exception:
+        raise CookieLoadError('failed to load cookies')
 
 
 def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(), *, keyring=None, container=None):
@@ -1053,8 +1061,9 @@ class DATA_BLOB(ctypes.Structure):
         ctypes.byref(blob_out),  # pDataOut
     )
     if not ret:
-        logger.warning('failed to decrypt with DPAPI', only_once=True)
+        message = 'Failed to decrypt with DPAPI. See  https://github.com/yt-dlp/yt-dlp/issues/10927  for more info'
-        return None
+        logger.error(message)
+        raise DownloadError(message)  # force exit
 
     result = ctypes.string_at(blob_out.pbData, blob_out.cbData)
     ctypes.windll.kernel32.LocalFree(blob_out.pbData)

yt_dlp/downloader/external.py

@@ -508,7 +508,7 @@ def _call_downloader(self, tmpfilename, info_dict):
         env = None
         proxy = self.params.get('proxy')
         if proxy:
-            if not re.match(r'^[\da-zA-Z]+://', proxy):
+            if not re.match(r'[\da-zA-Z]+://', proxy):
                 proxy = f'http://{proxy}'
 
             if proxy.startswith('socks'):
@@ -559,7 +559,7 @@ def _call_downloader(self, tmpfilename, info_dict):
 
         selected_formats = info_dict.get('requested_formats') or [info_dict]
         for i, fmt in enumerate(selected_formats):
-            is_http = re.match(r'^https?://', fmt['url'])
+            is_http = re.match(r'https?://', fmt['url'])
             cookies = self.ydl.cookiejar.get_cookies_for_url(fmt['url']) if is_http else []
             if cookies:
                 args.extend(['-cookies', ''.join(

yt_dlp/extractor/_extractors.py

@@ -217,6 +217,7 @@
     BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
 )
+from .beacon import BeaconTvIE
 from .beatbump import (
     BeatBumpPlaylistIE,
     BeatBumpVideoIE,
@@ -504,7 +505,6 @@
 from .digitalconcerthall import DigitalConcertHallIE
 from .digiteka import DigitekaIE
 from .discogs import DiscogsReleasePlaylistIE
-from .discovery import DiscoveryIE
 from .disney import DisneyIE
 from .dispeak import DigitallySpeakingIE
 from .dlf import (
@@ -532,16 +532,12 @@
     DiscoveryPlusIndiaShowIE,
     DiscoveryPlusItalyIE,
     DiscoveryPlusItalyShowIE,
-    DIYNetworkIE,
     DPlayIE,
     FoodNetworkIE,
-    GlobalCyclingNetworkPlusIE,
     GoDiscoveryIE,
     HGTVDeIE,
     HGTVUsaIE,
     InvestigationDiscoveryIE,
-    MotorTrendIE,
-    MotorTrendOnDemandIE,
     ScienceChannelIE,
     TravelChannelIE,
 )
@@ -734,6 +730,7 @@
     GeniusIE,
     GeniusLyricsIE,
 )
+from .germanupa import GermanupaIE
 from .getcourseru import (
     GetCourseRuIE,
     GetCourseRuPlayerIE,
@@ -827,7 +824,10 @@
     HungamaIE,
     HungamaSongIE,
 )
-from .huya import HuyaLiveIE
+from .huya import (
+    HuyaLiveIE,
+    HuyaVideoIE,
+)
 from .hypem import HypemIE
 from .hypergryph import MonsterSirenHypergryphMusicIE
 from .hytale import HytaleIE
@@ -944,11 +944,13 @@
     KhanAcademyUnitIE,
 )
 from .kick import (
+    KickClipIE,
     KickIE,
     KickVODIE,
 )
 from .kicker import KickerIE
 from .kickstarter import KickStarterIE
+from .kika import KikaIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
 from .kommunetv import KommunetvIE
@@ -991,6 +993,7 @@
     LcpIE,
     LcpPlayIE,
 )
+from .learningonscreen import LearningOnScreenIE
 from .lecture2go import Lecture2GoIE
 from .lecturio import (
     LecturioCourseIE,
@@ -1039,10 +1042,7 @@
     LivestreamShortenerIE,
 )
 from .livestreamfails import LivestreamfailsIE
-from .lnkgo import (
+from .lnk import LnkIE
-    LnkGoIE,
-    LnkIE,
-)
 from .loom import (
     LoomFolderIE,
     LoomIE,
@@ -1167,6 +1167,7 @@
 )
 from .mlssoccer import MLSSoccerIE
 from .mocha import MochaVideoIE
+from .mojevideo import MojevideoIE
 from .mojvideo import MojvideoIE
 from .monstercat import MonstercatIE
 from .motherless import (
@@ -1813,6 +1814,7 @@
 from .screencast import ScreencastIE
 from .screencastify import ScreencastifyIE
 from .screencastomatic import ScreencastOMaticIE
+from .screenrec import ScreenRecIE
 from .scrippsnetworks import (
     ScrippsNetworksIE,
     ScrippsNetworksWatchIE,
@@ -1823,6 +1825,7 @@
     SCTECourseIE,
 )
 from .sejmpl import SejmIE
+from .sen import SenIE
 from .senalcolombia import SenalColombiaLiveIE
 from .senategov import (
     SenateGovIE,
@@ -1878,6 +1881,7 @@
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
 from .smotrim import SmotrimIE
+from .snapchat import SnapchatSpotlightIE
 from .snotr import SnotrIE
 from .sohu import (
     SohuIE,
@@ -2174,10 +2178,7 @@
     TV5UnisVideoIE,
 )
 from .tv24ua import TV24UAVideoIE
-from .tva import (
+from .tva import TVAIE
-    TVAIE,
-    QubIE,
-)
 from .tvanouvelles import (
     TVANouvellesArticleIE,
     TVANouvellesIE,
@@ -2317,6 +2318,7 @@
     VideomoreVideoIE,
 )
 from .videopress import VideoPressIE
+from .vidflex import VidflexIE
 from .vidio import (
     VidioIE,
     VidioLiveIE,
@@ -2324,6 +2326,7 @@
 )
 from .vidlii import VidLiiIE
 from .vidly import VidlyIE
+from .vidyard import VidyardIE
 from .viewlift import (
     ViewLiftEmbedIE,
     ViewLiftIE,
@@ -2389,6 +2392,10 @@
     VrtNUIE,
 )
 from .vtm import VTMIE
+from .vtv import (
+    VTVIE,
+    VTVGoIE,
+)
 from .vuclip import VuClipIE
 from .vvvvid import (
     VVVVIDIE,

yt_dlp/extractor/abc.py

@@ -387,17 +387,27 @@ class ABCIViewShowSeriesIE(InfoExtractor):
             'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
         },
         'playlist_count': 15,
+        'skip': 'This program is not currently available in ABC iview',
+    }, {
+        'url': 'https://iview.abc.net.au/show/inbestigators',
+        'info_dict': {
+            'id': '175343-1',
+            'title': 'Series 1',
+            'description': 'md5:b9976935a6450e5b78ce2a940a755685',
+            'series': 'The Inbestigators',
+            'season': 'Series 1',
+            'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.+\.jpg',
+        },
+        'playlist_count': 17,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
         webpage = self._download_webpage(url, show_id)
-        webpage_data = self._search_regex(
+        video_data = self._search_json(
-            r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
+            r'window\.__INITIAL_STATE__\s*=\s*[\'"]', webpage, 'initial state', show_id,
-            webpage, 'initial state')
+            transform_source=lambda x: x.encode().decode('unicode_escape'),
-        video_data = self._parse_json(
+            end_pattern=r'[\'"]\s*;')['route']['pageData']['_embedded']
-            unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id)
-        video_data = video_data['route']['pageData']['_embedded']
 
         highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
         if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):

yt_dlp/extractor/abematv.py

@@ -9,12 +9,12 @@
 import struct
 import time
 import urllib.parse
-import urllib.request
-import urllib.response
 import uuid
 
 from .common import InfoExtractor
 from ..aes import aes_ecb_decrypt
+from ..networking import RequestHandler, Response
+from ..networking.exceptions import TransportError
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
@@ -26,37 +26,36 @@
     traverse_obj,
     update_url_query,
 )
-from ..utils.networking import clean_proxies
 
 
-def add_opener(ydl, handler):  # FIXME: Create proper API in .networking
+class AbemaLicenseRH(RequestHandler):
-    """Add a handler for opening URLs, like _download_webpage"""
+    _SUPPORTED_URL_SCHEMES = ('abematv-license',)
-    # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
+    _SUPPORTED_PROXY_SCHEMES = None
-    # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
+    _SUPPORTED_FEATURES = None
-    rh = ydl._request_director.handlers['Urllib']
+    RH_NAME = 'abematv_license'
-    if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
-        return
-    headers = ydl.params['http_headers'].copy()
-    proxies = ydl.proxies.copy()
-    clean_proxies(proxies, headers)
-    opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
-    assert isinstance(opener, urllib.request.OpenerDirector)
-    opener.add_handler(handler)
-    rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
 
+    _STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
+    _HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
 
-class AbemaLicenseHandler(urllib.request.BaseHandler):
+    def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
-    handler_order = 499
+        super().__init__(**kwargs)
-    STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
-    HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
-
-    def __init__(self, ie: 'AbemaTVIE'):
-        # the protocol that this should really handle is 'abematv-license://'
-        # abematv_license_open is just a placeholder for development purposes
-        # ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
-        setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
         self.ie = ie
 
+    def _send(self, request):
+        url = request.url
+        ticket = urllib.parse.urlparse(url).netloc
+
+        try:
+            response_data = self._get_videokey_from_ticket(ticket)
+        except ExtractorError as e:
+            raise TransportError(cause=e.cause) from e
+        except (IndexError, KeyError, TypeError) as e:
+            raise TransportError(cause=repr(e)) from e
+
+        return Response(
+            io.BytesIO(response_data), url,
+            headers={'Content-Length': str(len(response_data))})
+
     def _get_videokey_from_ticket(self, ticket):
         to_show = self.ie.get_param('verbose', False)
         media_token = self.ie._get_media_token(to_show=to_show)
@@ -72,25 +71,17 @@ def _get_videokey_from_ticket(self, ticket):
                 'Content-Type': 'application/json',
             })
 
-        res = decode_base_n(license_response['k'], table=self.STRTABLE)
+        res = decode_base_n(license_response['k'], table=self._STRTABLE)
         encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
 
         h = hmac.new(
-            binascii.unhexlify(self.HKEY),
+            binascii.unhexlify(self._HKEY),
             (license_response['cid'] + self.ie._DEVICE_ID).encode(),
             digestmod=hashlib.sha256)
         enckey = bytes_to_intlist(h.digest())
 
         return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
 
-    def abematv_license_open(self, url):
-        url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
-        ticket = urllib.parse.urlparse(url).netloc
-        response_data = self._get_videokey_from_ticket(ticket)
-        return urllib.response.addinfourl(io.BytesIO(response_data), headers={
-            'Content-Length': str(len(response_data)),
-        }, url=url, code=200)
-
 
 class AbemaTVBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'abematv'
@@ -139,7 +130,7 @@ def _get_device_token(self):
         if self._USERTOKEN:
             return self._USERTOKEN
 
-        add_opener(self._downloader, AbemaLicenseHandler(self))
+        self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
 
         username, _ = self._get_login_info()
         auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
@@ -368,6 +359,7 @@ def _real_extract(self, url):
             info['episode_number'] = epis if epis < 2000 else None
 
         is_live, m3u8_url = False, None
+        availability = 'public'
         if video_type == 'now-on-air':
             is_live = True
             channel_url = 'https://api.abema.io/v1/channels'
@@ -385,10 +377,10 @@ def _real_extract(self, url):
                 f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
                 note='Checking playability',
                 headers=headers)
-            ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
+            if not traverse_obj(api_response, ('label', 'free', {bool})):
-            if 3 not in ondemand_types:
                 # cannot acquire decryption key for these streams
                 self.report_warning('This is a premium-only stream')
+                availability = 'premium_only'
             info.update(traverse_obj(api_response, {
                 'series': ('series', 'title'),
                 'season': ('season', 'name'),
@@ -408,6 +400,7 @@ def _real_extract(self, url):
                 headers=headers)
             if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
                 self.report_warning('This is a premium-only stream')
+                availability = 'premium_only'
 
             m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
         else:
@@ -425,6 +418,7 @@ def _real_extract(self, url):
             'description': description,
             'formats': formats,
             'is_live': is_live,
+            'availability': availability,
         })
         return info
 

yt_dlp/extractor/academicearth.py

@@ -4,7 +4,7 @@
 
 
 class AcademicEarthCourseIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
+    _VALID_URL = r'https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
     _TEST = {
         'url': 'http://academicearth.org/playlists/laws-of-nature/',

yt_dlp/extractor/adn.py

@@ -16,6 +16,7 @@
     float_or_none,
     int_or_none,
     intlist_to_bytes,
+    join_nonempty,
     long_to_bytes,
     parse_iso8601,
     pkcs1pad,
@@ -48,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
 
 
 class ADNIE(ADNBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
+        'url': 'https://animationdigitalnetwork.com/video/558-fruits-basket/9841-episode-1-a-ce-soir',
         'md5': '1c9ef066ceb302c86f80c2b371615261',
         'info_dict': {
             'id': '9841',
@@ -70,10 +71,7 @@ class ADNIE(ADNBaseIE):
         },
         'skip': 'Only available in French and German speaking Europe',
     }, {
-        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'url': 'https://animationdigitalnetwork.com/de/video/973-the-eminence-in-shadow/23550-folge-1',
-        'only_matching': True,
-    }, {
-        'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1',
         'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
         'info_dict': {
             'id': '23550',
@@ -166,7 +164,7 @@ def _perform_login(self, username, password):
                     'username': username,
                 })) or {}).get('accessToken')
             if access_token:
-                self._HEADERS = {'authorization': 'Bearer ' + access_token}
+                self._HEADERS['Authorization'] = f'Bearer {access_token}'
         except ExtractorError as e:
             message = None
             if isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -177,6 +175,7 @@ def _perform_login(self, username, password):
 
     def _real_extract(self, url):
         lang, video_id = self._match_valid_url(url).group('lang', 'id')
+        self._HEADERS['X-Target-Distribution'] = lang or 'fr'
         video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
         player = self._download_json(
             video_base_url + 'configuration', video_id,
@@ -217,7 +216,6 @@ def _real_extract(self, url):
                 links_data = self._download_json(
                     links_url, video_id, 'Downloading links JSON metadata', headers={
                         'X-Player-Token': authorization,
-                        'X-Target-Distribution': lang,
                         **self._HEADERS,
                     }, query={
                         'freeWithAds': 'true',
@@ -256,6 +254,7 @@ def _real_extract(self, url):
                 load_balancer_data = self._download_json(
                     load_balancer_url, video_id,
                     f'Downloading {format_id} {quality} JSON metadata',
+                    headers=self._HEADERS,
                     fatal=False) or {}
                 m3u8_url = load_balancer_data.get('location')
                 if not m3u8_url:
@@ -276,7 +275,7 @@ def _real_extract(self, url):
 
         video = (self._download_json(
             self._API_BASE_URL + f'video/{video_id}', video_id,
-            'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
+            'Downloading additional video metadata', fatal=False, headers=self._HEADERS) or {}).get('video') or {}
         show = video.get('show') or {}
 
         return {
@@ -298,9 +297,9 @@ def _real_extract(self, url):
 
 
 class ADNSeasonIE(ADNBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>\d+)[^/?#]*/?(?:$|[#?])'
     _TESTS = [{
-        'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new',
+        'url': 'https://animationdigitalnetwork.com/video/911-tokyo-mew-mew-new',
         'playlist_count': 12,
         'info_dict': {
             'id': '911',
@@ -311,24 +310,22 @@ class ADNSeasonIE(ADNBaseIE):
 
     def _real_extract(self, url):
         lang, video_show_slug = self._match_valid_url(url).group('lang', 'id')
+        self._HEADERS['X-Target-Distribution'] = lang or 'fr'
         show = self._download_json(
             f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug,
             'Downloading show JSON metadata', headers=self._HEADERS)['show']
         show_id = str(show['id'])
         episodes = self._download_json(
             f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
-            'Downloading episode list', headers={
+            'Downloading episode list', headers=self._HEADERS, query={
-                'X-Target-Distribution': lang,
-                **self._HEADERS,
-            }, query={
                 'order': 'asc',
                 'limit': '-1',
             })
 
         def entries():
             for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
-                yield self.url_result(
+                yield self.url_result(join_nonempty(
-                    f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
+                    'https://animationdigitalnetwork.com', lang, 'video',
-                    ADNIE, episode_id)
+                    video_show_slug, episode_id, delim='/'), ADNIE, episode_id)
 
         return self.playlist_result(entries(), show_id, show.get('title'))

yt_dlp/extractor/afreecatv.py

@@ -1,6 +1,7 @@
 import functools
 
 from .common import InfoExtractor
+from ..networking import Request
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
@@ -58,6 +59,13 @@ def _perform_login(self, username, password):
                 f'Unable to login: {self.IE_NAME} said: {error}',
                 expected=True)
 
+    def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
+        return self._download_json(Request(
+            f'https://api.m.afreecatv.com/{endpoint}',
+            data=data, headers=headers, query=query,
+            extensions={'legacy_ssl': True}), display_id,
+            'Downloading API JSON', 'Unable to download API JSON')
+
 
 class AfreecaTVIE(AfreecaTVBaseIE):
     IE_NAME = 'afreecatv'
@@ -184,12 +192,12 @@ class AfreecaTVIE(AfreecaTVBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        data = self._download_json(
+        data = self._call_api(
-            'https://api.m.afreecatv.com/station/video/a/view', video_id,
+            'station/video/a/view', video_id, headers={'Referer': url},
-            headers={'Referer': url}, data=urlencode_postdata({
+            data=urlencode_postdata({
                 'nTitleNo': video_id,
                 'nApiLevel': 10,
-            }), impersonate=True)['data']
+            }))['data']
 
         error_code = traverse_obj(data, ('code', {int}))
         if error_code == -6221:
@@ -267,9 +275,9 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        data = self._download_json(
+        data = self._call_api(
-            'https://api.m.afreecatv.com/catchstory/a/view', video_id, headers={'Referer': url},
+            'catchstory/a/view', video_id, headers={'Referer': url},
-            query={'aStoryListIdx': '', 'nStoryIdx': video_id}, impersonate=True)
+            query={'aStoryListIdx': '', 'nStoryIdx': video_id})
 
         return self.playlist_result(self._entries(data), video_id)
 

yt_dlp/extractor/applepodcasts.py

@@ -1,27 +1,42 @@
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     clean_podcast_url,
-    get_element_by_class,
     int_or_none,
     parse_iso8601,
-    try_get,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ApplePodcastsIE(InfoExtractor):
     _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
     _TESTS = [{
+        'url': 'https://podcasts.apple.com/us/podcast/ferreck-dawn-to-the-break-of-dawn-117/id1625658232?i=1000665010654',
+        'md5': '82cc219b8cc1dcf8bfc5a5e99b23b172',
+        'info_dict': {
+            'id': '1000665010654',
+            'ext': 'mp3',
+            'title': 'Ferreck Dawn - To The Break of Dawn 117',
+            'episode': 'Ferreck Dawn - To The Break of Dawn 117',
+            'description': 'md5:1fc571102f79dbd0a77bfd71ffda23bc',
+            'upload_date': '20240812',
+            'timestamp': 1723449600,
+            'duration': 3596,
+            'series': 'Ferreck Dawn - To The Break of Dawn',
+            'thumbnail': 're:.+[.](png|jpe?g|webp)',
+        },
+    }, {
         'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
-        'md5': '41dc31cd650143e530d9423b6b5a344f',
+        'md5': 'baf8a6b8b8aa6062dbb4639ed73d0052',
         'info_dict': {
             'id': '1000482637777',
             'ext': 'mp3',
             'title': '207 - Whitney Webb Returns',
+            'episode': '207 - Whitney Webb Returns',
+            'episode_number': 207,
             'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
             'upload_date': '20200705',
             'timestamp': 1593932400,
-            'duration': 6454,
+            'duration': 5369,
             'series': 'The Tim Dillon Show',
             'thumbnail': 're:.+[.](png|jpe?g|webp)',
         },
@@ -39,47 +54,24 @@ class ApplePodcastsIE(InfoExtractor):
     def _real_extract(self, url):
         episode_id = self._match_id(url)
         webpage = self._download_webpage(url, episode_id)
-        episode_data = {}
+        server_data = self._search_json(
-        ember_data = {}
+            r'<script [^>]*\bid=["\']serialized-server-data["\'][^>]*>', webpage,
-        # new page type 2021-11
+            'server data', episode_id, contains_pattern=r'\[{(?s:.+)}\]')[0]['data']
-        amp_data = self._parse_json(self._search_regex(
+        model_data = traverse_obj(server_data, (
-            r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
+            'headerButtonItems', lambda _, v: v['$kind'] == 'bookmark' and v['modelType'] == 'EpisodeOffer',
-            webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
+            'model', {dict}, any))
-        amp_data = try_get(amp_data,
-                           lambda a: self._parse_json(
-                               next(a[x] for x in iter(a) if episode_id in x),
-                               episode_id),
-                           dict) or {}
-        amp_data = amp_data.get('d') or []
-        episode_data = try_get(
-            amp_data,
-            lambda a: next(x for x in a
-                           if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
-            dict)
-        if not episode_data:
-            # try pre 2021-11 page type: TODO: consider deleting if no longer used
-            ember_data = self._parse_json(self._search_regex(
-                r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
-                webpage, 'ember data'), episode_id) or {}
-            ember_data = ember_data.get(episode_id) or ember_data
-            episode_data = try_get(ember_data, lambda x: x['data'], dict)
-        episode = episode_data['attributes']
-        description = episode.get('description') or {}
-
-        series = None
-        for inc in (amp_data or ember_data.get('included') or []):
-            if inc.get('type') == 'media/podcast':
-                series = try_get(inc, lambda x: x['attributes']['name'])
-        series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
 
         return {
             'id': episode_id,
-            'title': episode.get('name'),
+            **self._json_ld(
-            'url': clean_podcast_url(episode['assetUrl']),
+                traverse_obj(server_data, ('seoData', 'schemaContent', {dict}))
-            'description': description.get('standard') or description.get('short'),
+                or self._yield_json_ld(webpage, episode_id, fatal=False), episode_id, fatal=False),
-            'timestamp': parse_iso8601(episode.get('releaseDateTime')),
+            **traverse_obj(model_data, {
-            'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
+                'title': ('title', {str}),
-            'series': series,
+                'url': ('streamUrl', {clean_podcast_url}),
+                'timestamp': ('releaseDate', {parse_iso8601}),
+                'duration': ('duration', {int_or_none}),
+            }),
             'thumbnail': self._og_search_thumbnail(webpage),
             'vcodec': 'none',
         }

yt_dlp/extractor/ard.py

@@ -231,7 +231,7 @@ def _real_extract(self, url):
 
 class ARDBetaMediathekIE(InfoExtractor):
     IE_NAME = 'ARDMediathek'
-    _VALID_URL = r'''(?x)https://
+    _VALID_URL = r'''(?x)https?://
         (?:(?:beta|www)\.)?ardmediathek\.de/
         (?:[^/]+/)?
         (?:player|live|video)/
@@ -470,7 +470,7 @@ def _real_extract(self, url):
 
 
 class ARDMediathekCollectionIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https://
+    _VALID_URL = r'''(?x)https?://
         (?:(?:beta|www)\.)?ardmediathek\.de/
         (?:[^/?#]+/)?
         (?P<playlist>sendung|serie|sammlung)/

yt_dlp/extractor/asobistage.py

@@ -101,9 +101,10 @@ def _real_initialize(self):
         self._HEADERS['Authorization'] = f'Bearer {token}'
 
     def _real_extract(self, url):
-        video_id, event, type_, slug = self._match_valid_url(url).group('id', 'event', 'type', 'slug')
+        webpage, urlh = self._download_webpage_handle(url, self._match_id(url))
+        video_id, event, type_, slug = self._match_valid_url(urlh.url).group('id', 'event', 'type', 'slug')
         video_type = {'archive': 'archives', 'player': 'broadcasts'}[type_]
-        webpage = self._download_webpage(url, video_id)
+
         event_data = traverse_obj(
             self._search_nextjs_data(webpage, video_id, default={}),
             ('props', 'pageProps', 'eventCMSData', {

yt_dlp/extractor/bandcamp.py

@@ -1,3 +1,5 @@
+import functools
+import json
 import random
 import re
 import time
@@ -6,7 +8,9 @@
 from ..utils import (
     KNOWN_EXTENSIONS,
     ExtractorError,
+    extract_attributes,
     float_or_none,
+    get_element_html_by_id,
     int_or_none,
     parse_filesize,
     str_or_none,
@@ -17,6 +21,7 @@
     url_or_none,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BandcampIE(InfoExtractor):
@@ -459,7 +464,7 @@ class BandcampUserIE(InfoExtractor):
         },
     }, {
         'url': 'https://coldworldofficial.bandcamp.com/music',
-        'playlist_mincount': 10,
+        'playlist_mincount': 7,
         'info_dict': {
             'id': 'coldworldofficial',
             'title': 'Discography of coldworldofficial',
@@ -473,12 +478,19 @@ class BandcampUserIE(InfoExtractor):
         },
     }]
 
+    def _yield_items(self, webpage):
+        yield from (
+            re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
+            or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
+
+        yield from traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'music-grid')}, {extract_attributes},
+            'data-client-items', {json.loads}, ..., 'page_url', {str}))
+
     def _real_extract(self, url):
         uploader = self._match_id(url)
         webpage = self._download_webpage(url, uploader)
 
