Merge 11fc1e228a into 0153b387e5

* [VidLii] Add HD support  (yt-dlp backport-ish)

* Also fix a bug with the view count

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>

test/helper.py

@@ -5,9 +5,9 @@ import hashlib
 import json
 import os.path
 import re
-import types
 import ssl
 import sys
+import types
 import unittest
 
 import youtube_dl.extractor
@@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
             op, _, expected_num = expected.partition(':')
             expected_num = int(expected_num)
             if op == 'mincount':
-                assert_func = assertGreaterEqual
+                assert_func = self.assertGreaterEqual
                 msg_tmpl = 'Expected %d items in field %s, but only got %d'
             elif op == 'maxcount':
-                assert_func = assertLessEqual
+                assert_func = self.assertLessEqual
                 msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
             elif op == 'count':
-                assert_func = assertEqual
+                assert_func = self.assertEqual
                 msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
             else:
                 assert False
             assert_func(
-                self, len(got), expected_num,
+                len(got), expected_num,
                 msg_tmpl % (expected_num, field, len(got)))
             return
         self.assertEqual(
@@ -262,27 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
             self.assertTrue(m, msg)
 
 
-def assertGreaterEqual(self, got, expected, msg=None):
-    if not (got >= expected):
-        if msg is None:
-            msg = '%r not greater than or equal to %r' % (got, expected)
-        self.assertTrue(got >= expected, msg)
-
-
-def assertLessEqual(self, got, expected, msg=None):
-    if not (got <= expected):
-        if msg is None:
-            msg = '%r not less than or equal to %r' % (got, expected)
-        self.assertTrue(got <= expected, msg)
-
-
-def assertEqual(self, got, expected, msg=None):
-    if not (got == expected):
-        if msg is None:
-            msg = '%r not equal to %r' % (got, expected)
-        self.assertTrue(got == expected, msg)
-
-
 def expect_warnings(ydl, warnings_re):
     real_warning = ydl.report_warning
 

test/test_download.py

@@ -9,8 +9,6 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
-    assertGreaterEqual,
-    assertLessEqual,
     expect_warnings,
     get_params,
     gettestcases,
@@ -36,12 +34,20 @@ from youtube_dl.utils import (
     ExtractorError,
     error_to_compat_str,
     format_bytes,
+    IDENTITY,
+    preferredencoding,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
 
 RETRIES = 3
 
+# Some unittest APIs require actual str
+if not isinstance('TEST', str):
+    _encode_str = lambda s: s.encode(preferredencoding())
+else:
+    _encode_str = IDENTITY
+
 
 class YoutubeDL(youtube_dl.YoutubeDL):
     def __init__(self, *args, **kwargs):
@@ -102,7 +108,7 @@ def generator(test_case, tname):
 
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
-            self.skipTest(reason)
+            self.skipTest(_encode_str(reason))
 
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
@@ -187,16 +193,14 @@ def generator(test_case, tname):
                 expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 
             if 'playlist_mincount' in test_case:
-                assertGreaterEqual(
-                    self,
+                self.assertGreaterEqual(
                     len(res_dict['entries']),
                     test_case['playlist_mincount'],
                     'Expected at least %d in playlist %s, but got only %d' % (
                         test_case['playlist_mincount'], test_case['url'],
                         len(res_dict['entries'])))
             if 'playlist_maxcount' in test_case:
-                assertLessEqual(
-                    self,
+                self.assertLessEqual(
                     len(res_dict['entries']),
                     test_case['playlist_maxcount'],
                     'Expected at most %d in playlist %s, but got %d' % (
@@ -243,8 +247,8 @@ def generator(test_case, tname):
                         if params.get('test'):
                             expected_minsize = max(expected_minsize, 10000)
                         got_fsize = os.path.getsize(tc_filename)
-                        assertGreaterEqual(
-                            self, got_fsize, expected_minsize,
+                        self.assertGreaterEqual(
+                            got_fsize, expected_minsize,
                             'Expected %s to be at least %s, but it\'s only %s ' %
                             (tc_filename, format_bytes(expected_minsize),
                                 format_bytes(got_fsize)))

