[paramountplus] Separate extractor and fix some titles (#652)

Co-authored-by: shirt, pukkandan

yt_dlp/extractor/cbs.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
 from .theplatform import ThePlatformFeedIE
 from ..utils import (
     ExtractorError,
@@ -9,6 +8,7 @@
     xpath_element,
     xpath_text,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -26,16 +26,62 @@ def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
                     })
         return subtitles
 
+    def _extract_common_video_info(self, content_id, asset_types, mpx_acc, extra_info):
+        tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
+        tp_release_url = f'https://link.theplatform.com/s/{tp_path}'
+        info = self._extract_theplatform_metadata(tp_path, content_id)
+
+        formats, subtitles = [], {}
+        last_e = None
+        for asset_type, query in asset_types.items():
+            try:
+                tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                    update_url_query(tp_release_url, query), content_id,
+                    'Downloading %s SMIL data' % asset_type)
+            except ExtractorError as e:
+                last_e = e
+                if asset_type != 'fallback':
+                    continue
+                query['formats'] = ''  # blank query to check if expired
+                try:
+                    tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                        update_url_query(tp_release_url, query), content_id,
+                        'Downloading %s SMIL data, trying again with another format' % asset_type)
+                except ExtractorError as e:
+                    last_e = e
+                    continue
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        if last_e and not formats:
+            self.raise_no_formats(last_e, True, content_id)
+        self._sort_formats(formats)
+
+        extra_info.update({
+            'id': content_id,
+            'formats': formats,
+            'subtitles': subtitles,
+        })
+        info.update({k: v for k, v in extra_info.items() if v is not None})
+        return info
+
+    def _extract_video_info(self, *args, **kwargs):
+        # Extract assets + metadata and call _extract_common_video_info
+        raise NotImplementedError('This method must be implemented by subclasses')
+
+    def _real_extract(self, url):
+        return self._extract_video_info(self._match_id(url))
+
 
 class CBSIE(CBSBaseIE):
     _VALID_URL = r'''(?x)
         (?:
             cbs:|
             https?://(?:www\.)?(?:
-                (?:cbs|paramountplus)\.com/(?:shows/[^/]+/video|movies/[^/]+)/|
+                cbs\.com/(?:shows/[^/]+/video|movies/[^/]+)/|
                 colbertlateshow\.com/(?:video|podcasts)/)
         )(?P<id>[\w-]+)'''
 
+    # All tests are blocked outside US
     _TESTS = [{
         'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
@@ -52,39 +98,6 @@ class CBSIE(CBSBaseIE):
             # m3u8 download
             'skip_download': True,
         },
-        '_skip': 'Blocked outside the US',
-    }, {
-        'url': 'https://www.paramountplus.com/shows/catdog/video/Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k/catdog-climb-every-catdog-the-canine-mutiny/',
-        'info_dict': {
-            'id': 'Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k',
-            'ext': 'mp4',
-            'title': 'CatDog - Climb Every CatDog/The Canine Mutiny',
-            'description': 'md5:7ac835000645a69933df226940e3c859',
-            'duration': 1418,
-            'timestamp': 920264400,
-            'upload_date': '19990301',
-            'uploader': 'CBSI-NEW',
-        },
-        'params': {
-            'skip_download': 'm3u8',
-        },
-        '_skip': 'Blocked outside the US',
-    }, {
-        'url': 'https://www.paramountplus.com/shows/tooning-out-the-news/video/6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd/7-23-21-week-in-review-rep-jahana-hayes-howard-fineman-sen-michael-bennet-sheera-frenkel-cecilia-kang-/',
-        'info_dict': {
-            'id': '6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd',
-            'ext': 'mp4',
-            'title': '7/23/21 WEEK IN REVIEW (Rep. Jahana Hayes/Howard Fineman/Sen. Michael Bennet/Sheera Frenkel & Cecilia Kang)',
-            'description': 'md5:f4adcea3e8b106192022e121f1565bae',
-            'duration': 2506,
-            'timestamp': 1627063200,
-            'upload_date': '20210723',
-            'uploader': 'CBSI-NEW',
-        },
-        'params': {
-            'skip_download': 'm3u8',
-        },
-        '_skip': 'Blocked outside the US',
     }, {
         'url': 'https://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/60icOhMb9NcjbcWnF_gub9XXHdeBcNk2/the-late-show-6-23-21-christine-baranski-joy-oladokun-',
         'info_dict': {
@@ -107,12 +120,6 @@ class CBSIE(CBSBaseIE):
     }, {
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
-    }, {
-        'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.paramountplus.com/movies/million-dollar-american-princesses-meghan-and-harry/C0LpgNwXYeB8txxycdWdR9TjxpJOsdCq',
-        'only_matching': True,
     }]
 