-        discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
-                            or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
-
         return self.playlist_from_matches(
-            discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
+            self._yield_items(webpage), uploader, f'Discography of {uploader}',
+            getter=functools.partial(urljoin, url))

yt_dlp/extractor/beacon.py

@@ -0,0 +1,68 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+    traverse_obj,
+)
+
+
+class BeaconTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?beacon\.tv/content/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://beacon.tv/content/welcome-to-beacon',
+        'md5': 'b3f5932d437f288e662f10f3bfc5bd04',
+        'info_dict': {
+            'id': 'welcome-to-beacon',
+            'ext': 'mp4',
+            'upload_date': '20240509',
+            'description': 'md5:ea2bd32e71acf3f9fca6937412cc3563',
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/I4CkkEvN/poster.jpg?width=720',
+            'title': 'Your home for Critical Role!',
+            'timestamp': 1715227200,
+            'duration': 105.494,
+        },
+    }, {
+        'url': 'https://beacon.tv/content/re-slayers-take-trailer',
+        'md5': 'd879b091485dbed2245094c8152afd89',
+        'info_dict': {
+            'id': 're-slayers-take-trailer',
+            'ext': 'mp4',
+            'title': 'The Re-Slayer’s Take | Official Trailer',
+            'timestamp': 1715189040,
+            'upload_date': '20240508',
+            'duration': 53.249,
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/PW5ApIw3/poster.jpg?width=720',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        content_data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
+            'props', 'pageProps', '__APOLLO_STATE__',
+            lambda k, v: k.startswith('Content:') and v['slug'] == video_id, any))
+        if not content_data:
+            raise ExtractorError('Failed to extract content data')
+
+        jwplayer_data = traverse_obj(content_data, (
+            (('contentVideo', 'video', 'videoData'),
+             ('contentPodcast', 'podcast', 'audioData')), {json.loads}, {dict}, any))
+        if not jwplayer_data:
+            if content_data.get('contentType') not in ('videoPodcast', 'video', 'podcast'):
+                raise ExtractorError('Content is not a video/podcast', expected=True)
+            if traverse_obj(content_data, ('contentTier', '__ref')) != 'MemberTier:65b258d178f89be87b4dc0a4':
+                self.raise_login_required('This video/podcast is for members only')
+            raise ExtractorError('Failed to extract content')
+
+        return {
+            **self._parse_jwplayer_data(jwplayer_data, video_id),
+            **traverse_obj(content_data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('publishedAt', {parse_iso8601}),
+            }),
+        }

yt_dlp/extractor/bilibili.py

@@ -46,6 +46,7 @@
 
 
 class BilibiliBaseIE(InfoExtractor):
+    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
     _FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?')
     _WBI_KEY_CACHE_TIMEOUT = 30  # exact expire timeout is unclear, use 30s for one session
     _wbi_key_cache = {}
@@ -192,7 +193,7 @@ def _get_subtitles(self, video_id, cid, aid=None):
         video_info = self._download_json(
             'https://api.bilibili.com/x/player/v2', video_id,
             query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid},
-            note=f'Extracting subtitle info {cid}')
+            note=f'Extracting subtitle info {cid}', headers=self._HEADERS)
         if traverse_obj(video_info, ('data', 'need_login_subtitle')):
             self.report_warning(
                 f'Subtitles are only available when logged in. {self._login_hint()}', only_once=True)
@@ -207,7 +208,7 @@ def _get_subtitles(self, video_id, cid, aid=None):
     def _get_chapters(self, aid, cid):
         chapters = aid and cid and self._download_json(
             'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid},
-            note='Extracting chapters', fatal=False)
+            note='Extracting chapters', fatal=False, headers=self._HEADERS)
         return traverse_obj(chapters, ('data', 'view_points', ..., {
             'title': 'content',
             'start_time': 'from',
@@ -298,7 +299,7 @@ def _get_interactive_entries(self, video_id, cid, metainfo, headers=None):
 
 
 class BiliBiliIE(BilibiliBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'https://www.bilibili.com/video/BV13x41117TL',
@@ -622,6 +623,10 @@ class BiliBiliIE(BilibiliBaseIE):
             'ext': 'mp4',
         },
         'skip': 'geo-restricted',
+    }, {
+        'note': 'has - in the last path segment of the url',
+        'url': 'https://www.bilibili.com/festival/bh3-7th?bvid=BV1tr4y1f7p2&',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -1017,8 +1022,6 @@ def _real_extract(self, url):
 
 
 class BilibiliCheeseBaseIE(BilibiliBaseIE):
-    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
-
     def _extract_episode(self, season_info, ep_id):
         episode_info = traverse_obj(season_info, (
             'episodes', lambda _, v: v['id'] == int(ep_id)), get_all=False)
@@ -1848,7 +1851,7 @@ def _real_extract(self, url):
 class BiliIntlBaseIE(InfoExtractor):
     _API_URL = 'https://api.bilibili.tv/intl/gateway'
     _NETRC_MACHINE = 'biliintl'
-    _HEADERS = {'Referer': 'https://www.bilibili.com/'}
+    _HEADERS = {'Referer': 'https://www.bilibili.tv/'}
 
     def _call_api(self, endpoint, *args, **kwargs):
         json = self._download_json(self._API_URL + endpoint, *args, **kwargs)

yt_dlp/extractor/box.py

@@ -12,7 +12,7 @@
 
 
 class BoxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
+    _VALID_URL = r'https?://(?:[^.]+\.)?(?P<service>app|ent)\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
     _TESTS = [{
         'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
         'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@@ -38,10 +38,22 @@ class BoxIE(InfoExtractor):
             'uploader_id': '239068974',
         },
         'params': {'skip_download': 'dash fragment too small'},
+    }, {
+        'url': 'https://thejacksonlaboratory.ent.box.com/s/2x09dm6vcg6y28o0oox1so4l0t8wzt6l/file/1536173056065',
+        'info_dict': {
+            'id': '1536173056065',
+            'ext': 'mp4',
+            'uploader_id': '18523128264',
+            'uploader': 'Lexi Hennigan',
+            'title': 'iPSC Symposium recording part 1.mp4',
+            'timestamp': 1716228343,
+            'upload_date': '20240520',
+        },
+        'params': {'skip_download': 'dash fragment too small'},
     }]
 
     def _real_extract(self, url):
-        shared_name, file_id = self._match_valid_url(url).groups()
+        shared_name, file_id, service = self._match_valid_url(url).group('shared_name', 'id', 'service')
         webpage = self._download_webpage(url, file_id or shared_name)
 
         if not file_id:
@@ -57,14 +69,14 @@ def _real_extract(self, url):
         request_token = self._search_json(
             r'Box\.config\s*=', webpage, 'Box config', file_id)['requestToken']
         access_token = self._download_json(
-            'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
+            f'https://{service}.box.com/app-api/enduserapp/elements/tokens', file_id,
             'Downloading token JSON metadata',
             data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
                 'Content-Type': 'application/json',
                 'X-Request-Token': request_token,
                 'X-Box-EndUser-API': 'sharedName=' + shared_name,
             })[file_id]['read']
-        shared_link = 'https://app.box.com/s/' + shared_name
+        shared_link = f'https://{service}.box.com/s/{shared_name}'
         f = self._download_json(
             'https://api.box.com/2.0/files/' + file_id, file_id,
             'Downloading file JSON metadata', headers={

yt_dlp/extractor/callin.py

@@ -3,7 +3,7 @@
 
 
 class CallinIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?callin\.com/(episode)/(?P<id>[-a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?P<id>[-a-zA-Z]+)'
     _TESTS = [{
         'url': 'https://www.callin.com/episode/the-title-ix-regime-and-the-long-march-through-EBfXYSrsjc',
         'info_dict': {

yt_dlp/extractor/cbc.py

@@ -1,4 +1,5 @@
 import base64
+import functools
 import json
 import re
 import time
@@ -6,17 +7,24 @@
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
+from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
+    float_or_none,
     int_or_none,
     join_nonempty,
     js_to_json,
+    mimetype2ext,
     orderedSet,
     parse_iso8601,
+    replace_extension,
     smuggle_url,
     strip_or_none,
     traverse_obj,
     try_get,
+    update_url,
+    url_basename,
+    url_or_none,
 )
 
 
@@ -149,6 +157,7 @@ def _real_extract(self, url):
 class CBCPlayerIE(InfoExtractor):
     IE_NAME = 'cbc.ca:player'
     _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
+    _GEO_COUNTRIES = ['CA']
     _TESTS = [{
         'url': 'http://www.cbc.ca/player/play/2683190193',
         'md5': '64d25f841ddf4ddb28a235338af32e2c',
@@ -172,21 +181,20 @@ class CBCPlayerIE(InfoExtractor):
             'description': 'md5:dd3b692f0a139b0369943150bd1c46a9',
             'timestamp': 1425704400,
             'upload_date': '20150307',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
-            'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
-            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'categories': ['All in a Weekend Montreal'],
-            'tags': 'count:8',
+            'tags': 'count:11',
             'location': 'Quebec',
             'series': 'All in a Weekend Montreal',
             'season': 'Season 2015',
             'season_number': 2015,
             'media_type': 'Excerpt',
+            'genres': ['Other'],
         },
     }, {
         'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062',
-        'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
         'info_dict': {
             'id': '2164402062',
             'ext': 'mp4',
@@ -194,107 +202,168 @@ class CBCPlayerIE(InfoExtractor):
             'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
             'timestamp': 1320410746,
             'upload_date': '20111104',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
             'series': 'CBC News: Windsor at 6:00',
-            'categories': ['News/Canada/Windsor'],
+            'categories': ['Windsor'],
             'location': 'Windsor',
-            'tags': ['cancer'],
+            'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
-            'creators': ['Allison Johnson'],
             'media_type': 'Excerpt',
+            'genres': ['News'],
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
         'url': 'https://www.cbc.ca/player/play/1.2985700',
         'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
         'info_dict': {
-            'id': '2657631896',
+            'id': '1.2985700',
             'ext': 'mp3',
             'title': 'CBC Montreal is organizing its first ever community hackathon!',
             'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
             'timestamp': 1425704400,
             'upload_date': '20150307',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
-            'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
-            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'categories': ['All in a Weekend Montreal'],
-            'tags': 'count:8',
+            'tags': 'count:11',
             'location': 'Quebec',
             'series': 'All in a Weekend Montreal',
             'season': 'Season 2015',
             'season_number': 2015,
             'media_type': 'Excerpt',
+            'genres': ['Other'],
         },
     }, {
         'url': 'https://www.cbc.ca/player/play/1.1711287',
-        'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
         'info_dict': {
-            'id': '2164402062',
+            'id': '1.1711287',
             'ext': 'mp4',
             'title': 'Cancer survivor four times over',
             'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
             'timestamp': 1320410746,
             'upload_date': '20111104',
-            'uploader': 'CBCC-NEW',
+            'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
             'series': 'CBC News: Windsor at 6:00',
-            'categories': ['News/Canada/Windsor'],
+            'categories': ['Windsor'],
             'location': 'Windsor',
-            'tags': ['cancer'],
+            'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
-            'creators': ['Allison Johnson'],
             'media_type': 'Excerpt',
+            'genres': ['News'],
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Has subtitles
         # These broadcasts expire after ~1 month, can find new test URL here:
         # https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
-        'url': 'https://www.cbc.ca/player/play/1.7159484',
+        'url': 'https://www.cbc.ca/player/play/video/9.6424403',
-        'md5': '6ed6cd0fc2ef568d2297ba68a763d455',
+        'md5': '8025909eaffcf0adf59922904def9a5e',
         'info_dict': {
-            'id': '2324213316001',
+            'id': '9.6424403',
             'ext': 'mp4',
-            'title': 'The National | School boards sue social media giants',
+            'title': 'The National | N.W.T. wildfire emergency',
-            'description': 'md5:4b4db69322fa32186c3ce426da07402c',
+            'description': 'md5:ada33d36d1df69347ed575905bfd496c',
-            'timestamp': 1711681200,
+            'timestamp': 1718589600,
-            'duration': 2743.400,
+            'duration': 2692.833,
-            'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
+            'subtitles': {
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg',
+                'en-US': [{
-            'uploader': 'CBCC-NEW',
+                    'name': 'English Captions',
+                    'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
+                }],
+            },
+            'thumbnail': 'https://i.cbc.ca/ais/6272b5c6-5e78-4c05-915d-0e36672e33d1,1714756287822/full/max/0/default.jpg',
             'chapters': 'count:5',
-            'upload_date': '20240329',
+            'upload_date': '20240617',
-            'categories': 'count:4',
+            'categories': ['News', 'The National', 'The National Latest Broadcasts'],
             'series': 'The National - Full Show',
-            'tags': 'count:1',
+            'tags': ['The National'],
-            'creators': ['News'],
             'location': 'Canada',
             'media_type': 'Full Program',
+            'genres': ['News'],
         },
     }, {
         'url': 'https://www.cbc.ca/player/play/video/1.7194274',
         'md5': '188b96cf6bdcb2540e178a6caa957128',
         'info_dict': {
-            'id': '2334524995812',
+            'id': '1.7194274',
             'ext': 'mp4',
             'title': '#TheMoment a rare white spirit moose was spotted in Alberta',
             'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3',
             'timestamp': 1714788791,
             'duration': 77.678,
             'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg',
+            'thumbnail': 'https://i.cbc.ca/ais/1.7194274,1717224990425/full/max/0/default.jpg',
-            'uploader': 'CBCC-NEW',
+            'chapters': [],
-            'chapters': 'count:0',
-            'upload_date': '20240504',
             'categories': 'count:3',
             'series': 'The National',
-            'tags': 'count:15',
+            'tags': 'count:17',
-            'creators': ['encoder'],
             'location': 'Canada',
             'media_type': 'Excerpt',
+            'upload_date': '20240504',
+            'genres': ['News'],
+        },
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6427282',
+        'info_dict': {
+            'id': '9.6427282',
+            'ext': 'mp4',
+            'title': 'Men\'s Soccer - Argentina vs Morocco',
+            'description': 'Argentina faces Morocco on the football pitch at Saint Etienne Stadium.',
+            'series': 'CBC Sports',
+            'media_type': 'Event Coverage',
+            'thumbnail': 'https://i.cbc.ca/ais/a4c5c0c2-99fa-4bd3-8061-5a63879c1b33,1718828053500/full/max/0/default.jpg',
+            'timestamp': 1721825400.0,
+            'upload_date': '20240724',
+            'duration': 10568.0,
+            'chapters': [],
+            'genres': [],
+            'tags': ['2024 Paris Olympic Games'],
+            'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
+            'location': 'Canada',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6459530',
+        'md5': '6c1bb76693ab321a2e99c347a1d5ecbc',
+        'info_dict': {
+            'id': '9.6459530',
+            'ext': 'mp4',
+            'title': 'Parts of Jasper incinerated as wildfire rages',
+            'description': 'md5:6f1caa8d128ad3f629257ef5fecf0962',
+            'series': 'The National',
+            'media_type': 'Excerpt',
+            'thumbnail': 'https://i.cbc.ca/ais/507c0086-31a2-494d-96e4-bffb1048d045,1721953984375/full/max/0/default.jpg',
+            'timestamp': 1721964091.012,
+            'upload_date': '20240726',
+            'duration': 952.285,
+            'chapters': [],
+            'genres': [],
+            'tags': 'count:23',
+            'categories': ['News (FAST)', 'News', 'The National', 'TV News Shows', 'The National '],
+        },
+    }, {
+        'url': 'https://www.cbc.ca/player/play/video/9.6420651',
+        'md5': '71a850c2c6ee5e912de169f5311bb533',
+        'info_dict': {
+            'id': '9.6420651',
+            'ext': 'mp4',
+            'title': 'Is it a breath of fresh air? Measuring air quality in Edmonton',
+            'description': 'md5:3922b92cc8b69212d739bd9dd095b1c3',
+            'series': 'CBC News Edmonton',
+            'media_type': 'Excerpt',
+            'thumbnail': 'https://i.cbc.ca/ais/73c4ab9c-7ad4-46ee-bb9b-020fdc01c745,1718214547576/full/max/0/default.jpg',
+            'timestamp': 1718220065.768,
+            'upload_date': '20240612',
+            'duration': 286.086,
+            'chapters': [],
+            'genres': ['News'],
+            'categories': ['News', 'Edmonton'],
+            'tags': 'count:7',
+            'location': 'Edmonton',
         },
     }, {
         'url': 'cbcplayer:1.7159484',
@@ -307,23 +376,113 @@ class CBCPlayerIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _parse_param(self, asset_data, name):
+        return traverse_obj(asset_data, ('params', lambda _, v: v['name'] == name, 'value', {str}, any))
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        if '.' in video_id:
+        webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
-            webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
+        data = self._search_json(
-            video_id = self._search_json(
+            r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip']
-                r'window\.__INITIAL_STATE__\s*=', webpage,
+        assets = traverse_obj(
-                'initial state', video_id)['video']['currentClip']['mediaId']
+            data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
+
+        if not assets and (media_id := traverse_obj(data, ('mediaId', {str}))):
+            # XXX: Deprecated; CBC is migrating off of ThePlatform
+            return {
+                '_type': 'url_transparent',
+                'ie_key': 'ThePlatform',
+                'url': smuggle_url(
+                    f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{media_id}?mbr=true&formats=MPEG4,FLV,MP3', {
+                        'force_smil_url': True,
+                    }),
+                'id': media_id,
+                '_format_sort_fields': ('res', 'proto'),  # Prioritize direct http formats over HLS
+            }
+
+        is_live = traverse_obj(data, ('media', 'streamType', {str})) == 'Live'
+        formats, subtitles = [], {}
+
+        for sub in traverse_obj(data, ('media', 'textTracks', lambda _, v: url_or_none(v['src']))):
+            subtitles.setdefault(sub.get('language') or 'und', []).append({
+                'url': sub['src'],
+                'name': sub.get('label'),
+            })
+
+        for asset in assets:
+            asset_key = asset['key']
+            asset_type = asset['type']
+            if asset_type != 'medianet':
+                self.report_warning(f'Skipping unsupported asset type "{asset_type}": {asset_key}')
+                continue
+            asset_data = self._download_json(asset_key, video_id, f'Downloading {asset_type} JSON')
+            ext = mimetype2ext(self._parse_param(asset_data, 'contentType'))
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    asset_data['url'], video_id, 'mp4', m3u8_id='hls', live=is_live)
+                formats.extend(fmts)
+                # Avoid slow/error-prone webvtt-over-m3u8 if direct https vtt is available
+                if not subtitles:
+                    self._merge_subtitles(subs, target=subtitles)
+                if is_live or not fmts:
+                    continue
+                # Check for direct https mp4 format
+                best_video_fmt = traverse_obj(fmts, (
+                    lambda _, v: v.get('vcodec') != 'none' and v['tbr'], all,
+                    {functools.partial(sorted, key=lambda x: x['tbr'])}, -1, {dict})) or {}
+                base_url = self._search_regex(
+                    r'(https?://[^?#]+?/)hdntl=', best_video_fmt.get('url'), 'base url', default=None)
+                if not base_url or '/live/' in base_url:
+                    continue
+                mp4_url = base_url + replace_extension(url_basename(best_video_fmt['url']), 'mp4')
+                if self._request_webpage(
+                        HEADRequest(mp4_url), video_id, 'Checking for https format',
+                        errnote=False, fatal=False):
+                    formats.append({
+                        **best_video_fmt,
+                        'url': mp4_url,
+                        'format_id': 'https-mp4',
+                        'protocol': 'https',
+                        'manifest_url': None,
+                        'acodec': None,
+                    })
+            else:
+                formats.append({
+                    'url': asset_data['url'],
+                    'ext': ext,
+                    'vcodec': 'none' if self._parse_param(asset_data, 'mediaType') == 'audio' else None,
+                })
+
+        chapters = traverse_obj(data, (
+            'media', 'chapters', lambda _, v: float(v['startTime']) is not None, {
+                'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}),
+                'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}),
+                'title': ('name', {str}),
+            }))
+        # Filter out pointless single chapters with start_time==0 and no end_time
+        if len(chapters) == 1 and not (chapters[0].get('start_time') or chapters[0].get('end_time')):
+            chapters = []
 
         return {
-            '_type': 'url_transparent',
+            **traverse_obj(data, {
-            'ie_key': 'ThePlatform',
+                'title': ('title', {str}),
-            'url': smuggle_url(
+                'description': ('description', {str.strip}),
-                f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{video_id}?mbr=true&formats=MPEG4,FLV,MP3', {
+                'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}),
-                    'force_smil_url': True,
+                'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}),
-                }),
+                'media_type': ('media', 'clipType', {str}),
+                'series': ('showName', {str}),
+                'season_number': ('media', 'season', {int_or_none}),
+                'duration': ('media', 'duration', {float_or_none}, {lambda x: None if is_live else x}),
+                'location': ('media', 'region', {str}),
+                'tags': ('tags', ..., 'name', {str}),
+                'genres': ('media', 'genre', all),
+                'categories': ('categories', ..., 'name', {str}),
+            }),
             'id': video_id,
-            '_format_sort_fields': ('res', 'proto'),  # Prioritize direct http formats over HLS
+            'formats': formats,
+            'subtitles': subtitles,
+            'chapters': chapters,
+            'is_live': is_live,
         }
 
 
@@ -647,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor):
                 'title': 'Ottawa',
                 'description': 'The live TV channel and local programming from Ottawa',
                 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
-                'is_live': True,
+                'live_status': 'is_live',
                 'id': 'AyqZwxRqh8EH',
                 'ext': 'mp4',
-                'timestamp': 1492106160,
+                'release_timestamp': 1492106160,
-                'upload_date': '20170413',
+                'release_date': '20170413',
                 'uploader': 'CBCC-NEW',
             },
             'skip': 'Live might have ended',
@@ -680,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor):
                 'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
                 'live_status': 'is_live',
                 'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
-                'timestamp': 1679706000,
+                'release_timestamp': 1679706000,
-                'upload_date': '20230325',
+                'release_date': '20230325',
             },
             'params': {'skip_download': True},
             'skip': 'Live might have ended',
         },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/42314',
+            'md5': '297a9600f554f2258aed01514226a697',
+            'info_dict': {
+                'id': '42314',
+                'ext': 'mp4',
+                'live_status': 'was_live',
+                'title': 'Women\'s Soccer - Canada vs New Zealand',
+                'description': 'md5:36200e5f1a70982277b5a6ecea86155d',
+                'thumbnail': r're:https://.+default\.jpg',
+                'release_timestamp': 1721917200,
+                'release_date': '20240725',
+            },
+            'params': {'skip_download': True},
+            'skip': 'Replay might no longer be available',
+        },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/43273',
+            'only_matching': True,
+        },
     ]
+    _GEO_COUNTRIES = ['CA']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
 
-        # Two types of metadata JSON
+        # Three types of video_info JSON: info in root, freeTv stream/item, event replay
         if not video_info.get('formattedIdMedia'):
-            video_info = traverse_obj(
+            if traverse_obj(video_info, ('event', 'key')) == video_id:
-                video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
+                video_info = video_info['event']
-                get_all=False, default={})
+            else:
+                video_info = traverse_obj(video_info, (
+                    ('freeTv', ('streams', ...)), 'items',
+                    lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {}
 
         video_stream_id = video_info.get('formattedIdMedia')
         if not video_stream_id:
-            raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
+            raise ExtractorError(
+                'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
 
-        stream_data = self._download_json(
+        live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live'
-            'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
+        release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601}))
-                'appCode': 'mpx',
+
-                'connectionType': 'hd',
+        if live_status == 'is_live' and release_timestamp and release_timestamp > time.time():
-                'deviceType': 'ipad',
+            formats = []
-                'idMedia': video_stream_id,
+            live_status = 'is_upcoming'
-                'multibitrate': 'true',
+            self.raise_no_formats('This livestream has not yet started', expected=True)
-                'output': 'json',
+        else:
-                'tech': 'hls',
+            stream_data = self._download_json(
-                'manifestType': 'desktop',
+                'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
-            })
+                    'appCode': 'medianetlive',
+                    'connectionType': 'hd',
+                    'deviceType': 'ipad',
+                    'idMedia': video_stream_id,
+                    'multibitrate': 'true',
+                    'output': 'json',
+                    'tech': 'hls',
+                    'manifestType': 'desktop',
+                })
+            formats = self._extract_m3u8_formats(
+                stream_data['url'], video_id, 'mp4', live=live_status == 'is_live')
 
         return {
             'id': video_id,
-            'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
+            'formats': formats,
-            'is_live': True,
+            'live_status': live_status,
+            'release_timestamp': release_timestamp,
             **traverse_obj(video_info, {
-                'title': 'title',
+                'title': ('title', {str}),
-                'description': 'description',
+                'description': ('description', {str}),
                 'thumbnail': ('images', 'card', 'url'),
-                'timestamp': ('airDate', {parse_iso8601}),
             }),
         }

yt_dlp/extractor/cellebrite.py

@@ -1,63 +1,50 @@
-from .common import InfoExtractor
+from .vidyard import VidyardBaseIE, VidyardIE
-from ..utils import traverse_obj
+from ..utils import ExtractorError, make_archive_id, url_basename
 