youtube_dl/YoutubeDL.py

@@ -1039,8 +1039,8 @@ class YoutubeDL(object):
         elif result_type in ('playlist', 'multi_video'):
             # Protect from infinite recursion due to recursively nested playlists
             # (see https://github.com/ytdl-org/youtube-dl/issues/27833)
-            webpage_url = ie_result['webpage_url']
-            if webpage_url in self._playlist_urls:
+            webpage_url = ie_result.get('webpage_url')  # not all pl/mv have this
+            if webpage_url and webpage_url in self._playlist_urls:
                 self.to_screen(
                     '[download] Skipping already downloaded playlist: %s'
                     % ie_result.get('title') or ie_result.get('id'))
@@ -1048,6 +1048,10 @@ class YoutubeDL(object):
 
             self._playlist_level += 1
             self._playlist_urls.add(webpage_url)
+            new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
+            if new_result:
+                new_result.update(ie_result)
+                ie_result = new_result
             try:
                 return self.__process_playlist(ie_result, download)
             finally:
@@ -1593,6 +1597,28 @@ class YoutubeDL(object):
         self.cookiejar.add_cookie_header(pr)
         return pr.get_header('Cookie')
 
+    def _fill_common_fields(self, info_dict, final=True):
+
+        for ts_key, date_key in (
+                ('timestamp', 'upload_date'),
+                ('release_timestamp', 'release_date'),
+        ):
+            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
+                # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+                # see http://bugs.python.org/issue1646728)
+                try:
+                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
+                    info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
+                except (ValueError, OverflowError, OSError):
+                    pass
+
+        # Auto generate title fields corresponding to the *_number fields when missing
+        # in order to always have clean titles. This is very common for TV series.
+        if final:
+            for field in ('chapter', 'season', 'episode'):
+                if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
+                    info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
+
     def process_video_result(self, info_dict, download=True):
         assert info_dict.get('_type', 'video') == 'video'
 
@@ -1660,24 +1686,7 @@ class YoutubeDL(object):
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
-        for ts_key, date_key in (
-                ('timestamp', 'upload_date'),
-                ('release_timestamp', 'release_date'),
-        ):
-            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
-                # Working around out-of-range timestamp values (e.g. negative ones on Windows,
-                # see http://bugs.python.org/issue1646728)
-                try:
-                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
-                    info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
-                except (ValueError, OverflowError, OSError):
-                    pass
-
-        # Auto generate title fields corresponding to the *_number fields when missing
-        # in order to always have clean titles. This is very common for TV series.
-        for field in ('chapter', 'season', 'episode'):
-            if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
-                info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
+        self._fill_common_fields(info_dict)
 
         for cc_kind in ('subtitles', 'automatic_captions'):
             cc = info_dict.get(cc_kind)

youtube_dl/extractor/cbs.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .theplatform import ThePlatformFeedIE
@@ -8,6 +9,7 @@ from ..utils import (
     xpath_element,
     xpath_text,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -25,68 +27,27 @@ class CBSBaseIE(ThePlatformFeedIE):
                     })
         return subtitles
 
-
-class CBSIE(CBSBaseIE):
-    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
-
-    _TESTS = [{
-        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
-        'info_dict': {
-            'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
-            'ext': 'mp4',
-            'title': 'Connect Chat feat. Garth Brooks',
-            'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
-            'duration': 1495,
-            'timestamp': 1385585425,
-            'upload_date': '20131127',
-            'uploader': 'CBSI-NEW',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        '_skip': 'Blocked outside the US',
-    }, {
-        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
-        'only_matching': True,
-    }, {
-        '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,
-    }]
-
-    def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
-        items_data = self._download_xml(
-            'http://can.cbs.com/thunder/player/videoPlayerService.php',
-            content_id, query={'partner': site, 'contentId': content_id})
-        video_data = xpath_element(items_data, './/item')
-        title = xpath_text(video_data, 'videoTitle', 'title', True)
+    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 = 'http://link.theplatform.com/s/' + tp_path
+        info = self._extract_theplatform_metadata(tp_path, content_id)
 