     def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
@@ -121,14 +128,8 @@ def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
             content_id, query={'partner': site, 'contentId': content_id})
         video_data = xpath_element(items_data, './/item')
         title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
-        tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
-        tp_release_url = 'https://link.theplatform.com/s/' + tp_path
 
-        asset_types = []
+        asset_types = {}
-        subtitles = {}
-        formats = []
-        useXMLmetadata = True
-        last_e = None
         for item in items_data.findall('.//item'):
             asset_type = xpath_text(item, 'assetType')
             query = {
@@ -137,94 +138,24 @@ def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
             }
             if not asset_type:
                 # fallback for content_ids that videoPlayerService doesn't return anything for
-                useXMLmetadata = False
                 asset_type = 'fallback'
                 query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
                 del query['assetTypes']
-            elif asset_type in asset_types:
+            if asset_type in asset_types:
                 continue
             elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
                 continue
-            asset_types.append(asset_type)
             if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
                 query['formats'] = 'MPEG4,M3U'
             elif asset_type in ('RTMP', 'WIFI', '3G'):
                 query['formats'] = 'MPEG4,FLV'
-            try:
+            asset_types[asset_type] = query
-                tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                    update_url_query(tp_release_url, query), content_id,
-                    'Downloading %s SMIL data' % asset_type)
-            except ExtractorError as e:
-                last_e = e
-                if useXMLmetadata:
-                    continue
-                query['formats'] = ''  # blank query to check if expired
-                try:
-                    tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                        update_url_query(tp_release_url, query), content_id,
-                        'Downloading %s SMIL data, trying again with another format' % asset_type)
-                except ExtractorError as e:
-                    last_e = e
-                    continue
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        if last_e and not formats:
-            self.raise_no_formats(last_e, True, content_id)
-        self._sort_formats(formats)
 
-        info = self._extract_theplatform_metadata(tp_path, content_id)
+        return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
-        info.update({
+            'title': title,
-            'formats': formats,
+            'series': xpath_text(video_data, 'seriesTitle'),
-            'subtitles': subtitles,
+            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
-            'id': content_id
+            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
+            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
+            'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
         })
-        if useXMLmetadata:
-            info.update({
-                'title': title,
-                'series': xpath_text(video_data, 'seriesTitle'),
-                'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
-                'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
-                'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
-                'thumbnail': xpath_text(video_data, 'previewImageURL')
-            })
-        return info
-
-    def _real_extract(self, url):
-        content_id = self._match_id(url)
-        return self._extract_video_info(content_id)
-
-
-class ParamountPlusSeriesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?paramountplus\.com/shows/(?P<id>[a-zA-Z0-9-_]+)/?(?:[#?]|$)'
-    _TESTS = [{
-        'url': 'https://www.paramountplus.com/shows/drake-josh',
-        'playlist_mincount': 50,
-        'info_dict': {
-            'id': 'drake-josh',
-        }
-    }, {
-        'url': 'https://www.paramountplus.com/shows/hawaii_five_0/',
-        'playlist_mincount': 240,
-        'info_dict': {
-            'id': 'hawaii_five_0',
-        }
-    }, {
-        'url': 'https://www.paramountplus.com/shows/spongebob-squarepants/',
-        'playlist_mincount': 248,
-        'info_dict': {
-            'id': 'spongebob-squarepants',
-        }
-    }]
-    _API_URL = 'https://www.paramountplus.com/shows/{}/xhr/episodes/page/0/size/100000/xs/0/season/0/'
-
-    def _entries(self, show_name):
-        show_json = self._download_json(self._API_URL.format(show_name), video_id=show_name)
-        if show_json.get('success'):
-            for episode in show_json['result']['data']:
-                yield self.url_result(
-                    'https://www.paramountplus.com%s' % episode['url'],
-                    ie=CBSIE.ie_key(), video_id=episode['content_id'])
-
-    def _real_extract(self, url):
-        show_name = self._match_id(url)
-        return self.playlist_result(self._entries(show_name), playlist_id=show_name)

