[Zee5] Add Show Extractor (#160)

Co-authored-by: Ashish <ashish@pop-os.localdomain>
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>

yt_dlp/extractor/extractors.py

@@ -1668,5 +1668,6 @@
 from .zhihu import ZhihuIE
 from .zingmp3 import ZingMp3IE
 from .zee5 import Zee5IE
+from .zee5 import Zee5SeriesIE
 from .zoom import ZoomIE
 from .zype import ZypeIE

yt_dlp/extractor/zee5.py

@@ -4,6 +4,7 @@
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_age_limit,
@@ -16,24 +17,34 @@
 
 
 class Zee5IE(InfoExtractor):
-    _VALID_URL = r'(?:zee5:|https?://(?:www\.)?zee5\.com/[^#?]*/(?P<display_id>[^#?]+)/)(?P<id>[^#?/]+)(?:$|[?#])'
+    _VALID_URL = r'''(?x)
+                     (?:
+                        zee5:|
+                        (?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
+                        (?:
+                            (?:tvshows|kids)(?:/[^#/?]+){3}
+                            |movies/[^#/?]+
+                        )/(?P<display_id>[^#/?]+)/
+                     )
+                     (?P<id>[^#/?]+)/?(?:$|[?#])
+                     '''
     _TESTS = [{
         'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
         'info_dict': {
-            "id": "0-0-63098",
+            'id': '0-0-63098',
-            "ext": "m3u8",
+            'ext': 'mp4',
-            "display_id": "krishna-the-birth",
+            'display_id': 'krishna-the-birth',
-            "title": "Krishna - The Birth",
+            'title': 'Krishna - The Birth',
-            "duration": 4368,
+            'duration': 4368,
-            "average_rating": 4,
+            'average_rating': 4,
-            "description": str,
+            'description': str,
-            "alt_title": "Krishna - The Birth",
+            'alt_title': 'Krishna - The Birth',
-            "uploader": "Zee Entertainment Enterprises Ltd",
+            'uploader': 'Zee Entertainment Enterprises Ltd',
-            "release_date": "20060101",
+            'release_date': '20060101',
-            "upload_date": "20060101",
+            'upload_date': '20060101',
-            "timestamp": 1136073600,
+            'timestamp': 1136073600,
-            "thumbnail": "https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg",
+            'thumbnail': 'https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg',
-            "tags": list
+            'tags': list
         },
         'params': {
             'format': 'bv',
@@ -41,23 +52,23 @@ class Zee5IE(InfoExtractor):
     }, {
         'url': 'https://zee5.com/tvshows/details/krishna-balram/0-6-1871/episode-1-the-test-of-bramha/0-1-233402',
         'info_dict': {
-            "id": "0-1-233402",
+            'id': '0-1-233402',
-            'ext': 'm3u8',
+            'ext': 'mp4',
-            "display_id": "episode-1-the-test-of-bramha",
+            'display_id': 'episode-1-the-test-of-bramha',
-            "title": "Episode 1 - The Test Of Bramha",
+            'title': 'Episode 1 - The Test Of Bramha',
-            "duration": 1336,
+            'duration': 1336,
-            "average_rating": 4,
+            'average_rating': 4,
-            "description": str,
+            'description': str,
-            "alt_title": "Episode 1 - The Test Of Bramha",
+            'alt_title': 'Episode 1 - The Test Of Bramha',
-            "uploader": "Green Gold",
+            'uploader': 'Green Gold',
-            "release_date": "20090101",
+            'release_date': '20090101',
-            "upload_date": "20090101",
+            'upload_date': '20090101',
-            "timestamp": 1230768000,
+            'timestamp': 1230768000,
-            "thumbnail": "https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg",
+            'thumbnail': 'https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg',
-            "series": "Krishna Balram",
+            'series': 'Krishna Balram',
-            "season_number": 1,
+            'season_number': 1,
-            "episode_number": 1,
+            'episode_number': 1,
-            "tags": list,
+            'tags': list,
         },
         'params': {
             'format': 'bv',
@@ -65,16 +76,19 @@ class Zee5IE(InfoExtractor):
     }, {
         'url': 'https://www.zee5.com/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
         'only_matching': True
+    }, {
+        'url': 'https://www.zee5.com/global/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
+        'only_matching': True
     }]
 