-        asset_types = []
-        subtitles = {}
-        formats = []
+        formats, subtitles = [], {}
         last_e = None
-        for item in items_data.findall('.//item'):
-            asset_type = xpath_text(item, 'assetType')
-            if not asset_type or asset_type in asset_types or 'HLS_FPS' in asset_type or 'DASH_CENC' in asset_type:
-                continue
-            asset_types.append(asset_type)
-            query = {
-                'mbr': 'true',
-                'assetTypes': asset_type,
-            }
-            if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
-                query['formats'] = 'MPEG4,M3U'
-            elif asset_type in ('RTMP', 'WIFI', '3G'):
-                query['formats'] = 'MPEG4,FLV'
+        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
@@ -96,20 +57,117 @@ class CBSIE(CBSBaseIE):
             raise last_e
         self._sort_formats(formats)
 
-        info = self._extract_theplatform_metadata(tp_path, content_id)
-        info.update({
+        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\.com/(?:shows|movies)/(?:video|[^/]+/video|[^/]+)/|
+                colbertlateshow\.com/(?:video|podcasts)/)
+        )(?P<id>[\w-]+)'''
+
+    # All tests are blocked outside US
+    _TESTS = [{
+        'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/',
+        'info_dict': {
+            'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R',
+            'ext': 'mp4',
+            'title': 'Tough As Nails - Dreams Never Die',
+            'description': 'md5:a3535a62531cdd52b0364248a2c1ae33',
+            'duration': 2588,
+            'timestamp': 1639015200,
+            'upload_date': '20211209',
+            'uploader': 'CBSI-NEW',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
+        'info_dict': {
+            'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1',
+            'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)',
+            'timestamp': 1647488100,
+            'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439',
+            'uploader': 'CBSI-NEW',
+            'upload_date': '20220317',
+        },
+        'params': {
+            'ignore_no_formats_error': True,
+            'skip_download': True,
+        },
+        'expected_warnings': [
+            'This content expired on', 'No video formats found', 'Requested format is not available'],
+    }, {
+        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
+        'only_matching': True,
+    }, {
+        # old format
+        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        'only_matching': True,
+    }]
+
+    def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
+        items_data = self._download_xml(
+            'https://can.cbs.com/thunder/player/videoPlayerService.php',
+            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')
+
+        asset_types = {}
+        has_drm = False
+        for item in items_data.findall('.//item'):
+            asset_type = xpath_text(item, 'assetType')
+            query = {
+                'mbr': 'true',
+                'assetTypes': asset_type,
+            }
+            if not asset_type:
+                # fallback for content_ids that videoPlayerService doesn't return anything for
+                asset_type = 'fallback'
+                query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
+                del query['assetTypes']
+            if asset_type in asset_types:
+                continue
+            elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
+                if 'DASH_CENC' in asset_type:
+                    has_drm = True
+                continue
+            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'
+            asset_types[asset_type] = query
+
+        if not asset_types and has_drm:
+            raise ExtractorError('Only DRM formats found', video_id=content_id, expected=True)
+
+        return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
             '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'),
-            'formats': formats,
-            'subtitles': subtitles,
+            'thumbnail': url_or_none(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)

youtube_dl/extractor/extractors.py

@@ -898,21 +898,13 @@ from .ooyala import (
 )
 from .ora import OraTVIE
 from .orf import (
-    ORFTVthekIE,
-    ORFFM4IE,
+    ORFONIE,
+    ORFONLiveIE,
     ORFFM4StoryIE,
-    ORFOE1IE,
-    ORFOE3IE,
-    ORFNOEIE,
-    ORFWIEIE,
-    ORFBGLIE,
-    ORFOOEIE,
-    ORFSTMIE,
-    ORFKTNIE,
-    ORFSBGIE,
-    ORFTIRIE,
-    ORFVBGIE,
     ORFIPTVIE,
+    ORFPodcastIE,
+    ORFRadioIE,
+    ORFRadioCollectionIE,
 )
 from .outsidetv import OutsideTVIE
 from .packtpub import (
@@ -925,6 +917,10 @@ from .palcomp3 import (
     PalcoMP3VideoIE,
 )
 from .pandoratv import PandoraTVIE
+from .paramountplus import (
+     ParamountPlusIE,
+     ParamountPlusSeriesIE,
+)
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE

youtube_dl/extractor/mixcloud.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools
@@ -10,7 +11,7 @@ from ..compat import (
     compat_ord,
     compat_str,
     compat_urllib_parse_unquote,
-    compat_zip
+    compat_zip as zip,
 )
 from ..utils import (
     int_or_none,
@@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
     def _call_api(self, object_type, object_fields, display_id, username, slug=None):
         lookup_key = object_type + 'Lookup'
         return self._download_json(
-            'https://www.mixcloud.com/graphql', display_id, query={
+            'https://app.mixcloud.com/graphql', display_id, query={
                 'query': '''{
   %s(lookup: {username: "%s"%s}) {
     %s
@@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
             'ext': 'm4a',
             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
-            'uploader': 'Daniel Holbach',
+            'uploader': 'dholbach',  # was: 'Daniel Holbach',
             'uploader_id': 'dholbach',
             'thumbnail': r're:https?://.*\.jpg',
             'view_count': int,
@@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
             'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
             'ext': 'mp3',
             'title': 'Caribou 7 inch Vinyl Mix & Chat',
-            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+            'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
             'uploader': 'Gilles Peterson Worldwide',
             'uploader_id': 'gillespeterson',
             'thumbnail': 're:https?://.*',
@@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
             'timestamp': 1422987057,
             'upload_date': '20150203',
         },
+        'params': {
+            'skip_download': '404 not found',
+        },
+    }, {
+        'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
+        'info_dict': {
+            'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
+            'ext': 'm4a',
+            'title': 'Carnival Música Popular Brasileira Mix',
+            'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
+            'timestamp': 1454347174,
+            'upload_date': '20160201',
+            'uploader': 'Gilles Peterson Worldwide',
+            'uploader_id': 'gillespeterson',
+            'thumbnail': 're:https?://.*',
+            'view_count': int,
+        },
     }, {
         'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
         'only_matching': True,
@@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
         """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
         return ''.join([
             compat_chr(compat_ord(ch) ^ compat_ord(k))
-            for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
+            for ch, k in zip(ciphertext, itertools.cycle(key))])
 
     def _real_extract(self, url):
-        username, slug = re.match(self._VALID_URL, url).groups()
+        username, slug = self._match_valid_url(url).groups()
         username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
         track_id = '%s_%s' % (username, slug)
 

youtube_dl/extractor/paramountplus.py

@@ -0,0 +1,159 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import itertools
+
+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|movies)/(?:video|[^/]+/video|[^/]+)/
+        )(?P<id>[\w-]+))'''
+
+    # All tests are blocked outside US
+    _TESTS = [{
+        'url': 'https://www.paramountplus.com/shows/video/Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k/',
+        'info_dict': {
+            'id': 'Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k',
+            'ext': 'mp4',
+            'title': 'CatDog - Climb Every CatDog/The Canine Mutiny',
+            'description': 'md5:7ac835000645a69933df226940e3c859',
+            'duration': 1426,
+            'timestamp': 920264400,
+            'upload_date': '19990301',
+            'uploader': 'CBSI-NEW',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        'url': 'https://www.paramountplus.com/shows/video/6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd/',
+        '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/video/vM2vm0kE6vsS2U41VhMRKTOVHyQAr6pC/',
+        'info_dict': {
+            'id': 'vM2vm0kE6vsS2U41VhMRKTOVHyQAr6pC',
+            'ext': 'mp4',
+            'title': 'Daddy\'s Home',
+            'upload_date': '20151225',
+            'description': 'md5:9a6300c504d5e12000e8707f20c54745',
+            '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/video/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/the-real-world/video/mOVeHeL9ub9yWdyzSZFYz8Uj4ZBkVzQg/the-real-world-reunion/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/shows/video/mOVeHeL9ub9yWdyzSZFYz8Uj4ZBkVzQg/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/movies/video/W0VyStQqUnqKzJkrpSAIARuCc9YuYGNy/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/movies/paw-patrol-the-movie/W0VyStQqUnqKzJkrpSAIARuCc9YuYGNy/',
+        'only_matching': True,
+    }, {
+        # old format
+        'url': 'https://www.paramountplus.com/shows/catdog/video/Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k/catdog-climb-every-catdog-the-canine-mutiny/',
+        '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='}, headers=self.geo_verification_headers())
+
+        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': 45,
+        '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',
+        }
+    }]
+
+    def _entries(self, show_name):
+        for page in itertools.count():
+            show_json = self._download_json(
+                'https://www.paramountplus.com/shows/{0}/xhr/episodes/page/{1}/size/50/xs/0/season/0'.format(show_name, page), show_name)
+            if not show_json.get('success'):
+                return
+            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)

youtube_dl/extractor/theplatform.py

@@ -20,6 +20,7 @@ from ..utils import (
     float_or_none,
     int_or_none,
     sanitized_Request,
+    try_get,
     unsmuggle_url,
     update_url_query,
     xpath_with_ns,
@@ -34,6 +35,15 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns})
 class ThePlatformBaseIE(OnceIE):
     _TP_TLD = 'com'
 
