[ie/hungama] Overhaul extractors (#7757)

Closes #7754
Authored by: Yalab7, bashonly

yt_dlp/extractor/hungama.py

@@ -1,19 +1,32 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    remove_end,
+    traverse_obj,
     try_get,
+    unified_timestamp,
+    url_or_none,
     urlencode_postdata,
 )
 
 
-class HungamaIE(InfoExtractor):
+class HungamaBaseIE(InfoExtractor):
+    def _call_api(self, path, content_id, fatal=False):
+        return traverse_obj(self._download_json(
+            f'https://cpage.api.hungama.com/v2/page/content/{content_id}/{path}/detail',
+            content_id, fatal=fatal, query={
+                'device': 'web',
+                'platform': 'a',
+                'storeId': '1',
+            }), ('data', {dict})) or {}
+
+
+class HungamaIE(HungamaBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:www\.)?hungama\.com/
+                        (?:www\.|un\.)?hungama\.com/
                         (?:
-                            (?:video|movie)/[^/]+/|
+                            (?:video|movie|short-film)/[^/]+/|
                             tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
                         )
                         (?P<id>\d+)
@@ -25,13 +38,28 @@ class HungamaIE(InfoExtractor):
             'id': '39349649',
             'ext': 'mp4',
             'title': 'Krishna Chants',
-            'description': 'Watch Krishna Chants video now. You can also watch other latest videos only at Hungama',
+            'description': ' ',
             'upload_date': '20180829',
             'duration': 264,
             'timestamp': 1535500800,
             'view_count': int,
-            'thumbnail': 'https://images.hungama.com/c/1/0dc/2ca/39349649/39349649_700x394.jpg',
+            'thumbnail': 'https://images1.hungama.com/tr:n-a_169_m/c/1/0dc/2ca/39349649/39349649_350x197.jpg?v=8',
-        }
+            'tags': 'count:6',
+        },
+    }, {
+        'url': 'https://un.hungama.com/short-film/adira/102524179/',
+        'md5': '2278463f5dc9db9054d0c02602d44666',
+        'info_dict': {
+            'id': '102524179',
+            'ext': 'mp4',
+            'title': 'Adira',
+            'description': 'md5:df20cd4d41eabb33634f06de1025a4b4',
+            'upload_date': '20230417',
+            'timestamp': 1681689600,
+            'view_count': int,
+            'thumbnail': 'https://images1.hungama.com/tr:n-a_23_m/c/1/197/ac9/102524179/102524179_350x525.jpg?v=1',
+            'tags': 'count:7',
+        },
     }, {
         'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
         'only_matching': True,
@@ -51,14 +79,19 @@ def _real_extract(self, url):
                 'c': 'common',
                 'm': 'get_video_mdn_url',
             })
-
         formats = self._extract_m3u8_formats(video_json['stream_url'], video_id, ext='mp4', m3u8_id='hls')
-
+        metadata = self._call_api('movie', video_id)
-        json_ld = self._search_json_ld(
-            self._download_webpage(url, video_id, fatal=False) or '', video_id, fatal=False)
 
         return {
-            **json_ld,
+            **traverse_obj(metadata, ('head', 'data', {
+                'title': ('title', {str}),
+                'description': ('misc', 'description', {str}),
+                'duration': ('duration', {int}),  # duration in JSON is incorrect if string
+                'timestamp': ('releasedate', {unified_timestamp}),
+                'view_count': ('misc', 'playcount', {int_or_none}),
+                'thumbnail': ('image', {url_or_none}),
+                'tags': ('misc', 'keywords', ..., {str}),
+            })),
             'id': video_id,
             'formats': formats,
             'subtitles': {
@@ -71,10 +104,10 @@ def _real_extract(self, url):
 
 
 class HungamaSongIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|un\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
-        'md5': 'd4a6a05a394ad0453a9bea3ca00e6024',
+        'md5': '964f46828e8b250aa35e5fdcfdcac367',
         'info_dict': {
             'id': '2931166',
             'ext': 'mp3',
@@ -83,8 +116,22 @@ class HungamaSongIE(InfoExtractor):
             'artist': 'Lucky Ali',
             'album': None,
             'release_year': 2000,
-        }
+            'thumbnail': 'https://stat2.hungama.ind.in/assets/images/default_images/da-200x200.png',
-    }
+        },
+    }, {
+        'url': 'https://un.hungama.com/song/tum-kya-mile-from-rocky-aur-rani-kii-prem-kahaani/103553672',
+        'md5': '964f46828e8b250aa35e5fdcfdcac367',
+        'info_dict': {
+            'id': '103553672',
+            'ext': 'mp3',
+            'title': 'md5:5ebeb1e10771b634ce5f700ce68ae5f4',
+            'track': 'Tum Kya Mile (From "Rocky Aur Rani Kii Prem Kahaani")',
+            'artist': 'Pritam Chakraborty, Arijit Singh, Shreya Ghoshal, Amitabh Bhattacharya',
+            'album': 'Tum Kya Mile (From "Rocky Aur Rani Kii Prem Kahaani")',
+            'release_year': 2023,
+            'thumbnail': 'https://images.hungama.com/c/1/7c2/c7b/103553671/103553671_200x200.jpg',
+        },
+    }]
 
     def _real_extract(self, url):
         audio_id = self._match_id(url)
@@ -122,8 +169,8 @@ def _real_extract(self, url):
         }
 
 
-class HungamaAlbumPlaylistIE(InfoExtractor):
+class HungamaAlbumPlaylistIE(HungamaBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?hungama\.com/(?:playlists|album)/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|un\.)?hungama\.com/(?P<path>playlists|album)/[^/]+/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.hungama.com/album/bhuj-the-pride-of-india/69481490/',
         'playlist_mincount': 7,
@@ -132,16 +179,24 @@ class HungamaAlbumPlaylistIE(InfoExtractor):
         },
     }, {
         'url': 'https://www.hungama.com/playlists/hindi-jan-to-june-2021/123063/',
-        'playlist_mincount': 50,
+        'playlist_mincount': 33,
         'info_dict': {
             'id': '123063',
         },
+    }, {
+        'url': 'https://un.hungama.com/album/what-jhumka-%3F-from-rocky-aur-rani-kii-prem-kahaani/103891805/',
+        'playlist_mincount': 1,
+        'info_dict': {
+            'id': '103891805',
+        },
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        playlist_id, path = self._match_valid_url(url).group('id', 'path')
-        webpage = self._download_webpage(url, video_id)
+        data = self._call_api(remove_end(path, 's'), playlist_id, fatal=True)
-        ptrn = r'<meta[^>]+?property=[\"\']?music:song:url[\"\']?[^>]+?content=[\"\']?([^\"\']+)'
+
-        items = re.findall(ptrn, webpage)
+        def entries():
-        entries = [self.url_result(item, ie=HungamaSongIE.ie_key()) for item in items]
+            for song_url in traverse_obj(data, ('body', 'rows', ..., 'data', 'misc', 'share', {url_or_none})):
-        return self.playlist_result(entries, video_id)
+                yield self.url_result(song_url, HungamaSongIE)
+
+        return self.playlist_result(entries(), playlist_id)