yt_dlp/extractor/extractors.py

@@ -202,10 +202,7 @@
     CBCWatchIE,
     CBCOlympicsIE,
 )
-from .cbs import (
+from .cbs import CBSIE
-    CBSIE,
-    ParamountPlusSeriesIE,
-)
 from .cbslocal import (
     CBSLocalIE,
     CBSLocalArticleIE,
@@ -969,6 +966,10 @@
     PalcoMP3VideoIE,
 )
 from .pandoratv import PandoraTVIE
+from .paramountplus import (
+    ParamountPlusIE,
+    ParamountPlusSeriesIE,
+)
 from .parliamentliveuk import ParliamentLiveUKIE
 from .parlview import ParlviewIE
 from .patreon import PatreonIE

yt_dlp/extractor/paramountplus.py

@@ -0,0 +1,145 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .cbs import CBSBaseIE
+from ..utils import (
+    int_or_none,
+    url_or_none,
+)
+
+
+class ParamountPlusIE(CBSBaseIE):
+    _VALID_URL = r'''(?x)
+        (?:
+            paramountplus:|
+            https?://(?:www\.)?(?:
+                paramountplus\.com/(?:shows/[^/]+/video|movies/[^/]+)/
+        )(?P<id>[\w-]+))'''
+
+    # All tests are blocked outside US
+    _TESTS = [{
+        'url': 'https://www.paramountplus.com/shows/catdog/video/Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k/catdog-climb-every-catdog-the-canine-mutiny/',
+        'info_dict': {
+            'id': 'Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k',
+            'ext': 'mp4',
+            'title': 'CatDog - Climb Every CatDog/The Canine Mutiny',
+            'description': 'md5:7ac835000645a69933df226940e3c859',
+            'duration': 1418,
+            'timestamp': 920264400,
+            'upload_date': '19990301',
+            'uploader': 'CBSI-NEW',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        'url': 'https://www.paramountplus.com/shows/tooning-out-the-news/video/6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd/7-23-21-week-in-review-rep-jahana-hayes-howard-fineman-sen-michael-bennet-sheera-frenkel-cecilia-kang-/',
+        'info_dict': {
+            'id': '6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd',
+            'ext': 'mp4',
+            'title': '7/23/21 WEEK IN REVIEW (Rep. Jahana Hayes/Howard Fineman/Sen. Michael Bennet/Sheera Frenkel & Cecilia Kang)',
+            'description': 'md5:f4adcea3e8b106192022e121f1565bae',
+            'duration': 2506,
+            'timestamp': 1627063200,
+            'upload_date': '20210723',
+            'uploader': 'CBSI-NEW',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        'url': 'https://www.paramountplus.com/movies/daddys-home/vM2vm0kE6vsS2U41VhMRKTOVHyQAr6pC',
+        'info_dict': {
+            'id': 'vM2vm0kE6vsS2U41VhMRKTOVHyQAr6pC',
+            'ext': 'mp4',
+            'title': 'Daddy\'s Home',
+            'upload_date': '20151225',
+            'description': 'md5:a0beaf24e8d3b0e81b2ee41d47c06f33',
+            'uploader': 'CBSI-NEW',
+            'timestamp': 1451030400,
+        },
+        'params': {
+            'skip_download': 'm3u8',
+            'format': 'bestvideo',
+        },
+        'expected_warnings': ['Ignoring subtitle tracks'],  # TODO: Investigate this
+    }, {
+        'url': 'https://www.paramountplus.com/movies/sonic-the-hedgehog/5EKDXPOzdVf9voUqW6oRuocyAEeJGbEc',