+    @classmethod
+    def _match_valid_url(cls, url):
+        # This does not use has/getattr intentionally - we want to know whether
+        # we have cached the regexp for *this* class, whereas getattr would also
+        # match the superclass
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        return cls._VALID_URL_RE.match(url)
+
     def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
         meta = self._download_xml(
             smil_url, video_id, note=note, query={'format': 'SMIL'},
@@ -238,7 +248,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
             'countries': smuggled_data.get('geo_countries'),
         })
 
-        mobj = re.match(self._VALID_URL, url)
+        mobj = self._match_valid_url(url)
         provider_id = mobj.group('provider_id')
         video_id = mobj.group('id')
 
@@ -338,6 +348,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
             'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'],
             'uploader': 'NBCU-NEWS',
         },
+        'expected_warnings': ('Empty metadata',),
     }, {
         'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byGuid=nn_netcast_180306.Copy.01',
         'only_matching': True,
@@ -345,7 +356,11 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
 
     def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None):
         real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
-        entry = self._download_json(real_url, video_id)['entries'][0]
+        entry = self._download_json(real_url, video_id)
+        entry = try_get(entry, lambda x: x['entries'][0], dict)
+        if not entry:
+            self.report_warning('Empty metadata', video_id)
+            return None
         main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else entry.get('plmedia$publicUrl')
 
         formats = []
@@ -404,7 +419,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
         return ret
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        mobj = self._match_valid_url(url)
 
         video_id = mobj.group('id')
         provider_id = mobj.group('provider_id')

youtube_dl/extractor/vidlii.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+
 from ..utils import (
     float_or_none,
     get_element_by_id,
@@ -11,6 +12,7 @@ from ..utils import (
     strip_or_none,
     unified_strdate,
     urljoin,
+    str_to_int,
 )
 
 
@@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
             'categories': ['News & Politics'],
             'tags': ['Vidlii', 'Jan', 'Videogames'],
         }
+    }, {
+        # HD
+        'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
+        'md5': '450e7da379c884788c3a4fa02a3ce1a4',
+        'info_dict': {
+            'id': '2Ng8Abj2Fkl',
+            'ext': 'mp4',
+            'title': 'test',
+            'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
+            'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
+            'uploader': 'VidLii',
+            'uploader_url': 'https://www.vidlii.com/user/VidLii',
+            'upload_date': '20200927',
+            'duration': 5,
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Film & Animation'],
+            'tags': list,
+        },
     }, {
         'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
         'only_matching': True,
@@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
         webpage = self._download_webpage(
             'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
 
-        video_url = self._search_regex(
-            r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
-            'video url', group='url')
+        formats = []
 
-        title = self._search_regex(
+        def add_format(format_url, height=None):
+            height = int(self._search_regex(r'(\d+)\.mp4',
+                         format_url, 'height', default=360))
+
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+            })
+
+        sources = re.findall(
+            r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
+            webpage)
+
+        formats = []
+        if len(sources) > 1:
+            add_format(sources[1][1])
+            self._check_formats(formats, video_id)
+        if len(sources) > 0:
+            add_format(sources[0][1])
+
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
             (r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
             'title')
 
@@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
             default=None) or self._search_regex(
             r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
 
-        view_count = int_or_none(self._search_regex(
-            (r'<strong>(\d+)</strong> views',
-             r'Views\s*:\s*<strong>(\d+)</strong>'),
+        view_count = str_to_int(self._html_search_regex(
+            (r'<strong>([\d,.]+)</strong> views',
+             r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
             webpage, 'view count', fatal=False))
 
         comment_count = int_or_none(self._search_regex(
@@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,