 
-class CellebriteIE(InfoExtractor):
+class CellebriteIE(VidyardBaseIE):
     _VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
         'info_dict': {
-            'id': '16025876',
+            'id': 'ZqmUss3dQfEMGpauambPuH',
+            'display_id': '16025876',
             'ext': 'mp4',
-            'description': 'md5:174571cb97083fd1d457d75c684f4e2b',
-            'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
             'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
-            'duration': 455,
+            'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4',
-            'tags': [],
+            'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
+            'duration': 455.979,
+            '_old_archive_ids': ['cellebrite 16025876'],
         },
     }, {
         'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
         'info_dict': {
-            'id': '29018255',
+            'id': 'QV1U8a2yzcxigw7VFnqKyg',
+            'display_id': '29018255',
             'ext': 'mp4',
-            'duration': 134,
+            'title': 'How to Lawfully Collect the Maximum Amount of Data From Android Devices',
-            'tags': [],
+            'description': 'md5:0e943a9ac14c374d5d74faed634d773c',
-            'description': 'md5:e9a3d124c7287b0b07bad2547061cacf',
             'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
-            'title': 'Android Extractions Explained',
+            'duration': 134.315,
+            '_old_archive_ids': ['cellebrite 29018255'],
         },
     }]
 
-    def _get_formats_and_subtitles(self, json_data, display_id):
-        formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []]
-        subtitles = {}
-
-        for url in traverse_obj(json_data, ('hls', ..., 'url')) or []:
-            fmt, sub = self._extract_m3u8_formats_and_subtitles(
-                url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'})
-            formats.extend(fmt)
-            self._merge_subtitles(sub, target=subtitles)
-
-        return formats, subtitles
-
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        slug = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(url, slug)
+        vidyard_url = next(VidyardIE._extract_embed_urls(url, webpage), None)
+        if not vidyard_url:
+            raise ExtractorError('No Vidyard video embeds found on page')
 
-        player_uuid = self._search_regex(
+        video_id = url_basename(vidyard_url)
-            r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID')
+        info = self._process_video_json(self._fetch_video_json(video_id)['chapters'][0], video_id)
-        json_data = self._download_json(
+        if info.get('display_id'):
-            f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0]
+            info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
+        if thumbnail := self._og_search_thumbnail(webpage, default=None):
+            info.setdefault('thumbnails', []).append({'url': thumbnail})
 
-        formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id)
         return {
-            'id': str(json_data['videoId']),
+            'description': self._og_search_description(webpage, default=None),
-            'title': json_data.get('name') or self._og_search_title(webpage),
+            **info,
-            'formats': formats,
-            'subtitles': subtitles,
-            'description': json_data.get('description') or self._og_search_description(webpage),
-            'duration': json_data.get('seconds'),
-            'tags': json_data.get('tags'),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'http_headers': {'Referer': 'https://play.vidyard.com/'},
         }

yt_dlp/extractor/chzzk.py

@@ -36,7 +36,7 @@ class CHZZKLiveIE(InfoExtractor):
     def _real_extract(self, url):
         channel_id = self._match_id(url)
         live_detail = self._download_json(
-            f'https://api.chzzk.naver.com/service/v2/channels/{channel_id}/live-detail', channel_id,
+            f'https://api.chzzk.naver.com/service/v3/channels/{channel_id}/live-detail', channel_id,
             note='Downloading channel info', errnote='Unable to download channel info')['content']
 
         if live_detail.get('status') == 'CLOSE':
@@ -106,12 +106,45 @@ class CHZZKVideoIE(InfoExtractor):
             'upload_date': '20231219',
             'view_count': int,
         },
+        'skip': 'Replay video is expired',
+    }, {
+        # Manually uploaded video
+        'url': 'https://chzzk.naver.com/video/1980',
+        'info_dict': {
+            'id': '1980',
+            'ext': 'mp4',
+            'title': '※시청주의※한번보면 잊기 힘든 영상',
+            'channel': '라디유radiyu',
+            'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
+            'channel_is_verified': False,
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 95,
+            'timestamp': 1703102631.722,
+            'upload_date': '20231220',
+            'view_count': int,
+        },
+    }, {
+        # Partner channel replay video
+        'url': 'https://chzzk.naver.com/video/2458',
+        'info_dict': {
+            'id': '2458',
+            'ext': 'mp4',
+            'title': '첫 방송',
+            'channel': '강지',
+            'channel_id': 'b5ed5db484d04faf4d150aedd362f34b',
+            'channel_is_verified': True,
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 4433,
+            'timestamp': 1703307460.214,
+            'upload_date': '20231223',
+            'view_count': int,
+        },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_meta = self._download_json(
-            f'https://api.chzzk.naver.com/service/v2/videos/{video_id}', video_id,
+            f'https://api.chzzk.naver.com/service/v3/videos/{video_id}', video_id,
             note='Downloading video info', errnote='Unable to download video info')['content']
         formats, subtitles = self._extract_mpd_formats_and_subtitles(
             f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}', video_id,

yt_dlp/extractor/common.py

@@ -35,6 +35,7 @@
 from ..networking.exceptions import (
     HTTPError,
     IncompleteRead,
+    TransportError,
     network_exceptions,
 )
 from ..networking.impersonate import ImpersonateTarget
@@ -572,13 +573,13 @@ class InfoExtractor:
 
     def _login_hint(self, method=NO_DEFAULT, netrc=None):
         password_hint = f'--username and --password, --netrc-cmd, or --netrc ({netrc or self._NETRC_MACHINE}) to provide account credentials'
+        cookies_hint = 'See  https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp  for how to manually pass cookies'
         return {
             None: '',
-            'any': f'Use --cookies, --cookies-from-browser, {password_hint}',
+            'any': f'Use --cookies, --cookies-from-browser, {password_hint}. {cookies_hint}',
             'password': f'Use {password_hint}',
-            'cookies': (
+            'cookies': f'Use --cookies-from-browser or --cookies for the authentication. {cookies_hint}',
-                'Use --cookies-from-browser or --cookies for the authentication. '
+            'session_cookies': f'Use --cookies for the authentication (--cookies-from-browser might not work). {cookies_hint}',
-                'See  https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp  for how to manually pass cookies'),
         }[method if method is not NO_DEFAULT else 'any' if self.supports_login() else 'cookies']
 
     def __init__(self, downloader=None):
@@ -965,6 +966,9 @@ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=
             return False
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal,
                                              encoding=encoding, data=data)
+        if content is False:
+            assert not fatal
+            return False
         return (content, urlh)
 
     @staticmethod
@@ -1039,7 +1043,15 @@ def __decode_webpage(self, webpage_bytes, encoding, headers):
 
     def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True,
                               prefix=None, encoding=None, data=None):
-        webpage_bytes = urlh.read()
+        try:
+            webpage_bytes = urlh.read()
+        except TransportError as err:
+            errmsg = f'{video_id}: Error reading response: {err.msg}'
+            if fatal:
+                raise ExtractorError(errmsg, cause=err)
+            self.report_warning(errmsg)
+            return False
+
         if prefix is not None:
             webpage_bytes = prefix + webpage_bytes
         if self.get_param('dump_intermediate_pages', False):
@@ -1698,7 +1710,7 @@ def traverse_json_ld(json_ld, at_top_level=True):
                 rating = traverse_obj(e, ('aggregateRating', 'ratingValue'), expected_type=float_or_none)
                 if rating is not None:
                     info['average_rating'] = rating
-                if is_type(e, 'TVEpisode', 'Episode'):
+                if is_type(e, 'TVEpisode', 'Episode', 'PodcastEpisode'):
                     episode_name = unescapeHTML(e.get('name'))
                     info.update({
                         'episode': episode_name,
@@ -2065,7 +2077,7 @@ def _parse_m3u8_formats_and_subtitles(
         has_drm = HlsFD._has_drm(m3u8_doc)
 
         def format_url(url):
-            return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url)
+            return url if re.match(r'https?://', url) else urllib.parse.urljoin(m3u8_url, url)
 
         if self.get_param('hls_split_discontinuity', False):
             def _extract_m3u8_playlist_indices(manifest_url=None, m3u8_doc=None):
@@ -2800,11 +2812,11 @@ def extract_Initialization(source):
                         base_url_e = element.find(_add_ns('BaseURL'))
                         if try_call(lambda: base_url_e.text) is not None:
                             base_url = base_url_e.text + base_url
-                            if re.match(r'^https?://', base_url):
+                            if re.match(r'https?://', base_url):
                                 break
                     if mpd_base_url and base_url.startswith('/'):
                         base_url = urllib.parse.urljoin(mpd_base_url, base_url)
-                    elif mpd_base_url and not re.match(r'^https?://', base_url):
+                    elif mpd_base_url and not re.match(r'https?://', base_url):
                         if not mpd_base_url.endswith('/'):
                             mpd_base_url += '/'
                         base_url = mpd_base_url + base_url
@@ -2894,7 +2906,7 @@ def prepare_template(template_name, identifiers):
                         }
 
                     def location_key(location):
-                        return 'url' if re.match(r'^https?://', location) else 'path'
+                        return 'url' if re.match(r'https?://', location) else 'path'
 
                     if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
 
@@ -3150,7 +3162,7 @@ def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None):
                     })
         return formats, subtitles
 
-    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None):
+    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None, _headers=None):
         def absolute_url(item_url):
             return urljoin(base_url, item_url)
 
@@ -3174,11 +3186,11 @@ def _media_formats(src, cur_media_type, type_info=None):
                 formats = self._extract_m3u8_formats(
                     full_url, video_id, ext='mp4',
                     entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
-                    preference=preference, quality=quality, fatal=False)
+                    preference=preference, quality=quality, fatal=False, headers=_headers)
             elif ext == 'mpd':
                 is_plain_url = False
                 formats = self._extract_mpd_formats(
-                    full_url, video_id, mpd_id=mpd_id, fatal=False)
+                    full_url, video_id, mpd_id=mpd_id, fatal=False, headers=_headers)
             else:
                 is_plain_url = True
                 formats = [{
@@ -3272,6 +3284,8 @@ def _media_formats(src, cur_media_type, type_info=None):
                         })
             for f in media_info['formats']:
                 f.setdefault('http_headers', {})['Referer'] = base_url
+                if _headers:
+                    f['http_headers'].update(_headers)
             if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries
@@ -3487,7 +3501,7 @@ def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
                 continue
             urls.add(source_url)
             source_type = source.get('type') or ''
-            ext = mimetype2ext(source_type) or determine_ext(source_url)
+            ext = determine_ext(source_url, default_ext=mimetype2ext(source_type))
             if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',

yt_dlp/extractor/cwtv.py

@@ -6,12 +6,37 @@
     parse_iso8601,
     smuggle_url,
     str_or_none,
+    update_url_query,
 )
 
 
 class CWTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
     _TESTS = [{
+        'url': 'https://www.cwtv.com/shows/all-american-homecoming/ready-or-not/?play=d848488f-f62a-40fd-af1f-6440b1821aab',
+        'info_dict': {
+            'id': 'd848488f-f62a-40fd-af1f-6440b1821aab',
+            'ext': 'mp4',
+            'title': 'Ready Or Not',
+            'description': 'Simone is concerned about changes taking place at Bringston; JR makes a decision about his future.',
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'duration': 2547,
+            'timestamp': 1720519200,
+            'uploader': 'CWTV',
+            'chapters': 'count:6',
+            'series': 'All American: Homecoming',
+            'season_number': 3,
+            'episode_number': 1,
+            'age_limit': 0,
+            'upload_date': '20240709',
+            'season': 'Season 3',
+            'episode': 'Episode 1',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
         'info_dict': {
             'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
@@ -69,13 +94,14 @@ class CWTVIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         data = self._download_json(
-            'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id,
+            f'https://images.cwtv.com/feed/mobileapp/video-meta/apiversion_12/guid_{video_id}', video_id)
-            video_id)
         if data.get('result') != 'ok':
             raise ExtractorError(data['msg'], expected=True)
         video_data = data['video']
         title = video_data['title']
-        mpx_url = video_data.get('mpx_url') or f'http://link.theplatform.com/s/cwtv/media/guid/2703454149/{video_id}?formats=M3U'
+        mpx_url = update_url_query(
+            video_data.get('mpx_url') or f'https://link.theplatform.com/s/cwtv/media/guid/2703454149/{video_id}',
+            {'formats': 'M3U+none'})
 
         season = str_or_none(video_data.get('season'))
         episode = str_or_none(video_data.get('episode'))

yt_dlp/extractor/digitalconcerthall.py

@@ -1,6 +1,8 @@
 from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
+    parse_codecs,
     try_get,
     url_or_none,
     urlencode_postdata,
@@ -12,6 +14,7 @@ class DigitalConcertHallIE(InfoExtractor):
     IE_DESC = 'DigitalConcertHall extractor'
     _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
     _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
+    _USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Safari/605.1.15'
     _ACCESS_TOKEN = None
     _NETRC_MACHINE = 'digitalconcerthall'
     _TESTS = [{
@@ -68,33 +71,42 @@ class DigitalConcertHallIE(InfoExtractor):
     }]
 
     def _perform_login(self, username, password):
-        token_response = self._download_json(
+        login_token = self._download_json(
             self._OAUTH_URL,
             None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({
                 'affiliate': 'none',
                 'grant_type': 'device',
                 'device_vendor': 'unknown',
+                # device_model 'Safari' gets split streams of 4K/HEVC video and lossless/FLAC audio
+                'device_model': 'unknown' if self._configuration_arg('prefer_combined_hls') else 'Safari',
                 'app_id': 'dch.webapp',
-                'app_version': '1.0.0',
+                'app_distributor': 'berlinphil',
+                'app_version': '1.84.0',
                 'client_secret': '2ySLN+2Fwb',
             }), headers={
-                'Content-Type': 'application/x-www-form-urlencoded',
+                'Accept': 'application/json',
-            })
+                'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
-        self._ACCESS_TOKEN = token_response['access_token']
+                'User-Agent': self._USER_AGENT,
+            })['access_token']
         try:
-            self._download_json(
+            login_response = self._download_json(
                 self._OAUTH_URL,
                 None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({
                     'grant_type': 'password',
                     'username': username,
                     'password': password,
                 }), headers={
-                    'Content-Type': 'application/x-www-form-urlencoded',
+                    'Accept': 'application/json',
+                    'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
                     'Referer': 'https://www.digitalconcerthall.com',
-                    'Authorization': f'Bearer {self._ACCESS_TOKEN}',
+                    'Authorization': f'Bearer {login_token}',
+                    'User-Agent': self._USER_AGENT,
                 })
-        except ExtractorError:
+        except ExtractorError as error:
-            self.raise_login_required(msg='Login info incorrect')
+            if isinstance(error.cause, HTTPError) and error.cause.status == 401:
+                raise ExtractorError('Invalid username or password', expected=True)
+            raise
+        self._ACCESS_TOKEN = login_response['access_token']
 
     def _real_initialize(self):
         if not self._ACCESS_TOKEN:
@@ -108,11 +120,15 @@ def _entries(self, items, language, type_, **kwargs):
                     'Accept': 'application/json',
                     'Authorization': f'Bearer {self._ACCESS_TOKEN}',
                     'Accept-Language': language,
+                    'User-Agent': self._USER_AGENT,
                 })
 
             formats = []
             for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
-                formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False))
+                formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+            for fmt in formats:
+                if fmt.get('format_note') and fmt.get('vcodec') == 'none':
+                    fmt.update(parse_codecs(fmt['format_note']))
 
             yield {
                 'id': video_id,
@@ -140,13 +156,15 @@ def _real_extract(self, url):
             f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
                 'Accept': 'application/json',
                 'Accept-Language': language,
+                'User-Agent': self._USER_AGENT,
+                'Authorization': f'Bearer {self._ACCESS_TOKEN}',
             })
-        album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
         videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
 
         if type_ == 'work':
             videos = [videos[int(part) - 1]]
 
+        album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name', {str}))
         thumbnail = traverse_obj(vid_info, (
             'image', ..., {self._proto_relative_url}, {url_or_none},
             {lambda x: x.format(width=0, height=0)}, any))  # NB: 0x0 is the original size

yt_dlp/extractor/discovery.py

@@ -1,115 +0,0 @@
-import random
-import string
-import urllib.parse
-
-from .discoverygo import DiscoveryGoBaseIE
-from ..networking.exceptions import HTTPError
-from ..utils import ExtractorError
-
-
-class DiscoveryIE(DiscoveryGoBaseIE):
-    _VALID_URL = r'''(?x)https?://
-        (?P<site>
-            go\.discovery|
-            www\.
-                (?:
-                    investigationdiscovery|
-                    discoverylife|
-                    animalplanet|
-                    ahctv|
-                    destinationamerica|
-                    sciencechannel|
-                    tlc
-                )|
-            watch\.
-                (?:
-                    hgtv|
-                    foodnetwork|
-                    travelchannel|
-                    diynetwork|
-                    cookingchanneltv|
-                    motortrend
-                )
-        )\.com/tv-shows/(?P<show_slug>[^/]+)/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
-    _TESTS = [{
-        'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
-        'info_dict': {
-            'id': '5a2f35ce6b66d17a5026e29e',
-            'ext': 'mp4',
-            'title': 'Riding with Matthew Perry',
-            'description': 'md5:a34333153e79bc4526019a5129e7f878',
-            'duration': 84,
-        },
-        'params': {
-            'skip_download': True,  # requires ffmpeg
-        },
-    }, {
-        'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision',
-        'only_matching': True,
-    }, {
-        'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road',
-        'only_matching': True,
-    }, {
-        # using `show_slug` is important to get the correct video data
-        'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special',
-        'only_matching': True,
-    }]
-    _GEO_COUNTRIES = ['US']
-    _GEO_BYPASS = False
-    _API_BASE_URL = 'https://api.discovery.com/v1/'
-
-    def _real_extract(self, url):
-        site, show_slug, display_id = self._match_valid_url(url).groups()
-
-        access_token = None
-        cookies = self._get_cookies(url)
-
-        # prefer Affiliate Auth Token over Anonymous Auth Token
-        auth_storage_cookie = cookies.get('eosAf') or cookies.get('eosAn')
-        if auth_storage_cookie and auth_storage_cookie.value:
-            auth_storage = self._parse_json(urllib.parse.unquote(
-                urllib.parse.unquote(auth_storage_cookie.value)),
-                display_id, fatal=False) or {}
-            access_token = auth_storage.get('a') or auth_storage.get('access_token')
-
-        if not access_token:
-            access_token = self._download_json(
-                f'https://{site}.com/anonymous', display_id,
-                'Downloading token JSON metadata', query={
-                    'authRel': 'authorization',
-                    'client_id': '3020a40c2356a645b4b4',
-                    'nonce': ''.join(random.choices(string.ascii_letters, k=32)),
-                    'redirectUri': 'https://www.discovery.com/',
-                })['access_token']
-
-        headers = self.geo_verification_headers()
-        headers['Authorization'] = 'Bearer ' + access_token
-
-        try:
-            video = self._download_json(
-                self._API_BASE_URL + 'content/videos',
-                display_id, 'Downloading content JSON metadata',
-                headers=headers, query={
-                    'embed': 'show.name',
-                    'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags',
-                    'slug': display_id,
-                    'show_slug': show_slug,
-                })[0]
-            video_id = video['id']
-            stream = self._download_json(
-                self._API_BASE_URL + 'streaming/video/' + video_id,
-                display_id, 'Downloading streaming JSON metadata', headers=headers)
-        except ExtractorError as e:
-            if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
-                e_description = self._parse_json(
-                    e.cause.response.read().decode(), display_id)['description']
-                if 'resource not available for country' in e_description:
-                    self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-                if 'Authorized Networks' in e_description:
-                    raise ExtractorError(
-                        'This video is only available via cable service provider subscription that'
-                        ' is not currently supported. You may want to use --cookies.', expected=True)
-                raise ExtractorError(e_description)
-            raise
-
-        return self._extract_video_info(video, stream, display_id)

yt_dlp/extractor/discoverygo.py

@@ -1,171 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    determine_ext,
-    extract_attributes,
-    int_or_none,
-    parse_age_limit,
-    remove_end,
-    unescapeHTML,
-    url_or_none,
-)
-
-
-class DiscoveryGoBaseIE(InfoExtractor):
-    _VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
-            discovery|
-            investigationdiscovery|
-            discoverylife|
-            animalplanet|
-            ahctv|
-            destinationamerica|
-            sciencechannel|
-            tlc|
-            velocitychannel
-        )go\.com/%s(?P<id>[^/?#&]+)'''
-
-    def _extract_video_info(self, video, stream, display_id):
-        title = video['name']
-
-        if not stream:
-            if video.get('authenticated') is True:
-                raise ExtractorError(
-                    'This video is only available via cable service provider subscription that'
-                    ' is not currently supported. You may want to use --cookies.', expected=True)
-            else:
-                raise ExtractorError('Unable to find stream')
-        STREAM_URL_SUFFIX = 'streamUrl'
-        formats = []
-        for stream_kind in ('', 'hds'):
-            suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
-            stream_url = stream.get(f'{stream_kind}{suffix}')
-            if not stream_url:
-                continue
-            if stream_kind == '':
-                formats.extend(self._extract_m3u8_formats(
-                    stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-            elif stream_kind == 'hds':
-                formats.extend(self._extract_f4m_formats(
-                    stream_url, display_id, f4m_id=stream_kind, fatal=False))
-
-        video_id = video.get('id') or display_id
-        description = video.get('description', {}).get('detailed')
-        duration = int_or_none(video.get('duration'))
-
-        series = video.get('show', {}).get('name')
-        season_number = int_or_none(video.get('season', {}).get('number'))
-        episode_number = int_or_none(video.get('episodeNumber'))
-
-        tags = video.get('tags')
-        age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
-
-        subtitles = {}
-        captions = stream.get('captions')
-        if isinstance(captions, list):
-            for caption in captions:
-                subtitle_url = url_or_none(caption.get('fileUrl'))
-                if not subtitle_url or not subtitle_url.startswith('http'):
-                    continue
-                lang = caption.get('fileLang', 'en')
-                ext = determine_ext(subtitle_url)
-                subtitles.setdefault(lang, []).append({
-                    'url': subtitle_url,
-                    'ext': 'ttml' if ext == 'xml' else ext,
-                })
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'series': series,
-            'season_number': season_number,
-            'episode_number': episode_number,
-            'tags': tags,
-            'age_limit': age_limit,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-
-class DiscoveryGoIE(DiscoveryGoBaseIE):
-    _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
-    _GEO_COUNTRIES = ['US']
-    _TEST = {
-        'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
-        'info_dict': {
-            'id': '58c167d86b66d12f2addeb01',
-            'ext': 'mp4',
-            'title': 'Reaper Madness',
-            'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
-            'duration': 2519,
-            'series': 'Bering Sea Gold',
-            'season_number': 8,
-            'episode_number': 6,
-            'age_limit': 14,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        container = extract_attributes(
-            self._search_regex(
-                r'(<div[^>]+class=["\']video-player-container[^>]+>)',
-                webpage, 'video container'))
-
-        video = self._parse_json(
-            container.get('data-video') or container.get('data-json'),
-            display_id)
-
-        stream = video.get('stream')
-
-        return self._extract_video_info(video, stream, display_id)
-
-
-class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
-    _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
-    _TEST = {
-        'url': 'https://www.discoverygo.com/bering-sea-gold/',
-        'info_dict': {
-            'id': 'bering-sea-gold',
-            'title': 'Bering Sea Gold',
-            'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
-        },
-        'playlist_mincount': 6,
-    }
-
-    @classmethod
-    def suitable(cls, url):
-        return False if DiscoveryGoIE.suitable(url) else super().suitable(url)
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        entries = []
-        for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
-            data = self._parse_json(
-                mobj.group('json'), display_id,
-                transform_source=unescapeHTML, fatal=False)
-            if not isinstance(data, dict) or data.get('type') != 'episode':
-                continue
-            episode_url = data.get('socialUrl')
-            if not episode_url:
-                continue
-            entries.append(self.url_result(
-                episode_url, ie=DiscoveryGoIE.ie_key(),
-                video_id=data.get('id')))
-
-        return self.playlist_result(
-            entries, display_id,
-            remove_end(self._og_search_title(
-                webpage, fatal=False), ' | Discovery GO'),
-            self._og_search_description(webpage))

yt_dlp/extractor/douyutv.py

@@ -24,8 +24,9 @@
 class DouyuBaseIE(InfoExtractor):
     def _download_cryptojs_md5(self, video_id):
         for url in [
+            # XXX: Do NOT use cdn.bootcdn.net; ref: https://sansec.io/research/polyfill-supply-chain-attack
             'https://cdnjs.cloudflare.com/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
-            'https://cdn.bootcdn.net/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
+            'https://unpkg.com/cryptojslib@3.1.2/rollups/md5.js',
         ]:
             js_code = self._download_webpage(
                 url, video_id, note='Downloading signing dependency', fatal=False)
@@ -35,7 +36,8 @@ def _download_cryptojs_md5(self, video_id):
         raise ExtractorError('Unable to download JS dependency (crypto-js/md5)')
 
     def _get_cryptojs_md5(self, video_id):
-        return self.cache.load('douyu', 'crypto-js-md5') or self._download_cryptojs_md5(video_id)
+        return self.cache.load(
+            'douyu', 'crypto-js-md5', min_ver='2024.07.04') or self._download_cryptojs_md5(video_id)
 
     def _calc_sign(self, sign_func, video_id, a):
         b = uuid.uuid4().hex

yt_dlp/extractor/dplay.py

@@ -319,35 +319,17 @@ def _real_extract(self, url):
             url, display_id, host, 'dplay' + country, country, domain)
 
