Merge branch 'yt-dlp:master' into playsuisse-handle-locale-parameters-from-urls

2026-09-04 10:11:38 +03:00 · 2025-03-03 23:44:42 +01:00
parent 4c8e7e7b6d 42b7440963
commit f4e4ab0c55
15 changed files with 420 additions and 65 deletions
@@ -2224,6 +2224,7 @@ from .tvplay import (
    TVPlayIE,
 )
 from .tvplayer import TVPlayerIE
+from .tvw import TvwIE
 from .tweakers import TweakersIE
 from .twentymin import TwentyMinutenIE
 from .twentythreevideo import TwentyThreeVideoIE
@@ -3,7 +3,7 @@ from ..utils import int_or_none


 class CultureUnpluggedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
+    _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/(?:documentary/watch-online/)?play/(?P<id>\d+)(?:/(?P<display_id>[^/#?]+))?'
    _TESTS = [{
        'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
        'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
@@ -12,12 +12,25 @@ class CultureUnpluggedIE(InfoExtractor):
            'display_id': 'The-Next--Best-West',
            'ext': 'mp4',
            'title': 'The Next, Best West',
-            'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
+            'description': 'md5:770033a3b7c2946a3bcfb7f1c6fb7045',
            'thumbnail': r're:^https?://.*\.jpg$',
-            'creator': 'Coldstream Creative',
+            'creators': ['Coldstream Creative'],
            'duration': 2203,
            'view_count': int,
        },
+    }, {
+        'url': 'https://www.cultureunplugged.com/play/2833/Koi-Sunta-Hai--Journeys-with-Kumar---Kabir--Someone-is-Listening-',
+        'md5': 'dc2014bc470dfccba389a1c934fa29fa',
+        'info_dict': {
+            'id': '2833',
+            'display_id': 'Koi-Sunta-Hai--Journeys-with-Kumar---Kabir--Someone-is-Listening-',
+            'ext': 'mp4',
+            'title': 'Koi Sunta Hai: Journeys with Kumar & Kabir (Someone is Listening)',
+            'description': 'md5:fa94ac934927c98660362b8285b2cda5',
+            'view_count': int,
+            'thumbnail': 'https://s3.amazonaws.com/cdn.cultureunplugged.com/thumbnails_16_9/lg/2833.jpg',
+            'creators': ['Srishti'],
+        },
    }, {
        'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
        'only_matching': True,
@@ -100,7 +100,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):

 class DailymotionIE(DailymotionBaseInfoExtractor):
    _VALID_URL = r'''(?ix)
-                    https?://
+                    (?:https?:)?//
                    (?:
                        dai\.ly/|
                        (?:
@@ -116,7 +116,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                    (?P<id>[^/?_&#]+)(?:[\w-]*\?playlist=(?P<playlist_id>x[0-9a-z]+))?
    '''
    IE_NAME = 'dailymotion'
-    _EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
+    _EMBED_REGEX = [rf'(?ix)<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)["\'](?P<url>{_VALID_URL[5:]})']
    _TESTS = [{
        'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
        'md5': '074b95bdee76b9e3654137aee9c79dfe',
@@ -308,6 +308,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
            'description': 'Que lindura',
            'tags': [],
        },
+    }, {
+        # //geo.dailymotion.com/player/xysxq.html?video=k2Y4Mjp7krAF9iCuINM
+        'url': 'https://lcp.fr/programmes/avant-la-catastrophe-la-naissance-de-la-dictature-nazie-1933-1936-346819',
+        'info_dict': {
+            'id': 'k2Y4Mjp7krAF9iCuINM',
+            'ext': 'mp4',
+            'title': 'Avant la catastrophe la naissance de la dictature nazie 1933 -1936',
+            'description': 'md5:7b620d5e26edbe45f27bbddc1c0257c1',
+            'uploader': 'LCP Assemblée nationale',
+            'uploader_id': 'xbz33d',
+            'view_count': int,
+            'like_count': int,
+            'age_limit': 0,
+            'duration': 3220,
+            'thumbnail': 'https://s1.dmcdn.net/v/Xvumk1djJBUZfjj2a/x1080',
+            'tags': [],
+            'timestamp': 1739919947,
+            'upload_date': '20250218',
+        },
    }]
    _GEO_BYPASS = False
    _COMMON_MEDIA_FIELDS = '''description
@@ -1,35 +1,36 @@
 from .common import InfoExtractor
-from ..utils import parse_age_limit, parse_duration, traverse_obj
+from ..utils import parse_age_limit, parse_duration, url_or_none
+from ..utils.traversal import traverse_obj


