From d42b2d2985f851078226e587fcdc8cdfd7cde435 Mon Sep 17 00:00:00 2001 From: tinybug Date: Thu, 7 Aug 2014 11:24:51 +0800 Subject: [PATCH 1/5] Update vube.py fix extractor is broken #3459 --- youtube_dl/extractor/vube.py | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index f1b9e9a19..109c4b459 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -71,12 +71,8 @@ class VubeIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - data_json = self._search_regex( - r'(?s)window\["(?:tapiVideoData|vubeOriginalVideoData)"\]\s*=\s*(\{.*?\n});\n', - webpage, 'video data' - ) - data = json.loads(data_json) + json_url = 'http://vube.com/t-api/v1/video/%s?country=US&limit=120®ion=US' % video_id + data = self._download_json(json_url, video_id) video = ( data.get('video') or data) From 5961017202174bf14eda0c0b603e4da44983c884 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 7 Aug 2014 20:04:29 +0700 Subject: [PATCH 2/5] [vube] Extract audio and categories --- youtube_dl/extractor/vube.py | 67 +++++++++++++++++++----------------- 1 file changed, 36 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index 109c4b459..2544c24bd 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -1,10 +1,12 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class VubeIE(InfoExtractor): @@ -29,6 +31,7 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], } }, { @@ -47,6 +50,7 @@ class VubeIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['seraina', 'jessica', 'krewella', 'alive'], } }, { 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', @@ -56,13 +60,15 @@ class VubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Frozen - Let It Go Cover by Siren Gene', 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.', - 'uploader': 'Siren Gene', - 'uploader_id': 'Siren', 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$', + 'uploader': 'Siren', + 'timestamp': 1395448018, + 'upload_date': '20140322', 'duration': 221.788, 'like_count': int, 'dislike_count': int, 'comment_count': int, + 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], } } ] @@ -71,43 +77,40 @@ class VubeIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - json_url = 'http://vube.com/t-api/v1/video/%s?country=US&limit=120®ion=US' % video_id - data = self._download_json(json_url, video_id) - video = ( - data.get('video') or - data) - assert isinstance(video, dict) + video = self._download_json( + 'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON') public_id = video['public_id'] - formats = [ - { - 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id), - 'height': int(fmt['height']), - 'abr': int(fmt['audio_bitrate']), - 'vbr': int(fmt['video_bitrate']), - 'format_id': fmt['media_resolution_id'] - } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed' - ] + formats = [] + + for media in video['media'].get('video', []) + video['media'].get('audio', []): + if media['transcoding_status'] != 'processed': + continue + fmt = { + 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id), + 'abr': int(media['audio_bitrate']), + 'format_id': compat_str(media['media_resolution_id']), + } + vbr = int(media['video_bitrate']) + if vbr: + fmt.update({ + 'vbr': vbr, + 'height': int(media['height']), + }) + formats.append(fmt) self._sort_formats(formats) title = video['title'] description = video.get('description') - thumbnail = self._proto_relative_url( - video.get('thumbnail') or video.get('thumbnail_src'), - scheme='http:') - uploader = data.get('user', {}).get('channel', {}).get('name') or video.get('user_alias') - uploader_id = data.get('user', {}).get('name') + thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') + uploader = video.get('user_alias') or video.get('channel') timestamp = int_or_none(video.get('upload_time')) duration = video['duration'] view_count = video.get('raw_view_count') - like_count = video.get('rlikes') - if like_count is None: - like_count = video.get('total_likes') - dislike_count = video.get('rhates') - if dislike_count is None: - dislike_count = video.get('total_hates') + like_count = video.get('total_likes') + dislike_count = video.get('total_hates') comments = video.get('comments') comment_count = None @@ -120,6 +123,8 @@ class VubeIE(InfoExtractor): else: comment_count = len(comments) + categories = [tag['text'] for tag in video['tags']] + return { 'id': video_id, 'formats': formats, @@ -127,11 +132,11 @@ class VubeIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'uploader_id': uploader_id, 'timestamp': timestamp, 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, + 'categories': categories, } From 64d02399d8d2acbb55b22f789a5b54e79591b7b3 Mon Sep 17 00:00:00 2001 From: pyed Date: Fri, 8 Aug 2014 09:48:02 +0300 Subject: [PATCH 3/5] [xboxclips] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/xboxclips.py | 34 +++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) create mode 100644 youtube_dl/extractor/xboxclips.