 
-class HGTVDeIE(DPlayBaseIE):
-    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX
-    _TESTS = [{
-        'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
-        'info_dict': {
-            'id': '151205',
-            'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
-            'ext': 'mp4',
-            'title': 'Wer braucht schon eine Toilette',
-            'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
-            'duration': 1177.024,
-            'timestamp': 1595705400,
-            'upload_date': '20200725',
-            'creator': 'HGTV',
-            'series': 'Tiny House - klein, aber oho',
-            'season_number': 3,
-            'episode_number': 3,
-        },
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        return self._get_disco_api_info(
-            url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
-
-
 class DiscoveryPlusBaseIE(DPlayBaseIE):
+    """Subclasses must set _PRODUCT, _DISCO_API_PARAMS"""
+
+    _DISCO_CLIENT_VER = '27.43.0'
+
     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
-        headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6'
+        headers.update({
+            'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
+            'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:{self._DISCO_CLIENT_VER}',
+            'Authorization': self._get_auth(disco_base, display_id, realm),
+        })
 
     def _download_video_playback_info(self, disco_base, video_id, headers):
         return self._download_json(
@@ -365,9 +347,68 @@ def _real_extract(self, url):
         return self._get_disco_api_info(url, self._match_id(url), **self._DISCO_API_PARAMS)
 
 
+class HGTVDeIE(DiscoveryPlusBaseIE):
+    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://de.hgtv.com/sendungen/mein-kleinstadt-traumhaus/vom-landleben-ins-loft',
+        'info_dict': {
+            'id': '7332936',
+            'ext': 'mp4',
+            'display_id': 'mein-kleinstadt-traumhaus/vom-landleben-ins-loft',
+            'title': 'Vom Landleben ins Loft',
+            'description': 'md5:e5f72c02c853970796dd3818f2e25745',
+            'episode': 'Episode 7',
+            'episode_number': 7,
+            'season': 'Season 7',
+            'season_number': 7,
+            'series': 'Mein Kleinstadt-Traumhaus',
+            'duration': 2645.0,
+            'timestamp': 1725998100,
+            'upload_date': '20240910',
+            'creators': ['HGTV'],
+            'tags': [],
+            'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/08/09/82a386b9-c688-32c7-b9ff-0b13865f0bae.jpeg',
+        },
+    }]
+
+    _PRODUCT = 'hgtv'
+    _DISCO_API_PARAMS = {
+        'disco_host': 'eu1-prod.disco-api.com',
+        'realm': 'hgtv',
+        'country': 'de',
+    }
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers.update({
+            'x-disco-params': f'realm={realm}',
+            'x-disco-client': 'Alps:HyogaPlayer:0.0.0',
+            'Authorization': self._get_auth(disco_base, display_id, realm),
+        })
+
+
 class GoDiscoveryIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://go.discovery.com/video/in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
+        'info_dict': {
+            'id': '5352642',
+            'display_id': 'in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
+            'ext': 'mp4',
+            'title': 'Trapped in a Twister',
+            'description': 'Twisters destroy Midwest towns, trapping spotters in the eye of the storm.',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'season_number': 1,
+            'season': 'Season 1',
+            'series': 'In The Eye Of The Storm',
+            'duration': 2490.237,
+            'upload_date': '20240715',
+            'timestamp': 1721008800,
+            'tags': [],
+            'creators': ['Discovery'],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/10/5e39637d-cabf-3ab3-8e9a-f4e9d37bc036.jpeg',
+        },
+    }, {
         'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
         'info_dict': {
             'id': '4164906',
@@ -395,6 +436,26 @@ class GoDiscoveryIE(DiscoveryPlusBaseIE):
 class TravelChannelIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://watch.travelchannel.com/video/the-dead-files-travel-channel/protect-the-children',
+        'info_dict': {
+            'id': '4710177',
+            'display_id': 'the-dead-files-travel-channel/protect-the-children',
+            'ext': 'mp4',
+            'title': 'Protect the Children',
+            'description': 'An evil presence threatens an Ohio woman\'s children and marriage.',
+            'season_number': 14,
+            'season': 'Season 14',
+            'episode_number': 10,
+            'episode': 'Episode 10',
+            'series': 'The Dead Files',
+            'duration': 2550.481,
+            'timestamp': 1664510400,
+            'upload_date': '20220930',
+            'tags': [],
+            'creators': ['Travel Channel'],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/17/5e45eace-de5d-343a-9293-f400a2aa77d5.jpeg',
+        },
+    }, {
         'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely',
         'info_dict': {
             'id': '2220256',
@@ -422,6 +483,26 @@ class TravelChannelIE(DiscoveryPlusBaseIE):
 class CookingChannelIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://watch.cookingchanneltv.com/video/bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
+        'info_dict': {
+            'id': '5350005',
+            'ext': 'mp4',
+            'display_id': 'bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
+            'title': 'Titans vs Marcus Samuelsson',
+            'description': 'Marcus Samuelsson throws his legendary global tricks at the Titans.',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'season_number': 3,
+            'season': 'Season 3',
+            'series': 'Bobby\'s Triple Threat',
+            'duration': 2520.851,
+            'upload_date': '20240710',
+            'timestamp': 1720573200,
+            'tags': [],
+            'creators': ['Food Network'],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/04/529cd095-27ec-35c5-84e9-90ebd3e5d2da.jpeg',
+        },
+    }, {
         'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
         'info_dict': {
             'id': '2348634',
@@ -449,6 +530,22 @@ class CookingChannelIE(DiscoveryPlusBaseIE):
 class HGTVUsaIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://watch.hgtv.com/video/flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
+        'info_dict': {
+            'id': '5025585',
+            'display_id': 'flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
+            'ext': 'mp4',
+            'title': 'Flip or Flop: The Final Flip',
+            'description': 'Tarek and Christina are going their separate ways after one last flip!',
+            'series': 'Flip or Flop: The Final Flip',
+            'duration': 2580.644,
+            'upload_date': '20231101',
+            'timestamp': 1698811200,
+            'tags': [],
+            'creators': ['HGTV'],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2022/11/27/455caa6c-1462-3f14-b63d-a026d7a5e6d3.jpeg',
+        },
+    }, {
         'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house',
         'info_dict': {
             'id': '4289736',
@@ -476,6 +573,26 @@ class HGTVUsaIE(DiscoveryPlusBaseIE):
 class FoodNetworkIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://watch.foodnetwork.com/video/guys-grocery-games-food-network/wild-in-the-aisles',
+        'info_dict': {
+            'id': '2152549',
+            'display_id': 'guys-grocery-games-food-network/wild-in-the-aisles',
+            'ext': 'mp4',
+            'title': 'Wild in the Aisles',
+            'description': 'The chefs make spaghetti and meatballs with "Out of Stock" ingredients.',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': 'Guy\'s Grocery Games',
+            'tags': [],
+            'creators': ['Food Network'],
+            'duration': 2520.651,
+            'upload_date': '20230623',
+            'timestamp': 1687492800,
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2022/06/15/37fb5333-cad2-3dbb-af7c-c20ec77c89c6.jpeg',
+        },
+    }, {
         'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly',
         'info_dict': {
             'id': '4116449',
@@ -503,6 +620,26 @@ class FoodNetworkIE(DiscoveryPlusBaseIE):
 class DestinationAmericaIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.destinationamerica.com/video/bbq-pit-wars-destination-america/smoke-on-the-water',
+        'info_dict': {
+            'id': '2218409',
+            'display_id': 'bbq-pit-wars-destination-america/smoke-on-the-water',
+            'ext': 'mp4',
+            'title': 'Smoke on the Water',
+            'description': 'The pitmasters head to Georgia for the Smoke on the Water BBQ Festival.',
+            'season_number': 2,
+            'season': 'Season 2',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': 'BBQ Pit Wars',
+            'tags': [],
+            'creators': ['Destination America'],
+            'duration': 2614.878,
+            'upload_date': '20230623',
+            'timestamp': 1687492800,
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/c0f8e85d-9a10-3e6f-8e43-f6faafa81ba2.jpeg',
+        },
+    }, {
         'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
         'info_dict': {
             'id': '4210904',
@@ -530,6 +667,26 @@ class DestinationAmericaIE(DiscoveryPlusBaseIE):
 class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.investigationdiscovery.com/video/deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
+        'info_dict': {
+            'id': '5341132',
+            'display_id': 'deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
+            'ext': 'mp4',
+            'title': 'RIP Bianca',
+            'description': 'A teenage influencer discovers an online world of threat, harm and danger.',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 3,
+            'episode': 'Episode 3',
+            'series': 'Deadly Influence: The Social Media Murders',
+            'creators': ['Investigation Discovery'],
+            'tags': [],
+            'duration': 2490.888,
+            'upload_date': '20240618',
+            'timestamp': 1718672400,
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2024/06/15/b567c774-9e44-3c6c-b0ba-db860a73e812.jpeg',
+        },
+    }, {
         'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown',
         'info_dict': {
             'id': '2139409',
@@ -557,6 +714,26 @@ class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
 class AmHistoryChannelIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.ahctv.com/video/blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
+        'info_dict': {
+            'id': '2139199',
+            'display_id': 'blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
+            'ext': 'mp4',
+            'title': 'Battle of Bull Run',
+            'description': 'Two untested armies clash in the first real battle of the Civil War.',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': 'Blood and Fury: America\'s Civil War',
+            'duration': 2612.509,
+            'upload_date': '20220923',
+            'timestamp': 1663905600,
+            'creators': ['AHC'],
+            'tags': [],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/4af61bd7-d705-3108-82c4-1a6e541e20fa.jpeg',
+        },
+    }, {
         'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army',
         'info_dict': {
             'id': '2309730',
@@ -584,6 +761,26 @@ class AmHistoryChannelIE(DiscoveryPlusBaseIE):
 class ScienceChannelIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.sciencechannel.com/video/spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
+        'info_dict': {
+            'id': '2347335',
+            'display_id': 'spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
+            'ext': 'mp4',
+            'title': 'Mystery of the Dead Planets',
+            'description': 'Astronomers unmask the truly destructive nature of the cosmos.',
+            'season_number': 7,
+            'season': 'Season 7',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': 'Space\'s Deepest Secrets',
+            'duration': 2524.989,
+            'upload_date': '20230128',
+            'timestamp': 1674882000,
+            'creators': ['Science'],
+            'tags': [],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/30/3796829d-aead-3f9a-bd8d-e49048b3cdca.jpeg',
+        },
+    }, {
         'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
         'info_dict': {
             'id': '2842849',
@@ -608,36 +805,29 @@ class ScienceChannelIE(DiscoveryPlusBaseIE):
     }
 
 
-class DIYNetworkIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayBaseIE._PATH_REGEX
-    _TESTS = [{
-        'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
-        'info_dict': {
-            'id': '2309730',
-            'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas',
-            'ext': 'mp4',
-            'title': 'Bringing Beach Life to Texas',
-            'description': 'The Pool Kings give a family a day at the beach in their own backyard.',
-            'season_number': 10,
-            'episode_number': 2,
-        },
-        'skip': 'Available for Premium users',
-    }, {
-        'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
-        'only_matching': True,
-    }]
-
-    _PRODUCT = 'diy'
-    _DISCO_API_PARAMS = {
-        'disco_host': 'us1-prod-direct.watch.diynetwork.com',
-        'realm': 'go',
-        'country': 'us',
-    }
-
-
 class DiscoveryLifeIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.discoverylife.com/video/er-files-discovery-life-atve-us/sweet-charity',
+        'info_dict': {
+            'id': '2347614',
+            'display_id': 'er-files-discovery-life-atve-us/sweet-charity',
+            'ext': 'mp4',
+            'title': 'Sweet Charity',
+            'description': 'The staff at Charity Hospital treat a serious foot infection.',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': 'ER Files',
+            'duration': 2364.261,
+            'upload_date': '20230721',
+            'timestamp': 1689912000,
+            'creators': ['Discovery Life'],
+            'tags': [],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/16/4b6f0124-360b-3546-b6a4-5552db886b86.jpeg',
+        },
+    }, {
         'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma',
         'info_dict': {
             'id': '2218238',
@@ -665,6 +855,26 @@ class DiscoveryLifeIE(DiscoveryPlusBaseIE):
 class AnimalPlanetIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://www.animalplanet.com/video/mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
+        'info_dict': {
+            'id': '4650835',
+            'display_id': 'mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
+            'ext': 'mp4',
+            'title': 'The Demon of Peru',
+            'description': 'In Peru, a farming village is being terrorized by a “man-like beast.”',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 4,
+            'episode': 'Episode 4',
+            'series': 'Mysterious Creatures with Forrest Galante',
+            'duration': 2490.488,
+            'upload_date': '20230111',
+            'timestamp': 1673413200,
+            'creators': ['Animal Planet'],
+            'tags': [],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/01/6dbaa833-9a2e-3fee-9381-c19eddf67c0c.jpeg',
+        },
+    }, {
         'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
         'info_dict': {
             'id': '3338923',
@@ -692,6 +902,26 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE):
 class TLCIE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
+        'url': 'https://go.tlc.com/video/90-day-the-last-resort-tlc-atve-us/the-last-chance',
+        'info_dict': {
+            'id': '5186422',
+            'display_id': '90-day-the-last-resort-tlc-atve-us/the-last-chance',
+            'ext': 'mp4',
+            'title': 'The Last Chance',
+            'description': 'Infidelity shakes Kalani and Asuelu\'s world, and Angela threatens divorce.',
+            'season_number': 1,
+            'season': 'Season 1',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'series': '90 Day: The Last Resort',
+            'duration': 5123.91,
+            'upload_date': '20230815',
+            'timestamp': 1692061200,
+            'creators': ['TLC'],
+            'tags': [],
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2023/08/08/0ee367e2-ac76-334d-bf23-dbf796696a24.jpeg',
+        },
+    }, {
         'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1',
         'info_dict': {
             'id': '2206540',
@@ -716,93 +946,8 @@ class TLCIE(DiscoveryPlusBaseIE):
     }
 
 
-class MotorTrendIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:watch\.)?motortrend\.com/video' + DPlayBaseIE._PATH_REGEX
-    _TESTS = [{
-        'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
-        'info_dict': {
-            'id': '"4859182"',
-            'display_id': 'double-dakotas',
-            'ext': 'mp4',
-            'title': 'Double Dakotas',
-            'description': 'Tylers buy-one-get-one Dakota deal has the Wizard pulling double duty.',
-            'season_number': 2,
-            'episode_number': 3,
-        },
-        'skip': 'Available for Premium users',
-    }, {
-        'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
-        'only_matching': True,
-    }]
-
-    _PRODUCT = 'vel'
-    _DISCO_API_PARAMS = {
-        'disco_host': 'us1-prod-direct.watch.motortrend.com',
-        'realm': 'go',
-        'country': 'us',
-    }
-
-
-class MotorTrendOnDemandIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?motortrend(?:ondemand\.com|\.com/plus)/detail' + DPlayBaseIE._PATH_REGEX
-    _TESTS = [{
-        'url': 'https://www.motortrendondemand.com/detail/wheelstanding-dump-truck-stubby-bobs-comeback/37699/784',
-        'info_dict': {
-            'id': '37699',
-            'display_id': 'wheelstanding-dump-truck-stubby-bobs-comeback/37699',
-            'ext': 'mp4',
-            'title': 'Wheelstanding Dump Truck! Stubby Bob’s Comeback',
-            'description': 'md5:996915abe52a1c3dfc83aecea3cce8e7',
-            'season_number': 5,
-            'episode_number': 52,
-            'episode': 'Episode 52',
-            'season': 'Season 5',
-            'thumbnail': r're:^https?://.+\.jpe?g$',
-            'timestamp': 1388534401,
-            'duration': 1887.345,
-            'creator': 'Originals',
-            'series': 'Roadkill',
-            'upload_date': '20140101',
-            'tags': [],
-        },
-    }, {
-        'url': 'https://www.motortrend.com/plus/detail/roadworthy-rescues-teaser-trailer/4922860/',
-        'info_dict': {
-            'id': '4922860',
-            'ext': 'mp4',
-            'title': 'Roadworthy Rescues | Teaser Trailer',
-            'description': 'Derek Bieri helps Freiburger and Finnegan with their \'68 big-block Dart.',
-            'display_id': 'roadworthy-rescues-teaser-trailer/4922860',
-            'creator': 'Originals',
-            'series': 'Roadworthy Rescues',
-            'thumbnail': r're:^https?://.+\.jpe?g$',
-            'upload_date': '20220907',
-            'timestamp': 1662523200,
-            'duration': 1066.356,
-            'tags': [],
-        },
-    }, {
-        'url': 'https://www.motortrend.com/plus/detail/ugly-duckling/2450033/12439',
-        'only_matching': True,
-    }]
-
-    _PRODUCT = 'MTOD'
-    _DISCO_API_PARAMS = {
-        'disco_host': 'us1-prod-direct.motortrendondemand.com',
-        'realm': 'motortrend',
-        'country': 'us',
-    }
-
-    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
-        headers.update({
-            'x-disco-params': f'realm={realm}',
-            'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:4.39.1-gi1',
-            'Authorization': self._get_auth(disco_base, display_id, realm),
-        })
-
-
 class DiscoveryPlusIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
         'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
         'info_dict': {
@@ -823,14 +968,45 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE):
     }, {
         'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/gb/video/olympics/dplus-sport-dplus-sport-sport/rugby-sevens-australia-samoa',
+        'only_matching': True,
     }]
 
-    _PRODUCT = 'dplus_us'
+    _PRODUCT = None
-    _DISCO_API_PARAMS = {
+    _DISCO_API_PARAMS = None
-        'disco_host': 'us1-prod-direct.discoveryplus.com',
+
-        'realm': 'go',
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
-        'country': 'us',
+        headers.update({
-    }
+            'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
+            'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
+            'Authorization': self._get_auth(disco_base, display_id, realm),
+        })
+
+    def _real_extract(self, url):
+        video_id, country = self._match_valid_url(url).group('id', 'country')
+        if not country:
+            country = 'us'
+
+        self._PRODUCT = f'dplus_{country}'
+
+        if country in ('br', 'ca', 'us'):
+            self._DISCO_API_PARAMS = {
+                'disco_host': 'us1-prod-direct.discoveryplus.com',
+                'realm': 'go',
+                'country': country,
+            }
+        else:
+            self._DISCO_API_PARAMS = {
+                'disco_host': 'eu1-prod-direct.discoveryplus.com',
+                'realm': 'dplay',
+                'country': country,
+            }
+
+        return self._get_disco_api_info(url, video_id, **self._DISCO_API_PARAMS)
 
 
 class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE):
@@ -984,16 +1160,22 @@ def _real_extract(self, url):
 
 
 class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
         'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi',
         'only_matching': True,
     }, {
         'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno',
+        'only_matching': True,
     }]
 
-    _PRODUCT = 'dplus_us'
+    _PRODUCT = 'dplus_it'
     _DISCO_API_PARAMS = {
         'disco_host': 'eu1-prod-direct.discoveryplus.com',
         'realm': 'dplay',
@@ -1002,8 +1184,8 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
 
     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
         headers.update({
-            'x-disco-params': f'realm={realm}',
+            'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
-            'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6',
+            'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
             'Authorization': self._get_auth(disco_base, display_id, realm),
         })
 
@@ -1044,39 +1226,3 @@ class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE):
     _SHOW_STR = 'show'
     _INDEX = 4
     _VIDEO_IE = DiscoveryPlusIndiaIE
-
-
-class GlobalCyclingNetworkPlusIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://plus\.globalcyclingnetwork\.com/watch/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://plus.globalcyclingnetwork.com/watch/1397691',
-        'info_dict': {
-            'id': '1397691',
-            'ext': 'mp4',
-            'title': 'The Athertons: Mountain Biking\'s Fastest Family',
-            'description': 'md5:75a81937fcd8b989eec6083a709cd837',
-            'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/04/eb9e3026-4849-3001-8281-9356466f0557.png',
-            'series': 'gcn',
-            'creator': 'Gcn',
-            'upload_date': '20210309',
-            'timestamp': 1615248000,
-            'duration': 2531.0,
-            'tags': [],
-        },
-        'skip': 'Subscription required',
-        'params': {'skip_download': 'm3u8'},
-    }]
-
-    _PRODUCT = 'web'
-    _DISCO_API_PARAMS = {
-        'disco_host': 'disco-api-prod.globalcyclingnetwork.com',
-        'realm': 'gcn',
-        'country': 'us',
-    }
-
-    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
-        headers.update({
-            'x-disco-params': f'realm={realm}',
-            'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:27.3.2',
-            'Authorization': self._get_auth(disco_base, display_id, realm),
-        })

yt_dlp/extractor/dropbox.py

@@ -6,8 +6,10 @@
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    update_url,
     update_url_query,
     url_basename,
+    urlencode_postdata,
 )
 
 
@@ -36,43 +38,58 @@ class DropboxIE(InfoExtractor):
         },
     ]
 
+    def _yield_decoded_parts(self, webpage):
+        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
+            yield base64.b64decode(encoded).decode('utf-8', 'ignore')
+
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         fn = urllib.parse.unquote(url_basename(url))
         title = os.path.splitext(fn)[0]
-
         password = self.get_param('videopassword')
-        if (self._og_search_title(webpage) == 'Dropbox - Password Required'
-                or 'Enter the password for this link' in webpage):
 
+        for part in self._yield_decoded_parts(webpage):
+            if '/sm/password' in part:
+                webpage = self._download_webpage(
+                    update_url('https://www.dropbox.com/sm/password', query=part.partition('?')[2]), video_id)
+                break
+
+        if (self._og_search_title(webpage, default=None) == 'Dropbox - Password Required'
+                or 'Enter the password for this link' in webpage):
             if password:
-                content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
-                payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
                 response = self._download_json(
-                    'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode(),
+                    'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password',
-                    headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+                    headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'},
+                    data=urlencode_postdata({
+                        'is_xhr': 'true',
+                        't': self._get_cookies('https://www.dropbox.com')['t'].value,
+                        'content_id': self._search_regex(r'content_id=([\w.+=/-]+)["\']', webpage, 'content id'),
+                        'password': password,
+                        'url': url,
+                    }))
 
                 if response.get('status') != 'authed':
-                    raise ExtractorError('Authentication failed!', expected=True)
+                    raise ExtractorError('Invalid password', expected=True)
-                webpage = self._download_webpage(url, video_id)
+            elif not self._get_cookies('https://dropbox.com').get('sm_auth'):
-            elif self._get_cookies('https://dropbox.com').get('sm_auth'):
-                webpage = self._download_webpage(url, video_id)
-            else:
                 raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
+            webpage = self._download_webpage(url, video_id)
 
-        formats, subtitles, has_anonymous_download = [], {}, False
+        formats, subtitles = [], {}
-        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
+        has_anonymous_download = False
-            decoded = base64.b64decode(encoded).decode('utf-8', 'ignore')
+        thumbnail = None
+        for part in self._yield_decoded_parts(webpage):
             if not has_anonymous_download:
                 has_anonymous_download = self._search_regex(
-                    r'(anonymous:\tanonymous)', decoded, 'anonymous', default=False)
+                    r'(anonymous:\tanonymous)', part, 'anonymous', default=False)
             transcode_url = self._search_regex(
-                r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', decoded, 'transcode url', default=None)
+                r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', part, 'transcode url', default=None)
             if not transcode_url:
                 continue
             formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id, 'mp4')
+            thumbnail = self._search_regex(
+                r'(https://www\.dropbox\.com/temp_thumb_from_token/[\w/?&=]+)', part, 'thumbnail', default=None)
             break
 
         # downloads enabled we can get the original file
@@ -89,4 +106,5 @@ def _real_extract(self, url):
             'title': title,
             'formats': formats,
             'subtitles': subtitles,
+            'thumbnail': thumbnail,
         }

yt_dlp/extractor/drtv.py

@@ -139,12 +139,11 @@ def _real_initialize(self):
             return
 
         token_response = self._download_json(
-            'https://production.dr-massive.com/api/authorization/anonymous-sso', None,
+            'https://isl.dr-massive.com/api/authorization/anonymous-sso', None,
             note='Downloading anonymous token', headers={
                 'content-type': 'application/json',
             }, query={
-                'device': 'web_browser',
+                'device': 'phone_android',
-                'ff': 'idp,ldp,rpt',
                 'lang': 'da',
                 'supportFallbackToken': 'true',
             }, data=json.dumps({

yt_dlp/extractor/epidemicsound.py

@@ -2,6 +2,7 @@
 from ..utils import (
     float_or_none,
     int_or_none,
+    join_nonempty,
     orderedSet,
     parse_iso8601,
     parse_qs,
@@ -13,7 +14,7 @@
 
 
 class EpidemicSoundIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/track/(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/(?:(?P<sfx>sound-effects/tracks)|track)/(?P<id>[0-9a-zA-Z-]+)'
     _TESTS = [{
         'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/',
         'md5': 'd98ff2ddb49e8acab9716541cbc9dfac',
@@ -47,6 +48,20 @@ class EpidemicSoundIE(InfoExtractor):
             'release_timestamp': 1700535606,
             'release_date': '20231121',
         },
+    }, {
+        'url': 'https://www.epidemicsound.com/sound-effects/tracks/2f02f54b-9faa-4daf-abac-1cfe9e9cef69/',
+        'md5': '35d7cf05bd8b614a84f0495a05de9388',
+        'info_dict': {
+            'id': '208931',
+            'ext': 'mp3',
+            'upload_date': '20240603',
+            'timestamp': 1717436529,
+            'categories': ['appliance'],
+            'display_id': '6b2NXLURPr',
+            'duration': 1.0,
+            'title': 'Oven, Grill, Door Open 01',
+            'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/default-sfx/3000x3000.jpg',
+        },
     }]
 