+        'info_dict': {
+            'id': '5EKDXPOzdVf9voUqW6oRuocyAEeJGbEc',
+            'ext': 'mp4',
+            'uploader': 'CBSI-NEW',
+            'description': 'md5:bc7b6fea84ba631ef77a9bda9f2ff911',
+            'timestamp': 1577865600,
+            'title': 'Sonic the Hedgehog',
+            'upload_date': '20200101',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+            'format': 'bestvideo',
+        },
+        'expected_warnings': ['Ignoring subtitle tracks'],
+    }, {
+        'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/movies/million-dollar-american-princesses-meghan-and-harry/C0LpgNwXYeB8txxycdWdR9TjxpJOsdCq',
+        'only_matching': True,
+    }]
+
+    def _extract_video_info(self, content_id, mpx_acc=2198311517):
+        items_data = self._download_json(
+            'https://www.paramountplus.com/apps-api/v2.0/androidtv/video/cid/%s.json' % content_id,
+            content_id, query={'locale': 'en-us', 'at': 'ABCqWNNSwhIqINWIIAG+DFzcFUvF8/vcN6cNyXFFfNzWAIvXuoVgX+fK4naOC7V8MLI='})
+
+        asset_types = {
+            item.get('assetType'): {
+                'format': 'SMIL',
+                'formats': 'MPEG4,M3U',
+            } for item in items_data['itemList']
+        }
+        item = items_data['itemList'][-1]
+        return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
+            'title': item.get('title'),
+            'series': item.get('seriesTitle'),
+            'season_number': int_or_none(item.get('seasonNum')),
+            'episode_number': int_or_none(item.get('episodeNum')),
+            'duration': int_or_none(item.get('duration')),
+            'thumbnail': url_or_none(item.get('thumbnail')),
+        })
+
+
+class ParamountPlusSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?paramountplus\.com/shows/(?P<id>[a-zA-Z0-9-_]+)/?(?:[#?]|$)'
+    _TESTS = [{
+        'url': 'https://www.paramountplus.com/shows/drake-josh',
+        'playlist_mincount': 50,
+        'info_dict': {
+            'id': 'drake-josh',
+        }
+    }, {
+        'url': 'https://www.paramountplus.com/shows/hawaii_five_0/',
+        'playlist_mincount': 240,
+        'info_dict': {
+            'id': 'hawaii_five_0',
+        }
+    }, {
+        'url': 'https://www.paramountplus.com/shows/spongebob-squarepants/',
+        'playlist_mincount': 248,
+        'info_dict': {
+            'id': 'spongebob-squarepants',
+        }
+    }]
+    _API_URL = 'https://www.paramountplus.com/shows/{}/xhr/episodes/page/0/size/100000/xs/0/season/0/'
+
+    def _entries(self, show_name):
+        show_json = self._download_json(self._API_URL.format(show_name), video_id=show_name)
+        if show_json.get('success'):
+            for episode in show_json['result']['data']:
+                yield self.url_result(
+                    'https://www.paramountplus.com%s' % episode['url'],
+                    ie=ParamountPlusIE.ie_key(), video_id=episode['content_id'])
+
+    def _real_extract(self, url):
+        show_name = self._match_id(url)
+        return self.playlist_result(self._entries(show_name), playlist_id=show_name)