     def _real_extract(self, url):
         video_id, display_id = re.match(self._VALID_URL, url).group('id', 'display_id')
         access_token_request = self._download_json(
             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
-            video_id, note="Downloading access token")
+            video_id, note='Downloading access token')
         token_request = self._download_json(
             'https://useraction.zee5.com/tokennd',
-            video_id, note="Downloading video token")
+            video_id, note='Downloading video token')
         json_data = self._download_json(
             'https://gwapi.zee5.com/content/details/{}?translation=en&country=IN'.format(video_id),
             video_id, headers={'X-Access-Token': access_token_request['token']})
@@ -114,3 +128,78 @@ def _real_extract(self, url):
             'episode_number': int_or_none(try_get(json_data, lambda x: x['index'])),
             'tags': try_get(json_data, lambda x: x['tags'], list)
         }
+
+
+class Zee5SeriesIE(InfoExtractor):
+    IE_NAME = 'zee5:series'
+    _VALID_URL = r'''(?x)
+                     (?:
+                        zee5:series:|
+                        (?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
+                        (?:tvshows|kids)(?:/[^#/?]+){2}/
+                     )
+                     (?P<id>[^#/?]+)/?(?:$|[?#])
+                     '''
+    _TESTS = [{
+        'url': 'https://www.zee5.com/kids/kids-shows/krishna-balram/0-6-1871',
+        'playlist_mincount': 43,
+        'info_dict': {
+            'id': '0-6-1871',
+        },
+    }, {
+        'url': 'https://www.zee5.com/tvshows/details/bhabi-ji-ghar-par-hai/0-6-199',
+        'playlist_mincount': 1500,
+        'info_dict': {
+            'id': '0-6-199',
+        },
+    }, {
+        'url': 'https://www.zee5.com/tvshows/details/agent-raghav-crime-branch/0-6-965',
+        'playlist_mincount': 25,
+        'info_dict': {
+            'id': '0-6-965',
+        },
+    }, {
+        'url': 'https://www.zee5.com/ta/tvshows/details/nagabhairavi/0-6-3201',
+        'playlist_mincount': 3,
+        'info_dict': {
+            'id': '0-6-3201',
+        },
+    }, {
+        'url': 'https://www.zee5.com/global/hi/tvshows/details/khwaabon-ki-zamin-par/0-6-270',
+        'playlist_mincount': 150,
+        'info_dict': {
+            'id': '0-6-270',
+        },
+    }
+    ]
+
+    def _entries(self, show_id):
+        access_token_request = self._download_json(
+            'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
+            show_id, note='Downloading access token')
+        headers = {
+            'X-Access-Token': access_token_request['token'],
+            'Referer': 'https://www.zee5.com/',
+        }
+        show_url = 'https://gwapi.zee5.com/content/tvshow/{}?translation=en&country=IN'.format(show_id)
+
+        page_num = 0
+        show_json = self._download_json(show_url, video_id=show_id, headers=headers)
+        for season in show_json.get('seasons') or []:
+            season_id = try_get(season, lambda x: x['id'], compat_str)
+            next_url = 'https://gwapi.zee5.com/content/tvshow/?season_id={}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'.format(season_id)
+            while next_url:
+                page_num += 1
+                episodes_json = self._download_json(
+                    next_url, video_id=show_id, headers=headers,
+                    note='Downloading JSON metadata page %d' % page_num)
+                for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
+                    video_id = episode.get('id')
+                    yield self.url_result(
+                        'zee5:%s' % video_id,
+                        ie=Zee5IE.ie_key(), video_id=video_id)
+                next_url = url_or_none(episodes_json.get('next_episode_api'))
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        return self.playlist_result(self._entries(show_id), playlist_id=show_id)