     @staticmethod
@@ -77,8 +92,10 @@ def _epidemic_fmt_or_none(f):
         return f
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, is_sfx = self._match_valid_url(url).group('id', 'sfx')
-        json_data = self._download_json(f'https://www.epidemicsound.com/json/track/{video_id}', video_id)
+        json_data = self._download_json(join_nonempty(
+            'https://www.epidemicsound.com/json/track',
+            is_sfx and 'kosmos-id', video_id, delim='/'), video_id)
 
         thumbnails = traverse_obj(json_data, [('imageUrl', 'cover')])
         thumb_base_url = traverse_obj(json_data, ('coverArt', 'baseUrl', {url_or_none}))

yt_dlp/extractor/ertgr.py

@@ -17,6 +17,7 @@
     url_or_none,
     variadic,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ERTFlixBaseIE(InfoExtractor):
@@ -74,29 +75,28 @@ class ERTFlixCodenameIE(ERTFlixBaseIE):
 
     def _extract_formats_and_subs(self, video_id):
         media_info = self._call_api(video_id, codename=video_id)
-        formats, subs = [], {}
+        formats, subtitles = [], {}
-        for media_file in try_get(media_info, lambda x: x['MediaFiles'], list) or []:
+        for media in traverse_obj(media_info, (
-            for media in try_get(media_file, lambda x: x['Formats'], list) or []:
+                'MediaFiles', lambda _, v: v['RoleCodename'] == 'main',
-                fmt_url = url_or_none(try_get(media, lambda x: x['Url']))
+                'Formats', lambda _, v: url_or_none(v['Url']))):
-                if not fmt_url:
+            fmt_url = media['Url']
-                    continue
+            ext = determine_ext(fmt_url)
-                ext = determine_ext(fmt_url)
+            if ext == 'm3u8':
-                if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    formats_, subs_ = self._extract_m3u8_formats_and_subtitles(
+                    fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
-                        fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
+            elif ext == 'mpd':
-                elif ext == 'mpd':
+                fmts, subs = self._extract_mpd_formats_and_subtitles(
-                    formats_, subs_ = self._extract_mpd_formats_and_subtitles(
+                    fmt_url, video_id, mpd_id='dash', fatal=False)
-                        fmt_url, video_id, mpd_id='dash', fatal=False)
+            else:
-                else:
+                formats.append({
-                    formats.append({
+                    'url': fmt_url,
-                        'url': fmt_url,
+                    'format_id': str_or_none(media.get('Id')),
-                        'format_id': str_or_none(media.get('Id')),
+                })
-                    })
+                continue
-                    continue
+            formats.extend(fmts)
-                formats.extend(formats_)
+            self._merge_subtitles(subs, target=subtitles)
-                self._merge_subtitles(subs_, target=subs)
 
-        return formats, subs
+        return formats, subtitles
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

yt_dlp/extractor/espn.py

@@ -294,37 +294,37 @@ def _real_extract(self, url):
 class WatchESPNIE(AdobePassIE):
     _VALID_URL = r'https?://(?:www\.)?espn\.com/(?:watch|espnplus)/player/_/id/(?P<id>[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})'
     _TESTS = [{
-        'url': 'https://www.espn.com/watch/player/_/id/dbbc6b1d-c084-4b47-9878-5f13c56ce309',
+        'url': 'https://www.espn.com/watch/player/_/id/11ce417a-6ac9-42b6-8a15-46aeb9ad5710',
         'info_dict': {
-            'id': 'dbbc6b1d-c084-4b47-9878-5f13c56ce309',
+            'id': '11ce417a-6ac9-42b6-8a15-46aeb9ad5710',
             'ext': 'mp4',
-            'title': 'Huddersfield vs. Burnley',
+            'title': 'Abilene Chrstn vs. Texas Tech',
-            'duration': 7500,
+            'duration': 14166,
-            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/dbbc6b1d-c084-4b47-9878-5f13c56ce309/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
+            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/11ce417a-6ac9-42b6-8a15-46aeb9ad5710/16x9.jpg?timestamp=202407252343&showBadge=true&cb=12&package=ESPN_PLUS',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.espn.com/watch/player/_/id/a049a56e-a7ce-477e-aef3-c7e48ef8221c',
+        'url': 'https://www.espn.com/watch/player/_/id/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3',
         'info_dict': {
-            'id': 'a049a56e-a7ce-477e-aef3-c7e48ef8221c',
+            'id': '90a2c85d-75e0-4b1e-a878-8e428a3cb2f3',
             'ext': 'mp4',
-            'title': 'Dynamo Dresden vs. VfB Stuttgart (Round #1) (German Cup)',
+            'title': 'UC Davis vs. California',
-            'duration': 8335,
+            'duration': 9547,
-            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/bd1f3d12-0654-47d9-852e-71b85ea695c7/16x9.jpg?timestamp=202201112217&showBadge=true&cb=12&package=ESPN_PLUS',
+            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.espn.com/espnplus/player/_/id/317f5fd1-c78a-4ebe-824a-129e0d348421',
+        'url': 'https://www.espn.com/watch/player/_/id/c4313bbe-95b5-4bb8-b251-ac143ea0fc54',
         'info_dict': {
-            'id': '317f5fd1-c78a-4ebe-824a-129e0d348421',
+            'id': 'c4313bbe-95b5-4bb8-b251-ac143ea0fc54',
             'ext': 'mp4',
-            'title': 'The Wheel - Episode 10',
+            'title': 'The College Football Show',
-            'duration': 3352,
+            'duration': 3639,
-            'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/317f5fd1-c78a-4ebe-824a-129e0d348421/16x9.jpg?timestamp=202205031523&showBadge=true&cb=12&package=ESPN_PLUS',
+            'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/c4313bbe-95b5-4bb8-b251-ac143ea0fc54/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs',
         },
         'params': {
             'skip_download': True,
@@ -353,6 +353,13 @@ def _real_extract(self, url):
             if not cookie:
                 self.raise_login_required(method='cookies')
 
+            jwt = self._search_regex(r'=([^|]+)\|', cookie.value, 'cookie jwt')
+            id_token = self._download_json(
+                'https://registerdisney.go.com/jgc/v6/client/ESPN-ONESITE.WEB-PROD/guest/refresh-auth',
+                None, 'Refreshing token', headers={'Content-Type': 'application/json'}, data=json.dumps({
+                    'refreshToken': json.loads(base64.urlsafe_b64decode(f'{jwt}==='))['refresh_token'],
+                }).encode())['data']['token']['id_token']
+
             assertion = self._call_bamgrid_api(
                 'devices', video_id,
                 headers={'Content-Type': 'application/json; charset=UTF-8'},
@@ -371,7 +378,7 @@ def _real_extract(self, url):
                 })['access_token']
 
             assertion = self._call_bamgrid_api(
-                'accounts/grant', video_id, payload={'id_token': cookie.value.split('|')[1]},
+                'accounts/grant', video_id, payload={'id_token': id_token},
                 headers={
                     'Authorization': token,
                     'Content-Type': 'application/json; charset=UTF-8',

yt_dlp/extractor/eurosport.py

@@ -3,7 +3,12 @@
 
 
 class EurosportIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.eurosport\.com/\w+/(?:[\w-]+/[\d-]+/)?[\w-]+_(?P<id>vid\d+)'
+    _VALID_URL = r'''(?x)
+        https?://(?:
+            (?:(?:www|espanol)\.)?eurosport\.(?:com(?:\.tr)?|de|dk|es|fr|hu|it|nl|no|ro)|
+            eurosport\.tvn24\.pl
+        )/[\w-]+/(?:[\w-]+/[\d-]+/)?[\w.-]+_(?P<id>vid\d+)
+    '''
     _TESTS = [{
         'url': 'https://www.eurosport.com/tennis/roland-garros/2022/highlights-rafael-nadal-brushes-aside-caper-ruud-to-win-record-extending-14th-french-open-title_vid1694147/video.shtml',
         'info_dict': {
@@ -70,6 +75,42 @@ class EurosportIE(InfoExtractor):
             'duration': 105.0,
             'upload_date': '20230518',
         },
+    }, {
+        'url': 'https://www.eurosport.de/radsport/vuelta-a-espana/2024/vuelta-a-espana-2024-wout-van-aert-und-co.-verzweifeln-an-mcnulty-zeitfahr-krimi-in-lissabon_vid2219478/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.dk/speedway/mikkel-michelsen-misser-finalen-i-cardiff-se-danskeren-i-semifinalen-her_vid2219363/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.nl/mixed-martial-arts/ufc/2022/ufc-305-respect-tussen-adesanya-en-du-plessis_vid2219650/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.es/ciclismo/la-vuelta-2024-carlos-rodriguez-olvida-la-crono-y-ya-espera-que-llegue-la-montana-no-me-encontre-nada-comodo_vid2219682/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.fr/football/supercoupe-d-europe/2024-2025/kylian-mbappe-vinicius-junior-eduardo-camavinga-touche.-extraits-de-l-entrainement-du-real-madrid-en-video_vid2216993/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.it/calcio/serie-a/2024-2025/samardzic-a-bergamo-per-le-visite-mediche-con-l-atalanta_vid2219680/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.hu/kerekpar/vuelta-a-espana/2024/dramai-harc-a-masodpercekert-meglepetesgyoztes-a-vuelta-nyitoszakaszan_vid2219481/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid30000618/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid2219531/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.ro/tenis/western-southern-open-2/2024/rezumatul-partidei-dintre-zverev-si-shelton-de-la-cincinnati_vid2219657/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.eurosport.com.tr/hentbol/olympic-games-paris-2024/2024/paris-2024-denmark-ile-germany-olimpiyatlarin-onemli-anlari_vid2215836/video.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'https://eurosport.tvn24.pl/kolarstwo/tour-de-france-kobiet/2024/kasia-niewiadoma-przed-ostatnim-8.-etapem-tour-de-france-kobiet_vid2219765/video.shtml',
+        'only_matching': True,
     }]
 
     _TOKEN = None
@@ -77,6 +118,7 @@ class EurosportIE(InfoExtractor):
     # actually defined in https://netsport.eurosport.io/?variables={"databaseId":<databaseId>,"playoutType":"VDP"}&extensions={"persistedQuery":{"version":1 ..
     # but this method require to get sha256 hash
     _GEO_COUNTRIES = ['DE', 'NL', 'EU', 'IT', 'FR']  # Not complete list but it should work
+    _GEO_BYPASS = False
 
     def _real_initialize(self):
         if EurosportIE._TOKEN is None:
@@ -98,13 +140,13 @@ def _real_extract(self, url):
         for stream_type in json_data['attributes']['streaming']:
             if stream_type == 'hls':
                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4')
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4', fatal=False)
             elif stream_type == 'dash':
                 fmts, subs = self._extract_mpd_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False)
             elif stream_type == 'mss':
                 fmts, subs = self._extract_ism_formats_and_subtitles(
-                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False)
 
             formats.extend(fmts)
             self._merge_subtitles(subs, target=subtitles)

yt_dlp/extractor/facebook.py

@@ -84,7 +84,7 @@ class FacebookIE(InfoExtractor):
             'timestamp': 1692346159,
             'thumbnail': r're:^https?://.*',
             'uploader_id': '100063551323670',
-            'duration': 3132.184,
+            'duration': 3133.583,
             'view_count': int,
             'concurrent_view_count': 0,
         },
@@ -112,9 +112,10 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20140506',
             'timestamp': 1399398998,
             'thumbnail': r're:^https?://.*',
-            'uploader_id': 'pfbid028wxorhX2ErLFJ578N6P3crHD3PHmXTCqCvfBpsnbSLmbokwSY75p5hWBjHGkG4zxl',
+            'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl',
             'duration': 131.03,
             'concurrent_view_count': int,
+            'view_count': int,
         },
     }, {
         'note': 'Video with DASH manifest',
@@ -167,7 +168,7 @@ class FacebookIE(InfoExtractor):
         # have 1080P, but only up to 720p in swf params
         # data.video.story.attachments[].media
         'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
-        'md5': 'ca63897a90c9452efee5f8c40d080e25',
+        'md5': '1659aa21fb3dd1585874f668e81a72c8',
         'info_dict': {
             'id': '10155529876156509',
             'ext': 'mp4',
@@ -180,9 +181,10 @@ class FacebookIE(InfoExtractor):
             'view_count': int,
             'uploader_id': '100059479812265',
             'concurrent_view_count': int,
-            'duration': 44.478,
+            'duration': 44.181,
         },
     }, {
+        # FIXME: unable to extract uploader, no formats found
         # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
         # data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
         'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
@@ -241,9 +243,9 @@ class FacebookIE(InfoExtractor):
             'timestamp': 1511548260,
             'upload_date': '20171124',
             'uploader': 'Vickie Gentry',
-            'uploader_id': 'pfbid0FuZhHCeWDAxWxEbr3yKPFaRstXvRxgsp9uCPG6GjD4J2AitB35NUAuJ4Q75KcjiDl',
+            'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l',
             'thumbnail': r're:^https?://.*',
-            'duration': 148.435,
+            'duration': 148.224,
         },
     }, {
         # data.node.comet_sections.content.story.attachments[].styles.attachment.media
@@ -271,7 +273,7 @@ class FacebookIE(InfoExtractor):
             'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...',
             'thumbnail': r're:^https?://.*',
             'uploader': 'Lela Evans',
-            'uploader_id': 'pfbid0shZJipuigyy5mqrUJn9ub5LJFWNHvan5prtyi3LrDuuuJ4NwrURgnQHYR9fywBepl',
+            'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl',
             'upload_date': '20231228',
             'timestamp': 1703804085,
             'duration': 394.347,
@@ -322,7 +324,7 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20180523',
             'uploader': 'ESL One Dota 2',
             'uploader_id': '100066514874195',
-            'duration': 4524.212,
+            'duration': 4524.001,
             'view_count': int,
             'thumbnail': r're:^https?://.*',
             'concurrent_view_count': int,
@@ -339,9 +341,9 @@ class FacebookIE(InfoExtractor):
             'title': 'Josef',
             'thumbnail': r're:^https?://.*',
             'concurrent_view_count': int,
-            'uploader_id': 'pfbid0cibUN6tV7DYgdbJdsUFN46wc4jKpVSPAvJQhFofGqBGmVn3V3JtAs2tfUwziw2hUl',
+            'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl',
             'timestamp': 1549275572,
-            'duration': 3.413,
+            'duration': 3.283,
             'uploader': 'Josef Novak',
             'description': '',
             'upload_date': '20190204',
@@ -396,6 +398,7 @@ class FacebookIE(InfoExtractor):
         'playlist_count': 1,
         'skip': 'Requires logging in',
     }, {
+        # FIXME: Cannot parse data error
         # data.event.cover_media_renderer.cover_video
         'url': 'https://m.facebook.com/events/1509582499515440',
         'info_dict': {
@@ -498,7 +501,8 @@ def extract_metadata(webpage):
                 or get_first(post, ('video', 'creation_story', 'attachments', ..., 'media', lambda k, v: k == 'owner' and v['name']))
                 or get_first(post, (..., 'video', lambda k, v: k == 'owner' and v['name']))
                 or get_first(post, ('node', 'actors', ..., {dict}))
-                or get_first(post, ('event', 'event_creator', {dict})) or {})
+                or get_first(post, ('event', 'event_creator', {dict}))
+                or get_first(post, ('video', 'creation_story', 'short_form_video_context', 'video_owner', {dict})) or {})
             uploader = uploader_data.get('name') or (
                 clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
                 or self._search_regex(
@@ -524,6 +528,11 @@ def extract_metadata(webpage):
                     webpage, 'view count', default=None)),
                 'concurrent_view_count': get_first(post, (
                     ('video', (..., ..., 'attachments', ..., 'media')), 'liveViewerCount', {int_or_none})),
+                **traverse_obj(post, (lambda _, v: video_id in v['url'], 'feedback', {
+                    'like_count': ('likers', 'count', {int}),
+                    'comment_count': ('total_comment_count', {int}),
+                    'repost_count': ('share_count_reduced', {parse_count}),
+                }), get_all=False),
             }
 
             info_json_ld = self._search_json_ld(webpage, video_id, default={})
@@ -571,16 +580,21 @@ def process_formats(info):
                 # Formats larger than ~500MB will return error 403 unless chunk size is regulated
                 f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20
 
-        def extract_relay_data(_filter):
+        def yield_all_relay_data(_filter):
-            return self._parse_json(self._search_regex(
+            for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})</script>', webpage):
-                rf'data-sjs>({{.*?{_filter}.*?}})</script>',
+                yield self._parse_json(relay_data, video_id, fatal=False) or {}
-                webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
 
-        def extract_relay_prefetched_data(_filter):
+        def extract_relay_data(_filter):
-            return traverse_obj(extract_relay_data(_filter), (
+            return next(filter(None, yield_all_relay_data(_filter)), {})
-                'require', (None, (..., ..., ..., '__bbox', 'require')),
+
+        def extract_relay_prefetched_data(_filter, target_keys=None):
+            path = 'data'
+            if target_keys is not None:
+                path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys))
+            return traverse_obj(yield_all_relay_data(_filter), (
+                ..., 'require', (None, (..., ..., ..., '__bbox', 'require')),
                 lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v),
-                ..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {}
+                ..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {}
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex([
@@ -591,7 +605,8 @@ def extract_relay_prefetched_data(_filter):
 
         if not video_data:
             data = extract_relay_prefetched_data(
-                r'"(?:dash_manifest|playable_url(?:_quality_hd)?)')
+                r'"(?:dash_manifest|playable_url(?:_quality_hd)?)',
+                target_keys=('video', 'event', 'nodes', 'node', 'mediaset'))
             if data:
                 entries = []
 
@@ -926,18 +941,21 @@ class FacebookReelIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'https://www.facebook.com/reel/1195289147628387',
-        'md5': 'f13dd37f2633595982db5ed8765474d3',
+        'md5': 'a53256d10fc2105441fe0c4212ed8cea',
         'info_dict': {
             'id': '1195289147628387',
             'ext': 'mp4',
-            'title': 'md5:b05800b5b1ad56c0ca78bd3807b6a61e',
+            'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$',
-            'description': 'md5:22f03309b216ac84720183961441d8db',
+            'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$',
-            'uploader': 'md5:723e6cb3091241160f20b3c5dc282af1',
+            'uploader': 'Beast Camp Training',
             'uploader_id': '100040874179269',
             'duration': 9.579,
             'timestamp': 1637502609,
             'upload_date': '20211121',
             'thumbnail': r're:^https?://.*',
+            'like_count': int,
+            'comment_count': int,
+            'repost_count': int,
         },
     }]
 
@@ -957,6 +975,7 @@ class FacebookAdsIE(InfoExtractor):
             'id': '899206155126718',
             'ext': 'mp4',
             'title': 'video by Kandao',
+            'description': 'md5:0822724069e3aca97cbed5dabbab282e',
             'uploader': 'Kandao',
             'uploader_id': '774114102743284',
             'uploader_url': r're:^https?://.*',
@@ -965,6 +984,22 @@ class FacebookAdsIE(InfoExtractor):
             'upload_date': '20231214',
             'like_count': int,
         },
+    }, {
+        # key 'watermarked_video_sd_url' missing
+        'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
+        'info_dict': {
+            'id': '501152689226254',
+            'ext': 'mp4',
+            'title': 'video by mat.nawrocki',
+            'description': 'md5:02a446ace7ff8c3c37a2892922492490',
+            'uploader': 'mat.nawrocki',
+            'uploader_id': '148586968341456',
+            'uploader_url': r're:^https?://.*',
+            'timestamp': 1723452305,
+            'thumbnail': r're:^https?://.*',
+            'upload_date': '20240812',
+            'like_count': int,
+        },
     }, {
         'url': 'https://www.facebook.com/ads/library/?id=893637265423481',
         'info_dict': {
@@ -1011,34 +1046,42 @@ def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        post_data = [self._parse_json(j, video_id, fatal=False)
+        post_data = traverse_obj(
-                     for j in re.findall(r's\.handle\(({.*})\);requireLazy\(', webpage)]
+            re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
-        data = traverse_obj(post_data, (
+        data = get_first(post_data, (
-            ..., 'require', ..., ..., ..., 'props', 'deeplinkAdCard', 'snapshot', {dict}), get_all=False)
+            'require', ..., ..., ..., '__bbox', 'require', ..., ..., ...,
+            'entryPointRoot', 'otherProps', 'deeplinkAdCard', 'snapshot', {dict}))
         if not data:
             raise ExtractorError('Unable to extract ad data')
 
         title = data.get('title')
         if not title or title == '{{product.name}}':
             title = join_nonempty('display_format', 'page_name', delim=' by ', from_dict=data)
+        markup_id = traverse_obj(data, ('body', '__m', {str}))
+        markup = traverse_obj(post_data, (
+            ..., 'require', ..., ..., ..., '__bbox', 'markup', lambda _, v: v[0].startswith(markup_id),
+            ..., '__html', {clean_html}, {lambda x: not x.startswith('{{product.') and x}, any))
 
-        info_dict = traverse_obj(data, {
+        info_dict = merge_dicts({
-            'description': ('link_description', {str}, {lambda x: x if x != '{{product.description}}' else None}),
+            'title': title,
+            'description': markup or None,
+        }, traverse_obj(data, {
+            'description': ('link_description', {lambda x: x if not x.startswith('{{product.') else None}),
             'uploader': ('page_name', {str}),
             'uploader_id': ('page_id', {str_or_none}),
             'uploader_url': ('page_profile_uri', {url_or_none}),
             'timestamp': ('creation_time', {int_or_none}),
             'like_count': ('page_like_count', {int_or_none}),
-        })
+        }))
 
         entries = []
         for idx, entry in enumerate(traverse_obj(
-            data, (('videos', 'cards'), lambda _, v: any(url_or_none(v[f]) for f in self._FORMATS_MAP))), 1,
+            data, (('videos', 'cards'), lambda _, v: any(url_or_none(v.get(f)) for f in self._FORMATS_MAP))), 1,
         ):
             entries.append({
                 'id': f'{video_id}_{idx}',
                 'title': entry.get('title') or title,
-                'description': entry.get('link_description') or info_dict.get('description'),
+                'description': traverse_obj(entry, 'body', 'link_description') or info_dict.get('description'),
                 'thumbnail': url_or_none(entry.get('video_preview_image_url')),
                 'formats': self._extract_formats(entry),
             })

yt_dlp/extractor/fc2.py

@@ -14,7 +14,7 @@
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
+    _VALID_URL = r'(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _NETRC_MACHINE = 'fc2'
     _TESTS = [{

yt_dlp/extractor/generic.py

@@ -8,6 +8,7 @@
 from .commonprotocols import RtmpIE
 from .youtube import YoutubeIE
 from ..compat import compat_etree_fromstring
+from ..networking.impersonate import ImpersonateTarget
 from ..utils import (
     KNOWN_EXTENSIONS,
     MEDIA_EXTENSIONS,
@@ -43,6 +44,7 @@
     xpath_text,
     xpath_with_ns,
 )
+from ..utils._utils import _UnsafeExtensionError
 
 
 class GenericIE(InfoExtractor):
@@ -2339,7 +2341,7 @@ def _real_extract(self, url):
                 default_search = 'fixup_error'
 
             if default_search in ('auto', 'auto_warning', 'fixup_error'):
-                if re.match(r'^[^\s/]+\.[^\s/]+/', url):
+                if re.match(r'[^\s/]+\.[^\s/]+/', url):
                     self.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
                 elif default_search != 'fixup_error':
@@ -2372,6 +2374,12 @@ def _real_extract(self, url):
         else:
             video_id = self._generic_id(url)
 
+        # Try to impersonate a web-browser by default if possible
+        # Skip impersonation if not available to omit the warning
+        impersonate = self._configuration_arg('impersonate', [''])
+        if 'false' in impersonate or not self._downloader._impersonate_target_available(ImpersonateTarget()):
+            impersonate = None
+
         # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
         # making it impossible to download only chunk of the file (yet we need only 512kB to
         # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
@@ -2383,7 +2391,7 @@ def _real_extract(self, url):
         full_response = self._request_webpage(url, video_id, headers=filter_dict({
             'Accept-Encoding': 'identity',
             'Referer': smuggled_data.get('referer'),
-        }))
+        }), impersonate=impersonate)
         new_url = full_response.url
         if new_url != extract_basic_auth(url)[0]:
             self.report_following_redirect(new_url)
@@ -2399,7 +2407,7 @@ def _real_extract(self, url):
 