 class MagellanTVIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?magellantv\.com/(?:watch|video)/(?P<id>[\w-]+)'
    _TESTS = [{
-        'url': 'https://www.magellantv.com/watch/my-dads-on-death-row?type=v',
+        'url': 'https://www.magellantv.com/watch/incas-the-new-story?type=v',
        'info_dict': {
-            'id': 'my-dads-on-death-row',
+            'id': 'incas-the-new-story',
            'ext': 'mp4',
-            'title': 'My Dad\'s On Death Row',
-            'description': 'md5:33ba23b9f0651fc4537ed19b1d5b0d7a',
-            'duration': 3780.0,
+            'title': 'Incas: The New Story',
+            'description': 'md5:936c7f6d711c02dfb9db22a067b586fe',
            'age_limit': 14,
-            'tags': ['Justice', 'Reality', 'United States', 'True Crime'],
+            'duration': 3060.0,
+            'tags': ['Ancient History', 'Archaeology', 'Anthropology'],
        },
        'params': {'skip_download': 'm3u8'},
    }, {
-        'url': 'https://www.magellantv.com/video/james-bulger-the-new-revelations',
+        'url': 'https://www.magellantv.com/video/tortured-to-death-murdering-the-nanny',
        'info_dict': {
-            'id': 'james-bulger-the-new-revelations',
+            'id': 'tortured-to-death-murdering-the-nanny',
            'ext': 'mp4',
-            'title': 'James Bulger: The New Revelations',
-            'description': 'md5:7b97922038bad1d0fe8d0470d8a189f2',
+            'title': 'Tortured to Death: Murdering the Nanny',
+            'description': 'md5:d87033594fa218af2b1a8b49f52511e5',
+            'age_limit': 14,
            'duration': 2640.0,
-            'age_limit': 0,
-            'tags': ['Investigation', 'True Crime', 'Justice', 'Europe'],
+            'tags': ['True Crime', 'Murder'],
        },
        'params': {'skip_download': 'm3u8'},
    }, {
-        'url': 'https://www.magellantv.com/watch/celebration-nation',
+        'url': 'https://www.magellantv.com/watch/celebration-nation?type=s',
        'info_dict': {
            'id': 'celebration-nation',
            'ext': 'mp4',
@@ -43,10 +44,19 @@ class MagellanTVIE(InfoExtractor):
    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
-        data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
-            'props', 'pageProps', 'reactContext',
-            (('video', 'detail'), ('series', 'currentEpisode')), {dict}), get_all=False)
-        formats, subtitles = self._extract_m3u8_formats_and_subtitles(data['jwpVideoUrl'], video_id)
+        context = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['reactContext']
+        data = traverse_obj(context, ((('video', 'detail'), ('series', 'currentEpisode')), {dict}, any))
+
+        formats, subtitles = [], {}
+        for m3u8_url in set(traverse_obj(data, ((('manifests', ..., 'hls'), 'jwp_video_url'), {url_or_none}))):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if not formats and (error := traverse_obj(context, ('errorDetailPage', 'errorMessage', {str}))):
+            if 'available in your country' in error:
+                self.raise_geo_restricted(msg=error)
+            self.raise_no_formats(f'{self.IE_NAME} said: {error}', expected=True)