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 468c7dc29..23f53ba13 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -384,6 +384,7 @@ from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .wrzuta import WrzutaIE from .xbef import XBefIE +from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py new file mode 100644 index 000000000..499702d0d --- /dev/null +++ b/youtube_dl/extractor/xboxclips.py @@ -0,0 +1,34 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor + +class XboxClipsIE(InfoExtractor): + _VALID_URL = r'^https?://(www\.)?xboxclips\.com/video.php\?.*vid=(?P[\w-]*)' + _TEST = { + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex(r'Link.*?"(.*?)"', + webpage, 'video URL') + + video_title = self._html_search_regex(r'.*?\|(.*?)<', + webpage, 'title') + + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'ext': 'mp4', + } From a91cf277672318e942af891d6c962c053abda45d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Aug 2014 18:43:28 +0700 Subject: [PATCH 4/5] [nowness] Add support for cn URLs (Closes #3465) --- youtube_dl/extractor/nowness.py | 40 +++++++++++++++++++++++---------- 1 file changed, 28 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index 1c5e9401f..6b2f3f55a 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,3 +1,4 @@ +# encoding: utf-8 from __future__ import unicode_literals import re @@ -8,19 +9,34 @@ from ..utils import ExtractorError class NownessIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' + _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])' - _TEST = { - 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'md5': '068bc0202558c2e391924cb8cc470676', - 'info_dict': { - 'id': '2520295746001', - 'ext': 'mp4', - 'description': 'Candor: The Art of Gesticulation', - 'uploader': 'Nowness', - 'title': 'Candor: The Art of Gesticulation', - } - } + _TESTS = [ + { + 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', + 'md5': '068bc0202558c2e391924cb8cc470676', + 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', + 'title': 'Candor: The Art of Gesticulation', + 'description': 'Candor: The Art of Gesticulation', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + { + 'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr', + 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', + 'info_dict': { + 'id': '3716354522001', + 'ext': 'mp4', + 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'Nowness', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) From 31bf213032b72069fdd14f5ace3ace33ee46eaf8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Aug 2014 19:21:24 +0700 Subject: [PATCH 5/5] [xboxclips] PEP8 and extract more metadata --- youtube_dl/extractor/xboxclips.py | 59 +++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/xboxclips.py b/youtube_dl/extractor/xboxclips.py index 499702d0d..a9aa72e73 100644 --- a/youtube_dl/extractor/xboxclips.py +++ b/youtube_dl/extractor/xboxclips.py @@ -1,34 +1,57 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + float_or_none, + int_or_none, +) + class XboxClipsIE(InfoExtractor): - _VALID_URL = r'^https?://(www\.)?xboxclips\.com/video.php\?.*vid=(?P<id>[\w-]*)' + _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})' _TEST = { - 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', - 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', - 'info_dict': { - 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', - 'ext': 'mp4', - 'title': 'Iabdulelah playing Upload Studio', - } - } + 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325', + 'md5': 'fbe1ec805e920aeb8eced3c3e657df5d', + 'info_dict': { + 'id': '074a69a9-5faf-46aa-b93b-9909c1720325', + 'ext': 'mp4', + 'title': 'Iabdulelah playing Upload Studio', + 'filesize_approx': 28101836.8, + 'timestamp': 1407388500, + 'upload_date': '20140807', + 'duration': 56, + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'Link.*?"(.*?)"', - webpage, 'video URL') - video_title = self._html_search_regex(r'<title>.*?\|(.*?)<', - webpage, 'title') + video_url = self._html_search_regex( + r'>Link: <a href="([^"]+)">', webpage, 'video URL') + title = self._html_search_regex( + r'<title>XboxClips \| ([^<]+)', webpage, 'title') + timestamp = parse_iso8601(self._html_search_regex( + r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False)) + filesize = float_or_none(self._html_search_regex( + r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024) + duration = int_or_none(self._html_search_regex( + r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'>Views: (\d+)<', webpage, 'view count', fatal=False)) return { - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': 'mp4', - } + 'id': video_id, + 'url': video_url, + 'title': title, + 'timestamp': timestamp, + 'filesize_approx': filesize, + 'duration': duration, + 'view_count': view_count, + }