         # Check for direct link to a video
         content_type = full_response.headers.get('Content-Type', '').lower()
-        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
+        m = re.match(r'(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
         if m:
             self.report_detected('direct video link')
             headers = filter_dict({'Referer': smuggled_data.get('referer')})
@@ -2446,9 +2454,13 @@ def _real_extract(self, url):
         if not is_html(first_bytes):
             self.report_warning(
                 'URL could be a direct video link, returning it as such.')
+            ext = determine_ext(url)
+            if ext not in _UnsafeExtensionError.ALLOWED_EXTENSIONS:
+                ext = 'unknown_video'
             info_dict.update({
                 'direct': True,
                 'url': url,
+                'ext': ext,
             })
             return info_dict
 

yt_dlp/extractor/germanupa.py

@@ -0,0 +1,91 @@
+from .common import InfoExtractor
+from .vimeo import VimeoIE
+from ..utils import (
+    parse_qs,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class GermanupaIE(InfoExtractor):
+    IE_DESC = 'germanupa.de'
+    _VALID_URL = r'https?://germanupa\.de/mediathek/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://germanupa.de/mediathek/4-figma-beratung-deine-sprechstunde-fuer-figma-fragen',
+        'info_dict': {
+            'id': '909179246',
+            'title': 'Tutorial: #4 Figma Beratung - Deine Sprechstunde für Figma-Fragen',
+            'ext': 'mp4',
+            'uploader': 'German UPA',
+            'uploader_id': 'germanupa',
+            'thumbnail': 'https://i.vimeocdn.com/video/1792564420-7415283ccef8bf8702dab8c6b7515555ceeb7a1c11371ffcc133b8e887dbf70e-d_1280',
+            'uploader_url': 'https://vimeo.com/germanupa',
+            'duration': 3987,
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'note': 'audio, uses GenericIE',
+        'url': 'https://germanupa.de/mediathek/live-vom-ux-festival-neuigkeiten-von-figma-jobmarkt-agenturszene-interview-zu-sustainable',
+        'info_dict': {
+            'id': '1867346676',
+            'title': 'Live vom UX Festival: Neuigkeiten von Figma, Jobmarkt, Agenturszene & Interview zu Sustainable UX',
+            'ext': 'opus',
+            'timestamp': 1720545088,
+            'upload_date': '20240709',
+            'duration': 3910.557,
+            'like_count': int,
+            'description': 'md5:db2aed5ff131e177a7b33901e9a8db05',
+            'uploader': 'German UPA',
+            'repost_count': int,
+            'genres': ['Science'],
+            'license': 'all-rights-reserved',
+            'uploader_url': 'https://soundcloud.com/user-80097677',
+            'uploader_id': '471579486',
+            'view_count': int,
+            'comment_count': int,
+            'thumbnail': 'https://i1.sndcdn.com/artworks-oCti2e9GhaZFWBqY-48ybGw-original.jpg',
+        },
+    }, {
+        'note': 'Nur für Mitglieder/Just for members',
+        'url': 'https://germanupa.de/mediathek/ux-festival-2024-usability-tests-und-ai',
+        'info_dict': {
+            'id': '986994430',
+            'title': 'UX Festival 2024 "Usability Tests und AI" von Lennart Weber',
+            'ext': 'mp4',
+            'release_date': '20240719',
+            'uploader_url': 'https://vimeo.com/germanupa',
+            'timestamp': 1721373980,
+            'license': 'by-sa',
+            'like_count': int,
+            'thumbnail': 'https://i.vimeocdn.com/video/1904187064-2a672630c30f9ad787bd390bff3f51d7506a3e8416763ba6dbf465732b165c5c-d_1280',
+            'duration': 2146,
+            'release_timestamp': 1721373980,
+            'uploader': 'German UPA',
+            'uploader_id': 'germanupa',
+            'upload_date': '20240719',
+            'comment_count': int,
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+        'skip': 'login required',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        param_url = traverse_obj(
+            self._search_regex(
+                r'<iframe[^>]+data-src\s*?=\s*?([\'"])(?P<url>https://germanupa\.de/media/oembed\?url=(?:(?!\1).)+)\1',
+                webpage, 'embedded video', default=None, group='url'),
+            ({parse_qs}, 'url', 0, {url_or_none}))
+
+        if not param_url:
+            if self._search_regex(
+                    r'<div[^>]+class\s*?=\s*?([\'"])(?:(?!\1).)*login-wrapper(?:(?!\1).)*\1',
+                    webpage, 'login wrapper', default=None):
+                self.raise_login_required('This video is only available for members')
+            return self.url_result(url, 'Generic')  # Fall back to generic to extract audio
+
+        real_url = param_url.replace('https://vimeo.com/', 'https://player.vimeo.com/video/')
+        return self.url_result(VimeoIE._smuggle_referrer(real_url, url), VimeoIE, video_id)

yt_dlp/extractor/getcourseru.py

@@ -52,7 +52,7 @@ class GetCourseRuIE(InfoExtractor):
     _BASE_URL_RE = rf'https?://(?:(?!player02\.)[^.]+\.getcourse\.(?:ru|io)|{"|".join(map(re.escape, _DOMAINS))})'
     _VALID_URL = [
         rf'{_BASE_URL_RE}/(?!pl/|teach/)(?P<id>[^?#]+)',
-        rf'{_BASE_URL_RE}/(:?pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
+        rf'{_BASE_URL_RE}/(?:pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
     ]
     _TESTS = [{
         'url': 'http://academymel.online/3video_1',

yt_dlp/extractor/golem.py

@@ -7,7 +7,7 @@
 
 
 class GolemIE(InfoExtractor):
-    _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
+    _VALID_URL = r'https?://video\.golem\.de/.+?/(?P<id>.+?)/'
     _TEST = {
         'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
         'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',

yt_dlp/extractor/hrfensehen.py

@@ -13,7 +13,7 @@
 
 class HRFernsehenIE(InfoExtractor):
     IE_NAME = 'hrfernsehen'
-    _VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
+    _VALID_URL = r'https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
     _TESTS = [{
         'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
         'md5': '5c4e0ba94677c516a2f65a84110fc536',

yt_dlp/extractor/huya.py

@@ -8,15 +8,19 @@
 from ..utils import (
     ExtractorError,
     int_or_none,
+    parse_duration,
     str_or_none,
     try_get,
     unescapeHTML,
+    unified_strdate,
     update_url_query,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class HuyaLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?P<id>[^/#?&]+)(?:\D|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
     IE_NAME = 'huya:live'
     IE_DESC = 'huya.com'
     TESTS = [{
@@ -24,6 +28,7 @@ class HuyaLiveIE(InfoExtractor):
         'info_dict': {
             'id': '572329',
             'title': str,
+            'ext': 'flv',
             'description': str,
             'is_live': True,
             'view_count': int,
@@ -131,3 +136,76 @@ def encrypt(self, params, stream_info, stream_name):
         fm = base64.b64decode(params['fm']).decode().split('_', 1)[0]
         ss = hashlib.md5('|'.join([params['seqid'], params['ctype'], params['t']]))
         return fm, ss
+
+
+class HuyaVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?huya\.com/video/play/(?P<id>\d+)\.html'
+    IE_NAME = 'huya:video'
+    IE_DESC = '虎牙视频'
+
+    _TESTS = [{
+        'url': 'https://www.huya.com/video/play/1002412640.html',
+        'info_dict': {
+            'id': '1002412640',
+            'ext': 'mp4',
+            'title': '8月3日',
+            'thumbnail': r're:https?://.*\.jpg',
+            'duration': 14,
+            'uploader': '虎牙-ATS欧卡车队青木',
+            'uploader_id': '1564376151',
+            'upload_date': '20240803',
+            'view_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    },
+        {
+        'url': 'https://www.huya.com/video/play/556054543.html',
+        'info_dict': {
+            'id': '556054543',
+            'ext': 'mp4',
+            'title': '我不挑事 也不怕事',
+            'thumbnail': r're:https?://.*\.jpg',
+            'duration': 1864,
+            'uploader': '卡尔',
+            'uploader_id': '367138632',
+            'upload_date': '20210811',
+            'view_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url: str):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://liveapi.huya.com/moment/getMomentContent', video_id,
+            query={'videoId': video_id})['data']['moment']['videoInfo']
+
+        formats = []
+        for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))):
+            formats.append({
+                'url': definition['url'],
+                **traverse_obj(definition, {
+                    'format_id': ('defName', {str}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                    'filesize': ('size', {int_or_none}),
+                }),
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            **traverse_obj(video_data, {
+                'title': ('videoTitle', {str}),
+                'thumbnail': ('videoCover', {url_or_none}),
+                'duration': ('videoDuration', {parse_duration}),
+                'uploader': ('nickName', {str}),
+                'uploader_id': ('uid', {str_or_none}),
+                'upload_date': ('videoUploadTime', {unified_strdate}),
+                'view_count': ('videoPlayNum', {int_or_none}),
+                'comment_count': ('videoCommentNum', {int_or_none}),
+                'like_count': ('favorCount', {int_or_none}),
+            }),
+        }

yt_dlp/extractor/instagram.py

@@ -48,7 +48,6 @@ class InstagramBaseIE(InfoExtractor):
         'X-IG-WWW-Claim': '0',
         'Origin': 'https://www.instagram.com',
         'Accept': '*/*',
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36',
     }
 
     def _perform_login(self, username, password):
@@ -435,10 +434,10 @@ def _real_extract(self, url):
                 'X-Requested-With': 'XMLHttpRequest',
                 'Referer': url,
             }, query={
-                'query_hash': '9f8827793ef34641b2fb195d4d41151c',
+                'doc_id': '8845758582119845',
                 'variables': json.dumps(variables, separators=(',', ':')),
             })
-        media.update(traverse_obj(general_info, ('data', 'shortcode_media')) or {})
+        media.update(traverse_obj(general_info, ('data', 'xdt_shortcode_media')) or {})
 
         if not general_info:
             self.report_warning('General metadata extraction failed (some metadata might be missing).', video_id)

yt_dlp/extractor/iprima.py

@@ -25,9 +25,29 @@ class IPrimaIE(InfoExtractor):
             'id': 'p51388',
             'ext': 'mp4',
             'title': 'Partička (92)',
-            'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
+            'description': 'md5:57943f6a50d6188288c3a579d2fd5f01',
-            'upload_date': '20201103',
+            'episode': 'Partička (92)',
-            'timestamp': 1604437480,
+            'season': 'Partička',
+            'series': 'Prima Partička',
+            'episode_number': 92,
+            'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-ef6cf9de-c980-4443-92e4-17fe8bccd45c-16x9.jpeg',
+        },
+        'params': {
+            'skip_download': True,  # m3u8 download
+        },
+    }, {
+        'url': 'https://zoom.iprima.cz/porady/krasy-kanarskych-ostrovu/tenerife-v-risi-ohne',
+        'info_dict': {
+            'id': 'p1412199',
+            'ext': 'mp4',
+            'episode_number': 3,
+            'episode': 'Tenerife: V říši ohně',
+            'description': 'md5:4b4a05c574b5eaef130e68d4811c3f2c',
+            'duration': 3111.0,
+            'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-f66dd7fb-c1a0-47d1-b3bc-7db328d566c5-16x9-1711636518.jpg/t_16x9_medium_1366_768',
+            'title': 'Tenerife: V říši ohně',
+            'timestamp': 1711825800,
+            'upload_date': '20240330',
         },
         'params': {
             'skip_download': True,  # m3u8 download
@@ -131,6 +151,7 @@ def _real_extract(self, url):
         video_id = self._search_regex((
             r'productId\s*=\s*([\'"])(?P<id>p\d+)\1',
             r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1',
+            r'let\s+videos\s*=\s*([\'"])(?P<id>p\d+)\1',
         ), webpage, 'real id', group='id', default=None)
 
         if not video_id:
@@ -176,7 +197,7 @@ def _real_extract(self, url):
         final_result = self._search_json_ld(webpage, video_id, default={})
         final_result.update({
             'id': video_id,
-            'title': title,
+            'title': final_result.get('title') or title,
             'thumbnail': self._html_search_meta(
                 ['thumbnail', 'og:image', 'twitter:image'],
                 webpage, 'thumbnail', default=None),

yt_dlp/extractor/japandiet.py

@@ -194,11 +194,14 @@ def _real_extract(self, url):
 
 
 class SangiinInstructionIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
+    _VALID_URL = r'https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
     IE_DESC = False  # this shouldn't be listed as a supported site
 
     def _real_extract(self, url):
-        raise ExtractorError('Copy the link from the botton below the video description or player, and use the link to download. If there are no button in the frame, get the URL of the frame showing the video.', expected=True)
+        raise ExtractorError(
+            'Copy the link from the button below the video description/player '
+            'and use that link to download. If there is no button in the frame, '
+            'get the URL of the frame showing the video.', expected=True)
 
 
 class SangiinIE(InfoExtractor):

yt_dlp/extractor/jiosaavn.py

@@ -158,7 +158,7 @@ def _real_extract(self, url):
 
 class JioSaavnPlaylistIE(JioSaavnBaseIE):
     IE_NAME = 'jiosaavn:playlist'
-    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/s/playlist/(?:[^/?#]+/){2}(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
         'info_dict': {
@@ -173,6 +173,13 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
             'title': 'Mood Hindi',
         },
         'playlist_mincount': 801,
+    }, {
+        'url': 'https://www.jiosaavn.com/featured/taaza-tunes/Me5RridRfDk_',
+        'info_dict': {
+            'id': 'Me5RridRfDk_',
+            'title': 'Taaza Tunes',
+        },
+        'playlist_mincount': 301,
     }]
     _PAGE_SIZE = 50
 

yt_dlp/extractor/kaltura.py

@@ -22,7 +22,7 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id>\w+):(?P<id>\w+)(?::(?P<player_type>\w+))?|
                     https?://
-                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
+                        (?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
                         (?:
                             (?:
                                 # flash player

yt_dlp/extractor/khanacademy.py

@@ -15,7 +15,7 @@
 class KhanAcademyBaseIE(InfoExtractor):
     _VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P<id>(?:[^/]+/){%s}%s[^?#/&]+)'
 
-    _PUBLISHED_CONTENT_VERSION = '171419ab20465d931b356f22d20527f13969bb70'
+    _PUBLISHED_CONTENT_VERSION = 'dc34750f0572c80f5effe7134082fe351143c1e4'
 
     def _parse_video(self, video):
         return {
@@ -39,7 +39,7 @@ def _real_extract(self, url):
             query={
                 'fastly_cacheable': 'persist_until_publish',
                 'pcv': self._PUBLISHED_CONTENT_VERSION,
-                'hash': '1242644265',
+                'hash': '3712657851',
                 'variables': json.dumps({
                     'path': display_id,
                     'countryCode': 'US',

yt_dlp/extractor/kick.py

@@ -1,9 +1,14 @@
+import functools
+
 from .common import InfoExtractor
 from ..networking import HEADRequest
 from ..utils import (
     UserNotLive,
+    determine_ext,
     float_or_none,
+    int_or_none,
     merge_dicts,
+    parse_iso8601,
     str_or_none,
     traverse_obj,
     unified_timestamp,
@@ -25,104 +30,212 @@ def _real_initialize(self):
 
     def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
         return self._download_json(
-            f'https://kick.com/api/v1/{path}', display_id, note=note,
+            f'https://kick.com/api/{path}', display_id, note=note,
             headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
 
 
 class KickIE(KickBaseIE):
+    IE_NAME = 'kick:live'
     _VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
     _TESTS = [{
-        'url': 'https://kick.com/yuppy',
+        'url': 'https://kick.com/buddha',
         'info_dict': {
-            'id': '6cde1-kickrp-joe-flemmingskick-info-heremust-knowmust-see21',
+            'id': '92722911-nopixel-40',
             'ext': 'mp4',
             'title': str,
             'description': str,
-            'channel': 'yuppy',
-            'channel_id': '33538',
-            'uploader': 'Yuppy',
-            'uploader_id': '33793',
-            'upload_date': str,
-            'live_status': 'is_live',
             'timestamp': int,
-            'thumbnail': r're:^https?://.*\.jpg',
+            'thumbnail': r're:https?://.+\.jpg',
             'categories': list,
+            'upload_date': str,
+            'channel': 'buddha',
+            'channel_id': '32807',
+            'uploader': 'Buddha',
+            'uploader_id': '33057',
+            'live_status': 'is_live',
+            'concurrent_view_count': int,
+            'release_timestamp': int,
+            'age_limit': 18,
+            'release_date': str,
         },
-        'skip': 'livestream',
+        'params': {'skip_download': 'livestream'},
+        # 'skip': 'livestream',
     }, {
-        'url': 'https://kick.com/kmack710',
+        'url': 'https://kick.com/xqc',
         'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if (KickVODIE.suitable(url) or KickClipIE.suitable(url)) else super().suitable(url)
+
     def _real_extract(self, url):
         channel = self._match_id(url)
-        response = self._call_api(f'channels/{channel}', channel)
+        response = self._call_api(f'v2/channels/{channel}', channel)
         if not traverse_obj(response, 'livestream', expected_type=dict):
             raise UserNotLive(video_id=channel)
 
         return {
-            'id': str(traverse_obj(
-                response, ('livestream', ('slug', 'id')), get_all=False, default=channel)),
-            'formats': self._extract_m3u8_formats(
-                response['playback_url'], channel, 'mp4', live=True),
-            'title': traverse_obj(
-                response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
-            'description': traverse_obj(response, ('user', 'bio')),
             'channel': channel,
-            'channel_id': str_or_none(traverse_obj(response, 'id', ('livestream', 'channel_id'))),
-            'uploader': traverse_obj(response, 'name', ('user', 'username')),
-            'uploader_id': str_or_none(traverse_obj(response, 'user_id', ('user', 'id'))),
             'is_live': True,
-            'timestamp': unified_timestamp(traverse_obj(response, ('livestream', 'created_at'))),
+            'formats': self._extract_m3u8_formats(response['playback_url'], channel, 'mp4', live=True),
-            'thumbnail': traverse_obj(
+            **traverse_obj(response, {
-                response, ('livestream', 'thumbnail', 'url'), expected_type=url_or_none),
+                'id': ('livestream', 'slug', {str}),
-            'categories': traverse_obj(response, ('recent_categories', ..., 'name')),
+                'title': ('livestream', 'session_title', {str}),
+                'description': ('user', 'bio', {str}),
+                'channel_id': (('id', ('livestream', 'channel_id')), {int}, {str_or_none}, any),
+                'uploader': (('name', ('user', 'username')), {str}, any),
+                'uploader_id': (('user_id', ('user', 'id')), {int}, {str_or_none}, any),
+                'timestamp': ('livestream', 'created_at', {unified_timestamp}),
+                'release_timestamp': ('livestream', 'start_time', {unified_timestamp}),
+                'thumbnail': ('livestream', 'thumbnail', 'url', {url_or_none}),
+                'categories': ('recent_categories', ..., 'name', {str}),
+                'concurrent_view_count': ('livestream', 'viewer_count', {int_or_none}),
+                'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
         }
 
 
 class KickVODIE(KickBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+    IE_NAME = 'kick:vod'
+    _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/videos/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
     _TESTS = [{
-        'url': 'https://kick.com/video/58bac65b-e641-4476-a7ba-3707a35e60e3',
+        'url': 'https://kick.com/xqc/videos/8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
         'md5': '3870f94153e40e7121a6e46c068b70cb',
         'info_dict': {
-            'id': '58bac65b-e641-4476-a7ba-3707a35e60e3',
+            'id': '8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
             'ext': 'mp4',
-            'title': '🤠REBIRTH IS BACK!!!!🤠!stake CODE JAREDFPS 🤠',
+            'title': '18+ #ad 🛑LIVE🛑CLICK🛑DRAMA🛑NEWS🛑STUFF🛑REACT🛑GET IN HHERE🛑BOP BOP🛑WEEEE WOOOO🛑',
-            'description': 'md5:02b0c46f9b4197fb545ab09dddb85b1d',
+            'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
-            'channel': 'jaredfps',
+            'channel': 'xqc',
-            'channel_id': '26608',
+            'channel_id': '668',
-            'uploader': 'JaredFPS',
+            'uploader': 'xQc',
-            'uploader_id': '26799',
+            'uploader_id': '676',
-            'upload_date': '20240402',
+            'upload_date': '20240909',
-            'timestamp': 1712097108,
+            'timestamp': 1725919141,
-            'duration': 33859.0,
+            'duration': 10155.0,
             'thumbnail': r're:^https?://.*\.jpg',
-            'categories': ['Call of Duty: Warzone'],
+            'view_count': int,
+            'categories': ['Just Chatting'],
+            'age_limit': 0,
         },
-        'params': {
+        'params': {'skip_download': 'm3u8'},
-            'skip_download': 'm3u8',
-        },
-        'expected_warnings': [r'impersonation'],
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        response = self._call_api(f'video/{video_id}', video_id)
+        response = self._call_api(f'v1/video/{video_id}', video_id)
 
         return {
             'id': video_id,
             'formats': self._extract_m3u8_formats(response['source'], video_id, 'mp4'),
-            'title': traverse_obj(
+            **traverse_obj(response, {
-                response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
+                'title': ('livestream', ('session_title', 'slug'), {str}, any),
-            'description': traverse_obj(response, ('livestream', 'channel', 'user', 'bio')),
+                'description': ('livestream', 'channel', 'user', 'bio', {str}),
-            'channel': traverse_obj(response, ('livestream', 'channel', 'slug')),
+                'channel': ('livestream', 'channel', 'slug', {str}),
-            'channel_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'id'))),
+                'channel_id': ('livestream', 'channel', 'id', {int}, {str_or_none}),
-            'uploader': traverse_obj(response, ('livestream', 'channel', 'user', 'username')),
+                'uploader': ('livestream', 'channel', 'user', 'username', {str}),
-            'uploader_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'user_id'))),
+                'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}),
-            'timestamp': unified_timestamp(response.get('created_at')),
+                'timestamp': ('created_at', {parse_iso8601}),
-            'duration': float_or_none(traverse_obj(response, ('livestream', 'duration')), scale=1000),
+                'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}),
-            'thumbnail': traverse_obj(
+                'thumbnail': ('livestream', 'thumbnail', {url_or_none}),
-                response, ('livestream', 'thumbnail'), expected_type=url_or_none),
+                'categories': ('livestream', 'categories', ..., 'name', {str}),
-            'categories': traverse_obj(response, ('livestream', 'categories', ..., 'name')),
+                'view_count': ('views', {int_or_none}),
+                'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
+        }
+
+
+class KickClipIE(KickBaseIE):
+    IE_NAME = 'kick:clips'
+    _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+(?:/clips/|/?\?(?:[^#]+&)?clip=)(?P<id>clip_[\w-]+)'
+    _TESTS = [{
+        'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
+        'info_dict': {
+            'id': 'clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
+            'ext': 'mp4',
+            'title': 'Maddy detains Abd D:',
+            'channel': 'mxddy',
+            'channel_id': '133789',
+            'uploader': 'AbdCreates',
+            'uploader_id': '3309077',
+            'thumbnail': r're:^https?://.*\.jpeg',
+            'duration': 35,
+            'timestamp': 1682481453,
+            'upload_date': '20230426',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['VALORANT'],
+            'age_limit': 18,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://kick.com/destiny?clip=clip_01H9SKET879NE7N9RJRRDS98J3',
+        'info_dict': {
+            'id': 'clip_01H9SKET879NE7N9RJRRDS98J3',
+            'title': 'W jews',
+            'ext': 'mp4',
+            'channel': 'destiny',
+            'channel_id': '1772249',
+            'uploader': 'punished_furry',
+            'uploader_id': '2027722',
+            'duration': 49.0,
+            'upload_date': '20230908',
+            'timestamp': 1694150180,
+            'thumbnail': 'https://clips.kick.com/clips/j3/clip_01H9SKET879NE7N9RJRRDS98J3/thumbnail.png',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['Just Chatting'],
+            'age_limit': 0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://kick.com/spreen/clips/clip_01J8RGZRKHXHXXKJEHGRM932A5',
+        'info_dict': {
+            'id': 'clip_01J8RGZRKHXHXXKJEHGRM932A5',
+            'ext': 'mp4',
+            'title': 'KLJASLDJKLJKASDLJKDAS',
+            'channel': 'spreen',
+            'channel_id': '5312671',
+            'uploader': 'AnormalBarraBaja',
+            'uploader_id': '26518262',
+            'duration': 43.0,
+            'upload_date': '20240927',
+            'timestamp': 1727399987,
+            'thumbnail': 'https://clips.kick.com/clips/f2/clip_01J8RGZRKHXHXXKJEHGRM932A5/thumbnail.webp',
+            'view_count': int,
+            'like_count': int,
+            'categories': ['Minecraft'],
+            'age_limit': 0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        clip_id = self._match_id(url)
+        clip = self._call_api(f'v2/clips/{clip_id}/play', clip_id)['clip']
+        clip_url = clip['clip_url']
+
+        if determine_ext(clip_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(clip_url, clip_id, 'mp4')
+        else:
+            formats = [{'url': clip_url}]
+
+        return {
+            'id': clip_id,
+            'formats': formats,
+            **traverse_obj(clip, {
+                'title': ('title', {str}),
+                'channel': ('channel', 'slug', {str}),
+                'channel_id': ('channel', 'id', {int}, {str_or_none}),
+                'uploader': ('creator', 'username', {str}),
+                'uploader_id': ('creator', 'id', {int}, {str_or_none}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'duration': ('duration', {float_or_none}),
+                'categories': ('category', 'name', {str}, all),
+                'timestamp': ('created_at', {parse_iso8601}),
+                'view_count': ('views', {int_or_none}),
+                'like_count': ('likes', {int_or_none}),
+                'age_limit': ('is_mature', {bool}, {lambda x: 18 if x else 0}),
+            }),
         }

yt_dlp/extractor/kika.py

@@ -0,0 +1,126 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class KikaIE(InfoExtractor):
+    IE_DESC = 'KiKA.de'
+    _VALID_URL = r'https?://(?:www\.)?kika\.de/[\w/-]+/videos/(?P<id>[a-z-]+\d+)'
+    _GEO_COUNTRIES = ['DE']
+
+    _TESTS = [{
+        'url': 'https://www.kika.de/logo/videos/logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
+        'md5': 'fbfc8da483719ef06f396e5e5b938c69',
+        'info_dict': {
+            'id': 'logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
+            'ext': 'mp4',
+            'upload_date': '20240831',
+            'timestamp': 1725126600,
+            'season_number': 2024,
+            'modified_date': '20240831',
+            'episode': 'Episode 476',
+            'episode_number': 476,
+            'season': 'Season 2024',
+            'duration': 634,
+            'title': 'logo! vom Samstag, 31. August 2024',
+            'modified_timestamp': 1725129983,
+        },
+    }, {
+        'url': 'https://www.kika.de/kaltstart/videos/video92498',
+        'md5': '710ece827e5055094afeb474beacb7aa',
+        'info_dict': {
+            'id': 'video92498',
+            'ext': 'mp4',
+            'title': '7. Wo ist Leo?',
+            'description': 'md5:fb48396a5b75068bcac1df74f1524920',
+            'duration': 436,
+            'timestamp': 1702926876,
+            'upload_date': '20231218',
+            'episode_number': 7,
+            'modified_date': '20240319',
+            'modified_timestamp': 1710880610,
+            'episode': 'Episode 7',
+            'season_number': 1,
+            'season': 'Season 1',
+        },
+    }, {
+        'url': 'https://www.kika.de/bernd-das-brot/astrobrot/videos/video90088',
+        'md5': 'ffd1b700d7de0a6616a1d08544c77294',
+        'info_dict': {
+            'id': 'video90088',
+            'ext': 'mp4',
+            'upload_date': '20221102',
+            'timestamp': 1667390580,
+            'duration': 197,
+            'modified_timestamp': 1711093771,
+            'episode_number': 8,
+            'title': 'Es ist nicht leicht, ein Astrobrot zu sein',
+            'modified_date': '20240322',
+            'description': 'md5:d3641deaf1b5515a160788b2be4159a9',
+            'season_number': 1,
+            'episode': 'Episode 8',
+            'season': 'Season 1',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        doc = self._download_json(f'https://www.kika.de/_next-api/proxy/v1/videos/{video_id}', video_id)
+        video_assets = self._download_json(doc['assets']['url'], video_id)
+
+        subtitles = {}
+        if ttml_resource := url_or_none(video_assets.get('videoSubtitle')):
+            subtitles['de'] = [{
+                'url': ttml_resource,
+                'ext': 'ttml',
+            }]
+        if webvtt_resource := url_or_none(video_assets.get('webvttUrl')):
+            subtitles.setdefault('de', []).append({
+                'url': webvtt_resource,
+                'ext': 'vtt',
+            })
+
+        return {
+            'id': video_id,
+            'formats': list(self._extract_formats(video_assets, video_id)),
+            'subtitles': subtitles,
+            **traverse_obj(doc, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('date', {parse_iso8601}),
+                'modified_timestamp': ('modificationDate', {parse_iso8601}),
+                'duration': ((
+                    ('durationInSeconds', {int_or_none}),
+                    ('duration', {parse_duration})), any),
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'season_number': ('season', {int_or_none}),
+            }),
+        }
+
+    def _extract_formats(self, media_info, video_id):
+        for media in traverse_obj(media_info, ('assets', lambda _, v: url_or_none(v['url']))):
+            stream_url = media['url']
+            ext = determine_ext(stream_url)
+            if ext == 'm3u8':
+                yield from self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            else:
+                yield {
+                    'url': stream_url,
+                    'format_id': ext,
+                    **traverse_obj(media, {
+                        'width': ('frameWidth', {int_or_none}),
+                        'height': ('frameHeight', {int_or_none}),
+                        # NB: filesize is 0 if unknown, bitrate is -1 if unknown
+                        'filesize': ('fileSize', {int_or_none}, {lambda x: x or None}),
+                        'abr': ('bitrateAudio', {int_or_none}, {lambda x: None if x == -1 else x}),
+                        'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
+                    }),
+                }

yt_dlp/extractor/learningonscreen.py

@@ -0,0 +1,78 @@
+import functools
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_id,
+    join_nonempty,
+    parse_duration,
+    unified_timestamp,
+)
+from ..utils.traversal import traverse_obj
+
+
+class LearningOnScreenIE(InfoExtractor):
+    _VALID_URL = r'https?://learningonscreen\.ac\.uk/ondemand/index\.php/prog/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://learningonscreen.ac.uk/ondemand/index.php/prog/005D81B2?bcast=22757013',
+        'info_dict': {
+            'id': '005D81B2',
+            'ext': 'mp4',
+            'title': 'Planet Earth',
+            'duration': 3600.0,
+            'timestamp': 1164567600.0,
+            'upload_date': '20061126',
+            'thumbnail': 'https://stream.learningonscreen.ac.uk/trilt-cover-images/005D81B2-Planet-Earth-2006-11-26T190000Z-BBC4.jpg',
+        },
+    }]
+
+    def _real_initialize(self):
+        if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'):
+            self.raise_login_required(
+                'Use --cookies for authentication. See '
+                ' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp  '
+                'for how to manually pass cookies', method=None)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        details = traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'programme-details')}, {
+                'title': ({functools.partial(re.search, r'<h2>([^<]+)</h2>')}, 1, {clean_html}),
+                'timestamp': (
+                    {functools.partial(get_element_by_class, 'broadcast-date')},
+                    {functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}),
+                'duration': (
+                    {functools.partial(get_element_by_class, 'prog-running-time')},
+                    {clean_html}, {parse_duration}),
+            }))
+
+        title = details.pop('title', None) or traverse_obj(webpage, (
+            {functools.partial(get_element_html_by_id, 'add-to-existing-playlist')},
+            {extract_attributes}, 'data-record-title', {clean_html}))
+
+        entries = self._parse_html5_media_entries(
+            'https://stream.learningonscreen.ac.uk', webpage, video_id, m3u8_id='hls', mpd_id='dash',
+            _headers={'Origin': 'https://learningonscreen.ac.uk', 'Referer': 'https://learningonscreen.ac.uk/'})
+        if not entries:
+            raise ExtractorError('No video found')
+
+        if len(entries) > 1:
+            duration = details.pop('duration', None)
+            for idx, entry in enumerate(entries, start=1):
+                entry.update(details)
+                entry['id'] = join_nonempty(video_id, idx)
+                entry['title'] = join_nonempty(title, idx)
+            return self.playlist_result(entries, video_id, title, duration=duration)
+
+        return {
+            **entries[0],
+            **details,
+            'id': video_id,
+            'title': title,
+        }

yt_dlp/extractor/lnk.py

@@ -1,86 +1,11 @@
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     format_field,
     int_or_none,
-    parse_iso8601,
     unified_strdate,
 )
 
 
-class LnkGoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?'
-    _TESTS = [{
-        'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
-        'info_dict': {
-            'id': '10809',
-            'ext': 'mp4',
-            'title': "Put'ka: Trys Klausimai",
-            'upload_date': '20161216',
-            'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.',
-            'age_limit': 18,
-            'duration': 117,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1481904000,
-        },
-        'params': {
-            'skip_download': True,  # HLS download
-        },
-    }, {
-        'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
-        'info_dict': {
-            'id': '10467',
-            'ext': 'mp4',
-            'title': 'Nėrdas: Kompiuterio Valymas',
-            'upload_date': '20150113',
-            'description': 'md5:7352d113a242a808676ff17e69db6a69',
-            'age_limit': 18,
-            'duration': 346,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1421164800,
-        },
-        'params': {
-            'skip_download': True,  # HLS download
-        },
-    }, {
-        'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413',
-        'only_matching': True,
-    }]
-    _AGE_LIMITS = {
-        'N-7': 7,
-        'N-14': 14,
-        'S': 18,
-    }
-    _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s'
-
-    def _real_extract(self, url):
-        display_id, video_id = self._match_valid_url(url).groups()
-
-        video_info = self._download_json(
-            'https://lnk.lt/api/main/video-page/{}/{}/false'.format(display_id, video_id or '0'),
-            display_id)['videoConfig']['videoInfo']
-
-        video_id = str(video_info['id'])
-        title = video_info['title']
-        prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4'
-        formats = self._extract_m3u8_formats(
-            self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''),
-            video_id, 'mp4', 'm3u8_native')
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'formats': formats,
-            'thumbnail': format_field(video_info, 'posterImage', 'https://lnk.lt/all-images/%s'),
-            'duration': int_or_none(video_info.get('duration')),
-            'description': clean_html(video_info.get('htmlDescription')),
-            'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0),
-            'timestamp': parse_iso8601(video_info.get('airDate')),
-            'view_count': int_or_none(video_info.get('viewsCount')),
-        }
-
-
 class LnkIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?lnk\.lt/[^/]+/(?P<id>\d+)'
 

yt_dlp/extractor/loom.py

@@ -92,9 +92,9 @@ class LoomIE(InfoExtractor):
         },
         'params': {'videopassword': 'seniorinfants2'},
     }, {
-        # embed, transcoded-url endpoint sends empty JSON response
+        # embed, transcoded-url endpoint sends empty JSON response, split video and audio HLS formats
         'url': 'https://www.loom.com/embed/ddcf1c1ad21f451ea7468b1e33917e4e',
-        'md5': '8488817242a0db1cb2ad0ea522553cf6',
+        'md5': 'b321d261656848c184a94e3b93eae28d',
         'info_dict': {
             'id': 'ddcf1c1ad21f451ea7468b1e33917e4e',
             'ext': 'mp4',
@@ -104,6 +104,7 @@ class LoomIE(InfoExtractor):
             'timestamp': 1657216459,
             'duration': 181,
         },
+        'params': {'format': 'bestvideo'},  # Test video-only fixup
         'expected_warnings': ['Failed to parse JSON'],
     }]
     _WEBPAGE_TESTS = [{
@@ -293,7 +294,11 @@ def get_formats(format_url, format_id, quality):
                 format_url = format_url.replace('-split.m3u8', '.m3u8')
                 m3u8_formats = self._extract_m3u8_formats(
                     format_url, video_id, 'mp4', m3u8_id=f'hls-{format_id}', fatal=False, quality=quality)
+                # Sometimes only split video/audio formats are available, need to fixup video-only formats
+                is_not_premerged = 'none' in traverse_obj(m3u8_formats, (..., 'vcodec'))
                 for fmt in m3u8_formats:
+                    if is_not_premerged and fmt.get('vcodec') != 'none':
+                        fmt['acodec'] = 'none'
                     yield {
                         **fmt,
                         'url': update_url(fmt['url'], query=query),

yt_dlp/extractor/mailru.py

@@ -126,7 +126,7 @@ def _real_extract(self, url):
         video_data = None
 
         # fix meta_url if missing the host address
-        if re.match(r'^\/\+\/', meta_url):
+        if re.match(r'\/\+\/', meta_url):
             meta_url = urljoin('https://my.mail.ru', meta_url)
 
         if meta_url:

yt_dlp/extractor/mdr.py

@@ -13,8 +13,8 @@
 
 
 class MDRIE(InfoExtractor):
-    IE_DESC = 'MDR.DE and KiKA'
+    IE_DESC = 'MDR.DE'
-    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?mdr\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
 
     _GEO_COUNTRIES = ['DE']
 
@@ -34,30 +34,6 @@ class MDRIE(InfoExtractor):
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },
         'skip': '404 not found',
-    }, {
-        'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
-        'md5': '4930515e36b06c111213e80d1e4aad0e',
-        'info_dict': {
-            'id': '19636',
-            'ext': 'mp4',
-            'title': 'Baumhaus vom 30. Oktober 2015',
-            'duration': 134,
-            'uploader': 'KIKA',
-        },
-        'skip': '404 not found',
-    }, {
-        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
-        'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
-        'info_dict': {
-            'id': '8182',
-            'ext': 'mp4',
-            'title': 'Beutolomäus und der geheime Weihnachtswunsch',
-            'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
-            'timestamp': 1482541200,
-            'upload_date': '20161224',
-            'duration': 4628,
-            'uploader': 'KIKA',
-        },
     }, {
         # audio with alternative playerURL pattern
         'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
@@ -68,28 +44,7 @@ class MDRIE(InfoExtractor):
             'duration': 3239,
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },
-    }, {
+        'skip': '404 not found',
-        # empty bitrateVideo and bitrateAudio
-        'url': 'https://www.kika.de/filme/sendung128372_zc-572e3f45_zs-1d9fb70e.html',
-        'info_dict': {
-            'id': '128372',
-            'ext': 'mp4',
-            'title': 'Der kleine Wichtel kehrt zurück',
-            'description': 'md5:f77fafdff90f7aa1e9dca14f662c052a',
-            'duration': 4876,
-            'timestamp': 1607823300,
-            'upload_date': '20201213',
-            'uploader': 'ZDF',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
-        'only_matching': True,
     }, {
         'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
         'only_matching': True,

yt_dlp/extractor/mediaklikk.py

@@ -16,6 +16,15 @@ class MediaKlikkIE(InfoExtractor):
                         (?P<id>[^/#?_]+)'''
 
     _TESTS = [{
+        'url': 'https://mediaklikk.hu/filmajanlo/cikk/az-ajto/',
+        'info_dict': {
+            'id': '668177',
+            'title': 'Az ajtó',
+            'display_id': 'az-ajto',
+            'ext': 'mp4',
+            'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2016/01/vlcsnap-2023-07-31-14h18m52s111.jpg',
+        },
+    }, {
         # (old) mediaklikk. date in html.
         'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/',
         'info_dict': {
@@ -37,6 +46,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230903',
             'thumbnail': 'https://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # (old) m4sport
         'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/',
@@ -59,6 +69,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230908',
             'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-08-22h43m18s691.jpg',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # m4sport with *video/ url and no date
         'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/',
@@ -69,6 +80,7 @@ class MediaKlikkIE(InfoExtractor):
             'ext': 'mp4',
             'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png',
         },
+        'skip': 'Webpage redirects to 404 page',
     }, {
         # (old) hirado
         'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/',
@@ -90,6 +102,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230911',
             'thumbnail': 'https://hirado.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-11-09h16m09s882.jpg',
         },
+        'skip': 'Webpage redirects to video list page',
     }, {
         # (old) petofilive
         'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/',
@@ -112,6 +125,7 @@ class MediaKlikkIE(InfoExtractor):
             'upload_date': '20230909',
             'thumbnail': 'https://petofilive.hu/wp-content/uploads/sites/4/2023/09/Clipboard11-2.jpg',
         },
+        'skip': 'Webpage redirects to video list page',
     }]
 
     def _real_extract(self, url):
@@ -133,7 +147,9 @@ def _real_extract(self, url):
                 r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
 
         player_data['video'] = player_data.pop('token')
-        player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data)
+        player_page = self._download_webpage(
+            'https://player.mediaklikk.hu/playernew/player.php', video_id,
+            query=player_data, headers={'Referer': url})
         player_json = self._search_json(
             r'\bpl\.setup\s*\(', player_page, 'player json', video_id, end_pattern=r'\);')
         playlist_url = traverse_obj(
@@ -141,14 +157,14 @@ def _real_extract(self, url):
         if not playlist_url:
             raise ExtractorError('Unable to extract playlist url')
 
-        formats = self._extract_wowza_formats(
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(playlist_url, video_id)
-            playlist_url, video_id, skip_protocols=['f4m', 'smil', 'dash'])
 
         return {
             'id': video_id,
             'title': title,
             'display_id': display_id,
             'formats': formats,
+            'subtitles': subtitles,
             'upload_date': upload_date,
             'thumbnail': player_data.get('bgImage') or self._og_search_thumbnail(webpage),
         }

yt_dlp/extractor/mgtv.py

@@ -16,7 +16,7 @@
 
 
 class MGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/[bv]/(?:[^/]+/)*(?P<id>\d+)\.html'
     IE_DESC = '芒果TV'
     IE_NAME = 'MangoTV'
 

yt_dlp/extractor/mit.py

@@ -65,7 +65,7 @@ def _real_extract(self, url):
 
 class OCWMITIE(InfoExtractor):
     IE_NAME = 'ocw.mit.edu'
-    _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+    _VALID_URL = r'https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
     _BASE_URL = 'http://ocw.mit.edu/'
 
     _TESTS = [

yt_dlp/extractor/mlb.py

@@ -1,16 +1,21 @@
+import json
 import re
-import urllib.parse
+import time
 import uuid
 
 from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
 from ..utils import (
+    ExtractorError,
     determine_ext,
     int_or_none,
     join_nonempty,
+    jwt_decode_hs256,
     parse_duration,
     parse_iso8601,
     try_get,
     url_or_none,
+    urlencode_postdata,
 )
 from ..utils.traversal import traverse_obj
 
@@ -276,81 +281,225 @@ def _download_video_data(self, display_id):
 class MLBTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})'
     _NETRC_MACHINE = 'mlb'
-
     _TESTS = [{
         'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638',
         'info_dict': {
             'id': '661581',
             'ext': 'mp4',
             'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies',
+            'release_date': '20220702',
+            'release_timestamp': 1656792300,
         },
-        'params': {
+        'params': {'skip_download': 'm3u8'},
-            'skip_download': True,
+    }, {
+        # makeup game: has multiple dates, need to avoid games with 'rescheduleDate'
+        'url': 'https://www.mlb.com/tv/g747039/vd22541c4-5a29-45f7-822b-635ec041cf5e',
+        'info_dict': {
+            'id': '747039',
+            'ext': 'mp4',
+            'title': '2024-07-29 - Toronto Blue Jays @ Baltimore Orioles',
+            'release_date': '20240729',
+            'release_timestamp': 1722280200,
         },
+        'params': {'skip_download': 'm3u8'},
     }]
+    _GRAPHQL_INIT_QUERY = '''\
+mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) {
+    initSession(device: $device, clientType: $clientType, experience: $experience) {
+        deviceId
+        sessionId
+        entitlements {
+            code
+        }
+        location {
+            countryCode
+            regionName
+            zipCode
+            latitude
+            longitude
+        }
+        clientExperience
+        features
+    }
+  }'''
+    _GRAPHQL_PLAYBACK_QUERY = '''\
+mutation initPlaybackSession(
+        $adCapabilities: [AdExperienceType]
+        $mediaId: String!
+        $deviceId: String!
+        $sessionId: String!
+        $quality: PlaybackQuality
+    ) {
+        initPlaybackSession(
+            adCapabilities: $adCapabilities
+            mediaId: $mediaId
+            deviceId: $deviceId
+            sessionId: $sessionId
+            quality: $quality
+        ) {
+            playbackSessionId
+            playback {
+                url
+                token
+                expiration
+                cdn
+            }
+        }
+    }'''
+    _APP_VERSION = '7.8.2'
+    _device_id = None
+    _session_id = None
     _access_token = None
+    _token_expiry = 0
+
+    @property
+    def _api_headers(self):
+        if (self._token_expiry - 120) <= time.time():
+            self.write_debug('Access token has expired; re-logging in')
+            self._perform_login(*self._get_login_info())
+        return {'Authorization': f'Bearer {self._access_token}'}
 
     def _real_initialize(self):
         if not self._access_token:
             self.raise_login_required(
                 'All videos are only available to registered users', method='password')
 
+    def _set_device_id(self, username):
+        if not self._device_id:
+            self._device_id = self.cache.load(
+                self._NETRC_MACHINE, 'device_ids', default={}).get(username)
+        if self._device_id:
+            return
+        self._device_id = str(uuid.uuid4())
+        self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id})
+
     def _perform_login(self, username, password):
-        data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356'
+        try:
-        access_token = self._download_json(
+            self._access_token = self._download_json(
-            'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
+                'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
-            headers={
+                'Logging in', 'Unable to log in', headers={
-                'User-Agent': 'okhttp/3.12.1',
+                    'User-Agent': 'okhttp/3.12.1',
-                'Content-Type': 'application/x-www-form-urlencoded',
+                    'Content-Type': 'application/x-www-form-urlencoded',
-            }, data=data.encode())['access_token']
+                }, data=urlencode_postdata({
+                    'grant_type': 'password',
+                    'username': username,
+                    'password': password,
+                    'scope': 'openid offline_access',
+                    'client_id': '0oa3e1nutA1HLzAKG356',
+                }))['access_token']
+        except ExtractorError as error:
+            if isinstance(error.cause, HTTPError) and error.cause.status == 400:
+                raise ExtractorError('Invalid username or password', expected=True)
+            raise
 
-        entitlement = self._download_webpage(
+        self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0
-            f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None,
+        self._set_device_id(username)
-            headers={
-                'User-Agent': 'okhttp/3.12.1',
-                'Authorization': f'Bearer {access_token}',
-            })
 
-        data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv'
+        self._session_id = self._call_api({
-        self._access_token = self._download_json(
+            'operationName': 'initSession',
-            'https://us.edge.bamgrid.com/token', None,
+            'query': self._GRAPHQL_INIT_QUERY,
+            'variables': {
+                'device': {
+                    'appVersion': self._APP_VERSION,
+                    'deviceFamily': 'desktop',
+                    'knownDeviceId': self._device_id,
+                    'languagePreference': 'ENGLISH',
+                    'manufacturer': '',
+                    'model': '',
+                    'os': '',
+                    'osVersion': '',
+                },
+                'clientType': 'WEB',
+            },
+        }, None, 'session ID')['data']['initSession']['sessionId']
+
+    def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True):
+        return self._download_json(
+            'https://media-gateway.mlb.com/graphql', video_id,
+            f'Downloading {description}', f'Unable to download {description}', fatal=fatal,
             headers={
+                **self._api_headers,
                 'Accept': 'application/json',
-                'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk',
+                'Content-Type': 'application/json',
-                'Content-Type': 'application/x-www-form-urlencoded',
+                'x-client-name': 'WEB',
-            }, data=data.encode())['access_token']
+                'x-client-version': self._APP_VERSION,
+            }, data=json.dumps(data, separators=(',', ':')).encode())
+
+    def _extract_formats_and_subtitles(self, broadcast, video_id):
+        feed = traverse_obj(broadcast, ('homeAway', {str.title}))
+        medium = traverse_obj(broadcast, ('type', {str}))
+        language = traverse_obj(broadcast, ('language', {str.lower}))
+        format_id = join_nonempty(feed, medium, language)
+
+        response = self._call_api({
+            'operationName': 'initPlaybackSession',
+            'query': self._GRAPHQL_PLAYBACK_QUERY,
+            'variables': {
+                'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'],
+                'deviceId': self._device_id,
+                'mediaId': broadcast['mediaId'],
+                'quality': 'PLACEHOLDER',
+                'sessionId': self._session_id,
+            },
+        }, video_id, f'{format_id} broadcast JSON', fatal=False)
+
+        playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict}))
+        m3u8_url = traverse_obj(playback, ('url', {url_or_none}))
+        token = traverse_obj(playback, ('token', {str}))
+
+        if not (m3u8_url and token):
+            errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
+            if 'not entitled' in errors:
+                raise ExtractorError(errors, expected=True)
+            elif errors:  # Only warn when 'blacked out' since radio formats are available
+                self.report_warning(f'API returned errors for {format_id}: {errors}')
+            else:
+                self.report_warning(f'No formats available for {format_id} broadcast; skipping')
+            return [], {}
+
+        cdn_headers = {'x-cdn-token': token}
+        fmts, subs = self._extract_m3u8_formats_and_subtitles(
+            m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
+            m3u8_id=format_id, fatal=False, headers=cdn_headers)
+        for fmt in fmts:
+            fmt['http_headers'] = cdn_headers
+            fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
+            fmt.setdefault('language', language)
+            if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':
+                fmt['source_preference'] = 10
+
+        return fmts, subs
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        airings = self._download_json(
+        data = self._download_json(
-            f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D',
+            'https://statsapi.mlb.com/api/v1/schedule', video_id, query={
-            video_id)['data']['Airings']
+                'gamePk': video_id,
+                'hydrate': 'broadcasts(all),statusFlags',
+            })
+        metadata = traverse_obj(data, (
+            'dates', ..., 'games',
+            lambda _, v: str(v['gamePk']) == video_id and not v.get('rescheduleDate'), any))
+
+        broadcasts = traverse_obj(metadata, (
+            'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF'))
 
         formats, subtitles = [], {}
-        for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
+        for broadcast in broadcasts:
-            format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
+            fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id)
-            m3u8_url = traverse_obj(self._download_json(
+            formats.extend(fmts)
-                airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
+            self._merge_subtitles(subs, target=subtitles)
-                note=f'Downloading {format_id} stream info JSON',
-                errnote=f'Failed to download {format_id} stream info, skipping',
-                fatal=False, headers={
-                    'Authorization': self._access_token,
-                    'Accept': 'application/vnd.media-service+json; version=2',
-                }), ('stream', 'complete', {url_or_none}))
-            if not m3u8_url:
-                continue
-            f, s = self._extract_m3u8_formats_and_subtitles(
-                m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
-            formats.extend(f)
-            self._merge_subtitles(s, target=subtitles)
 
         return {
             'id': video_id,
-            'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False),
+            'title': join_nonempty(
-            'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE',
+                traverse_obj(metadata, ('officialDate', {str})),
+                traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})),
+                delim=' - '),
+            'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON',
+            'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})),
             'formats': formats,
             'subtitles': subtitles,
-            'http_headers': {'Authorization': f'Bearer {self._access_token}'},
         }
 
 

yt_dlp/extractor/mojevideo.py

@@ -0,0 +1,121 @@
+from .common import InfoExtractor
+from ..utils import js_to_json, remove_end, update_url_query
+
+
+class MojevideoIE(InfoExtractor):
+    IE_DESC = 'mojevideo.sk'
+    _VALID_URL = r'https?://(?:www\.)?mojevideo\.sk/video/(?P<id>\w+)/(?P<display_id>[\w()]+?)\.html'
+
+    _TESTS = [{
+        'url': 'https://www.mojevideo.sk/video/3d17c/chlapci_dobetonovali_sme_mame_hotovo.html',
+        'md5': '384a4628bd2bbd261c5206cf77c38c17',
+        'info_dict': {
+            'id': '3d17c',
+            'ext': 'mp4',
+            'title': 'Chlapci dobetónovali sme, máme hotovo!',
+            'display_id': 'chlapci_dobetonovali_sme_mame_hotovo',
+            'description': 'md5:a0822126044050d304a9ef58c92ddb34',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/250236.jpg',
+            'duration': 21.0,
+            'upload_date': '20230919',
+            'timestamp': 1695129706,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/14677/den_blbec.html',
+        'md5': '517c3e111c53a67d10b429c1f344ba2f',
+        'info_dict': {
+            'id': '14677',
+            'ext': 'mp4',
+            'title': 'Deň blbec?',
+            'display_id': 'den_blbec',
+            'description': 'I maličkosť vám môže zmeniť celý deň. Nikdy nezahadzujte žuvačky na zem!',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/83575.jpg',
+            'duration': 100.0,
+            'upload_date': '20120515',
+            'timestamp': 1337076481,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/2feb2/band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd).html',
+        'md5': '64599a23d3ac31cf2fe069e4353d8162',
+        'info_dict': {
+            'id': '2feb2',
+            'ext': 'mp4',
+            'title': 'BAND-MAID - onset (Instrumental) Live - Zepp Tokyo (Full HD)',
+            'display_id': 'band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd)',
+            'description': 'Výborná inštrumentálna skladba od skupiny BAND-MAID.',
+            'thumbnail': 'https://fs5.mojevideo.sk/imgfb/196274.jpg',
+            'duration': 240.0,
+            'upload_date': '20190708',
+            'timestamp': 1562576592,
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/358c8/dva_nissany_skyline_strielaju_v_londyne.html',
+        'only_matching': True,
+    }, {
+        # 720p
+        'url': 'https://www.mojevideo.sk/video/2455d/gopro_hero4_session_nova_sportova_vodotesna_kamera.html',
+        'only_matching': True,
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/352ee/amd_rx_6800_xt_vs_nvidia_rtx_3080_(test_v_9_hrach).html',
+        'only_matching': True,
+    }, {
+        # 1080p
+        'url': 'https://www.mojevideo.sk/video/2cbeb/trailer_z_avengers_infinity_war.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id, display_id = self._match_valid_url(url).groups()
+        webpage = self._download_webpage(url, video_id)
+
+        video_id_dec = self._search_regex(
+            r'\bvId\s*=\s*(\d+)', webpage, 'video id', fatal=False) or str(int(video_id, 16))
+        video_exp = self._search_regex(r'\bvEx\s*=\s*["\'](\d+)', webpage, 'video expiry')
+        video_hashes = self._search_json(
+            r'\bvHash\s*=', webpage, 'video hashes', video_id,
+            contains_pattern=r'\[(?s:.+)\]', transform_source=js_to_json)
+
+        formats = []
+        for video_hash, (suffix, quality, format_note) in zip(video_hashes, [
+            ('', 1, 'normálna kvalita'),
+            ('_lq', 0, 'nízka kvalita'),
+            ('_hd', 2, 'HD-720p'),
+            ('_fhd', 3, 'FULL HD-1080p'),
+            ('_2k', 4, '2K-1440p'),
+        ]):
+            formats.append({
+                'format_id': f'mp4-{quality}',
+                'quality': quality,
+                'format_note': format_note,
+                'url': update_url_query(
+                    f'https://cache01.mojevideo.sk/securevideos69/{video_id_dec}{suffix}.mp4', {
+                        'md5': video_hash,
+                        'expires': video_exp,
+                    }),
+            })
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': (self._og_search_title(webpage, default=None)
+                      or remove_end(self._html_extract_title(webpage, 'title'), ' - Mojevideo')),
+            'description': self._og_search_description(webpage),
+            **self._search_json_ld(webpage, video_id, default={}),
+        }

yt_dlp/extractor/niconico.py

@@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
-        'md5': 'd1a75c0823e2f629128c43e1212760f9',
         'info_dict': {
             'id': 'sm22312215',
             'ext': 'mp4',
@@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['未設定'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # File downloaded with and without credentials are different, so omit
         # the md5 field
@@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor):
             'view_count': int,
             'genres': ['音楽・サウンド'],
             'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # 'video exists but is marked as "deleted"
         # md5 is unstable
@@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor):
     }, {
         # video not available via `getflv`; "old" HTML5 video
         'url': 'http://www.nicovideo.jp/watch/sm1151009',
-        'md5': 'f95a3d259172667b293530cc2e41ebda',
         'info_dict': {
             'id': 'sm1151009',
             'ext': 'mp4',
@@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['ゲーム'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # "New" HTML5 video
-        # md5 is unstable
         'url': 'http://www.nicovideo.jp/watch/sm31464864',
         'info_dict': {
             'id': 'sm31464864',
@@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['アニメ'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Video without owner
         'url': 'http://www.nicovideo.jp/watch/sm18238488',
-        'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
         'info_dict': {
             'id': 'sm18238488',
             'ext': 'mp4',
@@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['エンターテイメント'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
         'only_matching': True,
@@ -424,7 +420,7 @@ def _yield_dms_formats(self, api_data, video_id):
                 'x-request-with': 'https://www.nicovideo.jp',
             })['data']['contentUrl']
         # Getting all audio formats results in duplicate video formats which we filter out later
-        dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id)
+        dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id, 'mp4')
 
         # m3u8 extraction does not provide audio bitrates, so extract from the API data and fix
         for audio_fmt in traverse_obj(dms_fmts, lambda _, v: v['vcodec'] == 'none'):
@@ -436,7 +432,6 @@ def _yield_dms_formats(self, api_data, video_id):
                     'asr': ('samplingRate', {int_or_none}),
                 }), get_all=False),
                 'acodec': 'aac',
-                'ext': 'm4a',
             }
 
         # Sort before removing dupes to keep the format dicts with the lowest tbr
@@ -458,9 +453,11 @@ def _real_extract(self, url):
             if video_id.startswith('so'):
                 video_id = self._match_id(handle.url)
 
-            api_data = self._parse_json(self._html_search_regex(
+            api_data = traverse_obj(
-                'data-api-data="([^"]+)"', webpage,
+                self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
-                'API data', default='{}'), video_id)
+                ('data', 'response', {dict}))
+            if not api_data:
+                raise ExtractorError('Server response data not found')
         except ExtractorError as e:
             try:
                 api_data = self._download_json(

yt_dlp/extractor/noodlemagazine.py

@@ -43,14 +43,8 @@ def _real_extract(self, url):
         def build_url(url_or_path):
             return urljoin('https://adult.noodlemagazine.com', url_or_path)
 
-        headers = {'Referer': url}
+        playlist_info = self._search_json(
-        player_path = self._html_search_regex(
+            r'window\.playlist\s*=', webpage, video_id, 'playlist info')
-            r'<iframe[^>]+\bid="iplayer"[^>]+\bsrc="([^"]+)"', webpage, 'player path')
-        player_iframe = self._download_webpage(
-            build_url(player_path), video_id, 'Downloading iframe page', headers=headers)
-        playlist_url = self._search_regex(
-            r'window\.playlistUrl\s*=\s*["\']([^"\']+)["\']', player_iframe, 'playlist url')
-        playlist_info = self._download_json(build_url(playlist_url), video_id, headers=headers)
 
         formats = []
         for source in traverse_obj(playlist_info, ('sources', lambda _, v: v['file'])):

yt_dlp/extractor/nzonscreen.py

@@ -10,7 +10,7 @@
 
 
 class NZOnScreenIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
         'info_dict': {

yt_dlp/extractor/nzz.py

@@ -1,9 +1,6 @@
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    extract_attributes,
-)
 
 
 class NZZIE(InfoExtractor):
@@ -22,19 +19,14 @@ class NZZIE(InfoExtractor):
         'playlist_count': 1,
     }]
 
+    def _entries(self, webpage, page_id):
+        for script in re.findall(r'(?s)<script[^>]* data-hid="jw-video-jw[^>]+>(.+?)</script>', webpage):
+            settings = self._search_json(r'var\s+settings\s*=[^{]*', script, 'settings', page_id, fatal=False)
+            if entry := self._parse_jwplayer_data(settings, page_id):
+                yield entry
+
     def _real_extract(self, url):
         page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
 
-        entries = []
+        return self.playlist_result(self._entries(webpage, page_id), page_id)
-        for player_element in re.findall(
-                r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage):
-            player_params = extract_attributes(player_element)
-            if player_params.get('data-type') not in ('kaltura_singleArticle',):
-                self.report_warning('Unsupported player type')
-                continue
-            entry_id = player_params['data-id']
-            entries.append(self.url_result(
-                'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
-
-        return self.playlist_result(entries, page_id)

yt_dlp/extractor/olympics.py

@@ -1,9 +1,19 @@
 from .common import InfoExtractor
-from ..utils import int_or_none, try_get
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    parse_qs,
+    try_get,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
 
 
 class OlympicsReplayIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P<id>[^/#&?]+)'
+    _VALID_URL = r'https?://(?:www\.)?olympics\.com/[a-z]{2}/(?:paris-2024/)?(?:replay|videos?|original-series/episode)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays',
         'info_dict': {
@@ -11,26 +21,105 @@ class OlympicsReplayIE(InfoExtractor):
             'ext': 'mp4',
             'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020',
             'upload_date': '20210801',
-            'timestamp': 1627783200,
+            'timestamp': 1627797600,
             'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3',
-            'uploader': 'International Olympic Committee',
+            'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2',
-        },
+            'duration': 7017.0,
-        'params': {
-            'skip_download': True,
         },
     }, {
-        'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
+        'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024',
-        'only_matching': True,
+        'info_dict': {
+            'id': '32633650-c5ee-4280-8b94-fb6defb6a9b5',
+            'ext': 'mp4',
+            'title': 'B-girl Nicka - Breaking Life, Road to Paris 2024 | Episode 1',
+            'upload_date': '20240517',
+            'timestamp': 1715948200,
+            'description': 'md5:f63d728a41270ec628f6ac33ce471bb1',
+            'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/a3j96l7j6so3vyfijby1',
+            'duration': 1321.0,
+        },
+    }, {
+        'url': 'https://olympics.com/en/paris-2024/videos/men-s-preliminaries-gbr-esp-ned-rsa-hockey-olympic-games-paris-2024',
+        'info_dict': {
+            'id': '3d96db23-8eee-4b7c-8ef5-488a0361026c',
+            'ext': 'mp4',
+            'title': 'Men\'s Preliminaries GBR-ESP & NED-RSA | Hockey | Olympic Games Paris 2024',
+            'upload_date': '20240727',
+            'timestamp': 1722066600,
+        },
+        'skip': 'Geo-restricted to RU, BR, BT, NP, TM, BD, TL',
+    }, {
+        'url': 'https://olympics.com/en/paris-2024/videos/dnp-suni-lee-i-have-goals-and-i-have-expectations-for-myself-but-i-also-am-trying-to-give-myself-grace',
+        'info_dict': {
+            'id': 'a42f37ab-8a74-41d0-a7d9-af27b7b02a90',
+            'ext': 'mp4',
+            'title': 'md5:c7cfbc9918636a98e66400a812e4d407',
+            'upload_date': '20240729',
+            'timestamp': 1722288600,
+        },
     }]
+    _GEO_BYPASS = False
+
+    def _extract_from_nextjs_data(self, webpage, video_id):
+        data = traverse_obj(self._search_nextjs_data(webpage, video_id, default={}), (
+            'props', 'pageProps', 'page', 'items',
+            lambda _, v: v['name'] == 'videoPlaylist', 'data', 'currentVideo', {dict}, any))
+        if not data:
+            return None
+
+        geo_countries = traverse_obj(data, ('countries', ..., {str}))
+        if traverse_obj(data, ('geoRestrictedVideo', {bool})):
+            self.raise_geo_restricted(countries=geo_countries)
+
+        is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE'
+        m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl']
+        tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id)
+
+        try:
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                tokenized_url, video_id, 'mp4', m3u8_id='hls')
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and 'georestricted' in e.cause.msg:
+                self.raise_geo_restricted(countries=geo_countries)
+            raise
+
+        return {
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': is_live,
+            **traverse_obj(data, {
+                'id': ('videoID', {str}),
+                'title': ('title', {str}),
+                'timestamp': ('contentDate', {parse_iso8601}),
+            }),
+        }
+
+    def _tokenize_url(self, url, token, is_live, video_id):
+        return self._download_json(
+            'https://metering.olympics.com/tokengenerator', video_id,
+            'Downloading tokenized m3u8 url', query={
+                **parse_qs(url),
+                'url': update_url(url, query=None),
+                'service-id': 'live' if is_live else 'vod',
+                'user-auth': token,
+            })['data']['url']
+
+    def _legacy_tokenize_url(self, url, video_id):
+        return self._download_json(
+            'https://olympics.com/tokenGenerator', video_id,
+            'Downloading legacy tokenized m3u8 url', query={'url': url})
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+
+        if info := self._extract_from_nextjs_data(webpage, video_id):
+            return info
+
         title = self._html_search_meta(('title', 'og:title', 'twitter:title'), webpage)
-        uuid = self._html_search_meta('episode_uid', webpage)
+        video_uuid = self._html_search_meta('episode_uid', webpage)
         m3u8_url = self._html_search_meta('video_url', webpage)
-        json_ld = self._search_json_ld(webpage, uuid)
+        json_ld = self._search_json_ld(webpage, video_uuid)
         thumbnails_list = json_ld.get('image')
         if not thumbnails_list:
             thumbnails_list = self._html_search_regex(
@@ -48,12 +137,12 @@ def _real_extract(self, url):
                 'width': width,
                 'height': int_or_none(try_get(width, lambda x: x * height_a / width_a)),
             })
-        m3u8_url = self._download_json(
+
-            f'https://olympics.com/tokenGenerator?url={m3u8_url}', uuid, note='Downloading m3u8 url')
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-        formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, 'mp4', m3u8_id='hls')
+            self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
 
         return {
-            'id': uuid,
+            'id': video_uuid,
             'title': title,
             'thumbnails': thumbnails,
             'formats': formats,

yt_dlp/extractor/patreon.py

@@ -1,3 +1,4 @@
+import functools
 import itertools
 import urllib.parse
 
@@ -22,13 +23,19 @@
 
 
 class PatreonBaseIE(InfoExtractor):
-    USER_AGENT = 'Patreon/7.6.28 (Android; Android 11; Scale/2.10)'
+    @functools.cached_property
+    def patreon_user_agent(self):
+        # Patreon mobile UA is needed to avoid triggering Cloudflare anti-bot protection.
+        # Newer UA yields higher res m3u8 formats for locked posts, but gives 401 if not logged-in
+        if self._get_cookies('https://www.patreon.com/').get('session_id'):
+            return 'Patreon/72.2.28 (Android; Android 14; Scale/2.10)'
+        return 'Patreon/7.6.28 (Android; Android 11; Scale/2.10)'
 
     def _call_api(self, ep, item_id, query=None, headers=None, fatal=True, note=None):
         if headers is None:
             headers = {}
         if 'User-Agent' not in headers:
-            headers['User-Agent'] = self.USER_AGENT
+            headers['User-Agent'] = self.patreon_user_agent
         if query:
             query.update({'json-api-version': 1.0})
 
@@ -48,6 +55,7 @@ def _call_api(self, ep, item_id, query=None, headers=None, fatal=True, note=None
 
 
 class PatreonIE(PatreonBaseIE):
+    IE_NAME = 'patreon'
     _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.patreon.com/creation?hid=743933',
@@ -111,6 +119,7 @@ class PatreonIE(PatreonBaseIE):
             'comment_count': int,
             'channel_is_verified': True,
             'chapters': 'count:4',
+            'timestamp': 1423689666,
         },
         'params': {
             'noplaylist': True,
@@ -221,6 +230,7 @@ class PatreonIE(PatreonBaseIE):
             'thumbnail': r're:^https?://.+',
         },
         'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
     }, {
         # multiple attachments/embeds
         'url': 'https://www.patreon.com/posts/holy-wars-solos-100601977',
@@ -326,8 +336,13 @@ def _real_extract(self, url):
         if embed_url and (urlh := self._request_webpage(
                 embed_url, video_id, 'Checking embed URL', headers=headers,
                 fatal=False, errnote=False, expected_status=403)):
+            # Vimeo's Cloudflare anti-bot protection will return HTTP status 200 for 404, so we need
+            # to check for "Sorry, we couldn&amp;rsquo;t find that page" in the meta description tag
+            meta_description = clean_html(self._html_search_meta(
+                'description', self._webpage_read_content(urlh, embed_url, video_id, fatal=False), default=None))
             # Password-protected vids.io embeds return 403 errors w/o --video-password or session cookie
-            if urlh.status != 403 or VidsIoIE.suitable(embed_url):
+            if ((urlh.status != 403 and meta_description != 'Sorry, we couldn’t find that page')
+                    or VidsIoIE.suitable(embed_url)):
                 entries.append(self.url_result(smuggle_url(embed_url, headers)))
 
         post_file = traverse_obj(attributes, ('post_file', {dict}))
@@ -419,15 +434,19 @@ def _get_comments(self, post_id):
 
 
 class PatreonCampaignIE(PatreonBaseIE):
-
+    IE_NAME = 'patreon:campaign'
-    _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P<campaign_id>\d+))|(?P<vanity>[-\w]+))'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?patreon\.com/(?:
+            (?:m|api/campaigns)/(?P<campaign_id>\d+)|
+            (?P<vanity>(?!creation[?/]|posts/|rss[?/])[\w-]+)
+        )(?:/posts)?/?(?:$|[?#])'''
     _TESTS = [{
         'url': 'https://www.patreon.com/dissonancepod/',
         'info_dict': {
             'title': 'Cognitive Dissonance Podcast',
             'channel_url': 'https://www.patreon.com/dissonancepod',
             'id': '80642',
-            'description': 'md5:eb2fa8b83da7ab887adeac34da6b7af7',
+            'description': r're:(?s).*We produce a weekly news podcast focusing on stories that deal with skepticism and religion.*',
             'channel_id': '80642',
             'channel': 'Cognitive Dissonance Podcast',
             'age_limit': 0,
@@ -442,31 +461,46 @@ class PatreonCampaignIE(PatreonBaseIE):
         'url': 'https://www.patreon.com/m/4767637/posts',
         'info_dict': {
             'title': 'Not Just Bikes',
-            'channel_follower_count': int,
             'id': '4767637',
             'channel_id': '4767637',
             'channel_url': 'https://www.patreon.com/notjustbikes',
-            'description': 'md5:595c6e7dca76ae615b1d38c298a287a1',
+            'description': r're:(?s).*Not Just Bikes started as a way to explain why we chose to live in the Netherlands.*',
             'age_limit': 0,
             'channel': 'Not Just Bikes',
             'uploader_url': 'https://www.patreon.com/notjustbikes',
-            'uploader': 'Not Just Bikes',
+            'uploader': 'Jason',
             'uploader_id': '37306634',
             'thumbnail': r're:^https?://.*$',
         },
         'playlist_mincount': 71,
+    }, {
+        'url': 'https://www.patreon.com/api/campaigns/4243769/posts',
+        'info_dict': {
+            'title': 'Second Thought',
+            'channel_follower_count': int,
+            'id': '4243769',
+            'channel_id': '4243769',
+            'channel_url': 'https://www.patreon.com/secondthought',
+            'description': r're:(?s).*Second Thought is an educational YouTube channel.*',
+            'age_limit': 0,
+            'channel': 'Second Thought',
+            'uploader_url': 'https://www.patreon.com/secondthought',
+            'uploader': 'JT Chapman',
+            'uploader_id': '32718287',
+            'thumbnail': r're:^https?://.*$',
+        },
+        'playlist_mincount': 201,
     }, {
         'url': 'https://www.patreon.com/dissonancepod/posts',
         'only_matching': True,
     }, {
         'url': 'https://www.patreon.com/m/5932659',
         'only_matching': True,
+    }, {
+        'url': 'https://www.patreon.com/api/campaigns/4243769',
+        'only_matching': True,
     }]
 
-    @classmethod
-    def suitable(cls, url):
-        return False if PatreonIE.suitable(url) else super().suitable(url)
-
     def _entries(self, campaign_id):
         cursor = None
         params = {
@@ -493,7 +527,7 @@ def _real_extract(self, url):
 
         campaign_id, vanity = self._match_valid_url(url).group('campaign_id', 'vanity')
         if campaign_id is None:
-            webpage = self._download_webpage(url, vanity, headers={'User-Agent': self.USER_AGENT})
+            webpage = self._download_webpage(url, vanity, headers={'User-Agent': self.patreon_user_agent})
             campaign_id = self._search_nextjs_data(
                 webpage, vanity)['props']['pageProps']['bootstrapEnvelope']['pageBootstrap']['campaign']['data']['id']
 

yt_dlp/extractor/picarto.py

@@ -5,6 +5,7 @@
     ExtractorError,
     str_or_none,
     traverse_obj,
+    update_url,
 )
 
 
@@ -43,15 +44,16 @@ def _real_extract(self, url):
     url
   }
 }''' % (channel_id, channel_id),  # noqa: UP031
-            })['data']
+            }, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']
         metadata = data['channel']
 
         if metadata.get('online') == 0:
             raise ExtractorError('Stream is offline', expected=True)
         title = metadata['title']
 
-        cdn_data = self._download_json(
+        cdn_data = self._download_json(''.join((
-            data['getLoadBalancerUrl']['url'] + '/stream/json_' + metadata['stream_name'] + '.js',
+            update_url(data['getLoadBalancerUrl']['url'], scheme='https'),
+            '/stream/json_', metadata['stream_name'], '.js')),
             channel_id, 'Downloading load balancing info')
 
         formats = []
@@ -99,10 +101,10 @@ class PicartoVodIE(InfoExtractor):
         },
         'skip': 'The VOD does not exist',
     }, {
-        'url': 'https://picarto.tv/ArtofZod/videos/772650',
+        'url': 'https://picarto.tv/ArtofZod/videos/771008',
-        'md5': '00067a0889f1f6869cc512e3e79c521b',
+        'md5': 'abef5322f2700d967720c4c6754b2a34',
         'info_dict': {
-            'id': '772650',
+            'id': '771008',
             'ext': 'mp4',
             'title': 'Art of Zod - Drawing and Painting',
             'thumbnail': r're:^https?://.*\.jpg',
@@ -131,7 +133,7 @@ def _real_extract(self, url):
     }}
   }}
 }}''',
-            })['data']['video']
+            }, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']['video']
 
         file_name = data['file_name']
         netloc = urllib.parse.urlparse(data['video_recording_image_url']).netloc

yt_dlp/extractor/pinterest.py

@@ -109,7 +109,7 @@ def _extract_video(self, data, extract_formats=True):
 
 
 class PinterestIE(PinterestBaseIE):
-    _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?P<id>\d+)'
+    _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?:[\w-]+--)?(?P<id>\d+)'
     _TESTS = [{
         # formats found in data['videos']
         'url': 'https://www.pinterest.com/pin/664281013778109217/',
@@ -174,6 +174,25 @@ class PinterestIE(PinterestBaseIE):
     }, {
         'url': 'https://co.pinterest.com/pin/824721750502199491/',
         'only_matching': True,
+    },
+        {
+        'url': 'https://pinterest.com/pin/dive-into-serenity-blue-lagoon-pedi-nails-for-a-tranquil-and-refreshing-spa-experience-video-in-2024--2885187256207927',
+        'info_dict': {
+            'id': '2885187256207927',
+            'ext': 'mp4',
+            'title': 'Dive into Serenity: Blue Lagoon Pedi Nails for a Tranquil and Refreshing Spa Experience! 💙💅',
+            'description': 'md5:5da41c767d2317e42e49b663b0b2150f',
+            'uploader': 'Glamour Artistry |Everyday Outfits, Luxury Fashion & Nail Designs',
+            'uploader_id': '1142999717836434688',
+            'upload_date': '20240702',
+            'timestamp': 1719939156,
+            'duration': 7.967,
+            'comment_count': int,
+            'repost_count': int,
+            'categories': 'count:9',
+            'tags': ['#BlueLagoonPediNails', '#SpaExperience'],
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+        },
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/pornhub.py

@@ -628,8 +628,7 @@ def is_404(e):
             page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
-            for e in page_entries:
+            yield from page_entries
-                yield e
             if not self._has_more(webpage):
                 break
 

yt_dlp/extractor/radiko.py

@@ -7,6 +7,7 @@
 from ..utils import (
     ExtractorError,
     clean_html,
+    join_nonempty,
     time_seconds,
     try_call,
     unified_timestamp,
@@ -167,7 +168,7 @@ def _extract_performers(self, prog):
 
 
 class RadikoIE(RadikoBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<timestring>\d+)'
 
     _TESTS = [{
         # QRR (文化放送) station provides <desc>
@@ -183,8 +184,9 @@ class RadikoIE(RadikoBaseIE):
     }]
 
     def _real_extract(self, url):
-        station, video_id = self._match_valid_url(url).groups()
+        station, timestring = self._match_valid_url(url).group('station', 'timestring')
-        vid_int = unified_timestamp(video_id, False)
+        video_id = join_nonempty(station, timestring)
+        vid_int = unified_timestamp(timestring, False)
         prog, station_program, ft, radio_begin, radio_end = self._find_program(video_id, station, vid_int)
 
         auth_token, area_id = self._auth_client()
@@ -207,7 +209,7 @@ def _real_extract(self, url):
                     'ft': radio_begin,
                     'end_at': radio_end,
                     'to': radio_end,
-                    'seek': video_id,
+                    'seek': timestring,
                 },
             ),
         }

yt_dlp/extractor/radiofrance.py

@@ -16,7 +16,7 @@
 
 
 class RadioFranceIE(InfoExtractor):
-    _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
     IE_NAME = 'radiofrance'
 
     _TEST = {