        return {
            'id': video_id,
@@ -0,0 +1,117 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import clean_html, remove_end, unified_timestamp, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class TvwIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'https://tvw.org/video/billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211/',
+        'md5': '9ceb94fe2bb7fd726f74f16356825703',
+        'info_dict': {
+            'id': '2024011211',
+            'ext': 'mp4',
+            'title': 'Billy Frank Jr. Statue Maquette Unveiling Ceremony',
+            'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+            'description': 'md5:58a8150017d985b4f377e11ee8f6f36e',
+            'timestamp': 1704902400,
+            'upload_date': '20240110',
+            'location': 'Legislative Building',
+            'display_id': 'billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211',
+            'categories': ['General Interest'],
+        },
+    }, {
+        'url': 'https://tvw.org/video/ebeys-landing-state-park-2024081007/',
+        'md5': '71e87dae3deafd65d75ff3137b9a32fc',
+        'info_dict': {
+            'id': '2024081007',
+            'ext': 'mp4',
+            'title': 'Ebey\'s Landing State Park',
+            'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+            'description': 'md5:50c5bd73bde32fa6286a008dbc853386',
+            'timestamp': 1724310900,
+            'upload_date': '20240822',
+            'location': 'Ebey’s Landing State Park',
+            'display_id': 'ebeys-landing-state-park-2024081007',
+            'categories': ['Washington State Parks'],
+        },
+    }, {
+        'url': 'https://tvw.org/video/home-warranties-workgroup-2',
+        'md5': 'f678789bf94d07da89809f213cf37150',
+        'info_dict': {
+            'id': '1999121000',
+            'ext': 'mp4',
+            'title': 'Home Warranties Workgroup',
+            'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+            'description': 'md5:861396cc523c9641d0dce690bc5c35f3',
+            'timestamp': 946389600,
+            'upload_date': '19991228',
+            'display_id': 'home-warranties-workgroup-2',
+            'categories': ['Legislative'],
+        },
+    }, {
+        'url': 'https://tvw.org/video/washington-to-washington-a-new-space-race-2022041111/?eventID=2022041111',
+        'md5': '6f5551090b351aba10c0d08a881b4f30',
+        'info_dict': {
+            'id': '2022041111',
+            'ext': 'mp4',
+            'title': 'Washington to Washington - A New Space Race',
+            'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+            'description': 'md5:f65a24eec56107afbcebb3aa5cd26341',
+            'timestamp': 1650394800,
+            'upload_date': '20220419',
+            'location': 'Hayner Media Center',
+            'display_id': 'washington-to-washington-a-new-space-race-2022041111',
+            'categories': ['Washington to Washington', 'General Interest'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        client_id = self._html_search_meta('clientID', webpage, fatal=True)
+        video_id = self._html_search_meta('eventID', webpage, fatal=True)
+
+        video_data = self._download_json(
+            'https://api.v3.invintus.com/v2/Event/getDetailed', video_id,
+            headers={
+                'authorization': 'embedder',
+                'wsc-api-key': '7WhiEBzijpritypp8bqcU7pfU9uicDR',
+            },
+            data=json.dumps({
+                'clientID': client_id,
+                'eventID': video_id,
+                'showStreams': True,
+            }).encode())['data']
+
+        formats = []
+        subtitles = {}
+        for stream_url in traverse_obj(video_data, ('streamingURIs', ..., {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if caption_url := traverse_obj(video_data, ('captionPath', {url_or_none})):
+            subtitles.setdefault('en', []).append({'url': caption_url, 'ext': 'vtt'})
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'title': remove_end(self._og_search_title(webpage, default=None), ' - TVW'),
+            'description': self._og_search_description(webpage, default=None),
+            **traverse_obj(video_data, {
+                'title': ('title', {str}),
+                'description': ('description', {clean_html}),
+                'categories': ('categories', ..., {str}),
+                'thumbnail': ('videoThumbnail', {url_or_none}),
+                'timestamp': ('startDateTime', {unified_timestamp}),
+                'location': ('locationName', {str}),
+                'is_live': ('eventStatus', {lambda x: x == 'live'}),
+            }),
+        }
@@ -4266,6 +4266,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            } for range_start in range(0, f['filesize'], CHUNK_SIZE))

        for fmt in streaming_formats:
+            client_name = fmt[STREAMING_DATA_CLIENT_NAME]
            if fmt.get('targetDurationSec'):
                continue

@@ -4310,6 +4311,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
                encrypted_sig = try_get(sc, lambda x: x['s'][0])
                if not all((sc, fmt_url, player_url, encrypted_sig)):
+                    self.report_warning(
+                        f'Some {client_name} client formats have been skipped as they are missing a url. '
+                        f'{"Your account" if self.is_authenticated else "The current session"} may have '
+                        f'the SSAP (server-side ads) experiment which may be interfering with yt-dlp. '
+                        f'Please see  https://github.com/yt-dlp/yt-dlp/issues/12482  for more details.',
+                        only_once=True)
                    continue
                try:
                    fmt_url += '&{}={}'.format(
@@ -4356,7 +4363,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                self.report_warning(
                    f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)

-            client_name = fmt[STREAMING_DATA_CLIENT_NAME]
            po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)

            if po_token: