Merge 090fb58de7 into f2a4983df7

Closes #11526
Authored by: jshumphrey

yt_dlp/extractor/_extractors.py

@@ -75,6 +75,12 @@ from .aenetworks import (
     HistoryTopicIE,
 )
 from .aeonco import AeonCoIE
+from .afl import (
+    AFCVideoIE,
+    AFLPodcastIE,
+    AFLVideoIE,
+    CarltonFCVideoIE,
+)
 from .afreecatv import (
     AfreecaTVCatchStoryIE,
     AfreecaTVIE,
@@ -1433,6 +1439,7 @@ from .oftv import (
 )
 from .oktoberfesttv import OktoberfestTVIE
 from .olympics import OlympicsReplayIE
+from .omnyfm import OmnyFMShowIE
 from .on24 import On24IE
 from .ondemandkorea import (
     OnDemandKoreaIE,

yt_dlp/extractor/afl.py

@@ -0,0 +1,206 @@
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from .omnyfm import OmnyFMShowIE
+from ..utils import (
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_attribute,
+    get_element_html_by_id,
+    smuggle_url,
+    str_or_none,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class AFLVideoIE(InfoExtractor):
+    IE_NAME = 'afl:video'
+    _VALID_URL = r'https?://(?:www\.)?(?:afl|lions)\.com\.au/(?:aflw/)?video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.afl.com.au/aflw/video/1217670/the-w-show-aflws-line-in-the-sand-moment-bonnies-bold-bid',
+        'md5': '7000431c2bd3f96eddb5f63273aea83e',
+        'info_dict': {
+            'id': '6361825702112',
+            'ext': 'mp4',
+            'description': 'md5:d1fee2ae8e3ecf486c1f0f7aa19e724b',
+            'upload_date': '20240911',
+            'duration': 1523.28,
+            'tags': 'count:0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': "The W Show: AFLW's 'line in the sand' moment, Bonnie's bold bid",
+            'uploader_id': '6057984922001',
+            'timestamp': 1726038522,
+        },
+    }, {
+        'url': 'https://www.lions.com.au/video/1655451/team-song-brisbane?videoId=1655451&modal=true&type=video&publishFrom=1726318577001',
+        'md5': '47e8c67e317b48a69787c8bc39c3c591',
+        'info_dict': {
+            'id': '6361958949112',
+            'ext': 'mp4',
+            'description': 'md5:c0fb37fcad9ec0f49ac54eb8d76641bd',
+            'upload_date': '20240914',
+            'duration': 41.0,
+            'tags': 'count:0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'Team Song: Brisbane',
+            'uploader_id': '6057984922001',
+            'timestamp': 1726318788,
+        },
+    }, {
+        'url': 'https://www.afl.com.au/video/1217264/bulldogs-season-review-gold-plated-list-going-to-waste-duos-frightening-future?videoId=1217264&modal=true&type=video&publishFrom=1725998400001',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.afl.com.au/video/1210885/wafl-showreel-ef-hamish-davis-highlights?videoId=1210885&modal=true&type=video&publishFrom=1725171238001',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lions.com.au/video/1657551/svarc-weve-built-up-really-well?videoId=1657551&modal=true&type=video&publishFrom=1726545600001',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        element = get_element_by_class('inline-player__player-container', webpage)
+        attrs = traverse_obj(extract_attributes(element), {
+            'account_id': ('data-account', {str_or_none}),
+            'player_id': ('data-player', {lambda x: f'{x}_default'}, {str_or_none}),
+            'video_id': ('data-video-id', {str_or_none}),
+        })
+        account_id = attrs.get('account_id')
+        player_id = attrs.get('player_id')
+        video_id = attrs.get('video_id')
+
+        video_url = f'https://players.brightcove.net/{account_id}/{player_id}/index.html?videoId={video_id}'
+        video_url = smuggle_url(video_url, {'referrer': url})
+        return self.url_result(video_url, BrightcoveNewIE)
+
+
+class AFLPodcastIE(InfoExtractor):
+    IE_NAME = 'afl:podcast'
+    _VALID_URL = r'https?://(?:www\.)?(?:afl|carltonfc)\.com\.au/(?:aflw/)?podcasts/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.afl.com.au/podcasts/between-us',
+        'md5': '7000431c2bd3f96eddb5f63273aea83e',
+        'info_dict': {
+            'id': 'e0ab8454-f818-483f-bed1-b156002c021f',
+            'title': 'Between Us',
+        },
+        'playlist_mincount': 7,
+    }, {
+        'url': 'https://www.carltonfc.com.au/podcasts/walk-a-mile',
+        'md5': '',
+        'info_dict': {
+            'id': '6dbb9b23-7f00-49d4-b44e-aec2017651dc',
+            'title': 'Walk a Mile in Their Shoes',
+        },
+        'playlist_mincount': 3,
+    }, {
+        'url': 'https://www.afl.com.au/podcasts/afl-daily',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.carltonfc.com.au/podcasts/summer-sessions',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        element = get_element_by_class('omny-embed', webpage)
+        podcast_url = traverse_obj(extract_attributes(element), ('src', {url_or_none}))
+        return self.url_result(podcast_url, OmnyFMShowIE)
+
+
+class AFCVideoIE(InfoExtractor):
+    IE_NAME = 'afc:video'
+    _VALID_URL = r'https?://(?:www\.)?afc\.com\.au/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.afc.com.au/video/1657583/girls-academies-be-a-pro?videoId=1657583&modal=true&type=video&publishFrom=1726548621001',
+        'md5': 'd0f4ec78b5a693d95c975ae3aeed8b2d',
+        'info_dict': {
+            'id': '6362048189112',
+            'ext': 'mp4',
+            'description': 'md5:5c43f1affe1a0cd8e2192358a49de9cc',
+            'upload_date': '20240917',
+            'duration': 50.48,
+            'tags': 'count:0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'Girls Academies – ‘Be a Pro’',
+            'uploader_id': '6057984922001',
+            'timestamp': 1726548942,
+        },
+    }, {
+        'url': 'https://www.afc.com.au/video/1586280/se10ep16-the-crows-show?videoId=1586280&modal=true&type=video&publishFrom=1719639000001&tagNames=crowsshowepisode',
+        'md5': 'bd9984d62f87b4c2299bb62ffc869189',
+        'info_dict': {
+            'id': '6355746458112',
+            'ext': 'mp4',
+            'description': 'md5:4470d107af6e749a8225fd558b98b50b',
+            'upload_date': '20240627',
+            'duration': 1193.64,
+            'tags': 'count:0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'SE10EP16 - The Crows Show',
+            'uploader_id': '6057984922001',
+            'timestamp': 1719466601,
+        },
+    }, {
+        'url': 'https://www.afc.com.au/video/1634706/jones-radiology-injury-update-r24?videoId=1634706&modal=true&type=video&publishFrom=1724126172001',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_attrs = extract_attributes(get_element_html_by_id('VideoModal', webpage))
+        player_id = video_attrs['data-player-id'] + '_default'
+        account_id = video_attrs['data-account-id']
+
+        video_element_html = get_element_html_by_attribute('data-id', display_id, webpage, tag='a')
+        if video_element_html:
+            video_data = self._parse_json(extract_attributes(video_element_html)['data-ui-args'], display_id)
+        else:
+            video_data = self._download_json(f'https://aflapi.afc.com.au/content/aflc-adel/video/en/{display_id}', display_id)
+        video_id = video_data['mediaId']
+
+        video_url = f'https://players.brightcove.net/{account_id}/{player_id}/index.html?videoId={video_id}'
+        video_url = smuggle_url(video_url, {'referrer': url})
+        return self.url_result(video_url, BrightcoveNewIE)
+
+
+class CarltonFCVideoIE(InfoExtractor):
+    IE_NAME = 'carltonfc:video'
+    _VALID_URL = r'https?://(?:www\.)?carltonfc\.com\.au/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.carltonfc.com.au/video/1657596/cripps-on-taking-carlton-to-the-next-level?videoId=1657596&modal=true&type=video&publishFrom=1726555500001',
+        'md5': '67916ea9dd28376365184bb3869a1548',
+        'info_dict': {
+            'id': '6362046715112',
+            'ext': 'mp4',
+            'description': 'md5:02eeff6576fcd7c33e18e34b1b0ebf56',
+            'upload_date': '20240917',
+            'duration': 90.44,
+            'tags': 'count:0',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'Cripps on taking Carlton to the next level',
+            'uploader_id': '6057984922001',
+            'timestamp': 1726550622,
+        },
+    }, {
+        'url': 'https://www.carltonfc.com.au/video/1658173/the-rundown-impact-of-fans?videoId=1658173&modal=true&type=video&publishFrom=1726630922001',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_attrs = extract_attributes(get_element_html_by_id('VideoModal', webpage))
+        player_id = video_attrs['data-player-id'] + '_default'
+        account_id = video_attrs['data-account-id']
+
+        video_element_html = get_element_html_by_attribute('data-id', display_id, webpage)
+        video_data = self._search_json(r'data-ui-args\s*=\s*["\']', video_element_html, 'video-id', display_id)
+        video_id = video_data['mediaId']
+
+        video_url = f'https://players.brightcove.net/{account_id}/{player_id}/index.html?videoId={video_id}'
+        video_url = smuggle_url(video_url, {'referrer': url})
+        return self.url_result(video_url, BrightcoveNewIE)

yt_dlp/extractor/archiveorg.py

@@ -205,6 +205,26 @@ class ArchiveOrgIE(InfoExtractor):
                 },
             },
         ],
+    }, {
+        # The reviewbody is None for one of the reviews; just need to extract data without crashing
+        'url': 'https://archive.org/details/gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
+        'info_dict': {
+            'id': 'gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
+            'ext': 'mp3',
+            'title': 'Stuck Inside of Mobile with the Memphis Blues Again',
+            'creators': ['Grateful Dead'],
+            'duration': 338.31,
+            'track': 'Stuck Inside of Mobile with the Memphis Blues Again',
+            'description': 'md5:764348a470b986f1217ffd38d6ac7b72',
+            'display_id': 'gd95-04-02d1t04.shn',
+            'location': 'Pyramid Arena',
+            'uploader': 'jon@archive.org',
+            'album': '1995-04-02 - Pyramid Arena',
+            'upload_date': '20040519',
+            'track_number': 4,
+            'release_date': '19950402',
+            'timestamp': 1084927901,
+        },
     }]
 
     @staticmethod
@@ -335,7 +355,7 @@ class ArchiveOrgIE(InfoExtractor):
                 info['comments'].append({
                     'id': review.get('review_id'),
                     'author': review.get('reviewer'),
-                    'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
+                    'text': join_nonempty('reviewtitle', 'reviewbody', from_dict=review, delim='\n\n'),
                     'timestamp': unified_timestamp(review.get('createdate')),
                     'parent': 'root'})
 

yt_dlp/extractor/chaturbate.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://www.chaturbate.com/siswet19/',
         'info_dict': {
@@ -29,15 +29,24 @@ class ChaturbateIE(InfoExtractor):
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/siswet19/',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.global/siswet19/',
+        'only_matching': True,
     }]
 
     _ROOM_OFFLINE = 'Room is currently offline'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, tld = self._match_valid_url(url).group('id', 'tld')
 
         webpage = self._download_webpage(
-            f'https://chaturbate.com/{video_id}/', video_id,
+            f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers())
 
         found_m3u8_urls = []

yt_dlp/extractor/facebook.py

@@ -563,13 +563,13 @@ class FacebookIE(InfoExtractor):
                 return extract_video_data(try_get(
                     js_data, lambda x: x['jsmods']['instances'], list) or [])
 
-        def extract_dash_manifest(video, formats):
+        def extract_dash_manifest(vid_data, formats, mpd_url=None):
             dash_manifest = traverse_obj(
-                video, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', expected_type=str)
+                vid_data, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', 'manifest_xml', expected_type=str)
             if dash_manifest:
                 formats.extend(self._parse_mpd_formats(
                     compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
-                    mpd_url=url_or_none(video.get('dash_manifest_url'))))
+                    mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
 
         def process_formats(info):
             # Downloads with browser's User-Agent are rate limited. Working around
@@ -619,9 +619,12 @@ class FacebookIE(InfoExtractor):
                         video = video['creation_story']
                         video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner'))
                         video.update(reel_info)
-                    fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
+
                     formats = []
                     q = qualities(['sd', 'hd'])
+
+                    # Legacy formats extraction
+                    fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
                     for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'),
                                            ('playable_url_dash', ''), ('browser_native_hd_url', 'hd'),
                                            ('browser_native_sd_url', 'sd')):
@@ -629,7 +632,7 @@ class FacebookIE(InfoExtractor):
                         if not playable_url:
                             continue
                         if determine_ext(playable_url) == 'mpd':
-                            formats.extend(self._extract_mpd_formats(playable_url, video_id))
+                            formats.extend(self._extract_mpd_formats(playable_url, video_id, fatal=False))
                         else:
                             formats.append({
                                 'format_id': format_id,
@@ -638,6 +641,28 @@ class FacebookIE(InfoExtractor):
                                 'url': playable_url,
                             })
                     extract_dash_manifest(fmt_data, formats)
+
+                    # New videoDeliveryResponse formats extraction
+                    fmt_data = traverse_obj(video, ('videoDeliveryResponseFragment', 'videoDeliveryResponseResult'))
+                    mpd_urls = traverse_obj(fmt_data, ('dash_manifest_urls', ..., 'manifest_url', {url_or_none}))
+                    dash_manifests = traverse_obj(fmt_data, ('dash_manifests', lambda _, v: v['manifest_xml']))
+                    for idx, dash_manifest in enumerate(dash_manifests):
+                        extract_dash_manifest(dash_manifest, formats, mpd_url=traverse_obj(mpd_urls, idx))
+                    if not dash_manifests:
+                        # Only extract from MPD URLs if the manifests are not already provided
+                        for mpd_url in mpd_urls:
+                            formats.extend(self._extract_mpd_formats(mpd_url, video_id, fatal=False))
+                    for prog_fmt in traverse_obj(fmt_data, ('progressive_urls', lambda _, v: v['progressive_url'])):
+                        format_id = traverse_obj(prog_fmt, ('metadata', 'quality', {str.lower}))
+                        formats.append({
+                            'format_id': format_id,
+                            # sd, hd formats w/o resolution info should be deprioritized below DASH
+                            'quality': q(format_id) - 3,
+                            'url': prog_fmt['progressive_url'],
+                        })
+                    for m3u8_url in traverse_obj(fmt_data, ('hls_playlist_urls', ..., 'hls_playlist_url', {url_or_none})):
+                        formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False, m3u8_id='hls'))
+
                     if not formats:
                         # Do not append false positive entry w/o any formats
                         return

yt_dlp/extractor/omnyfm.py

@@ -0,0 +1,68 @@
+import functools
+import math
+
+from .common import InfoExtractor
+from ..utils import (
+    InAdvancePagedList,
+    clean_html,
+    float_or_none,
+    int_or_none,
+    str_or_none,
+    traverse_obj,
+    unified_strdate,
+    url_or_none,
+)
+
+
+class OmnyFMShowIE(InfoExtractor):
+    IE_NAME = 'omnyfm:show'
+    _VALID_URL = r'https?://omny\.fm/shows/(?P<id>[^/]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://omny\.fm/shows/.+?)\1']
+    _PAGE_SIZE = 10
+    _TESTS = [{
+        'url': 'https://omny.fm/shows/league-leaders',
+        'info_dict': {
+            'id': 'bbe146d4-9bee-4763-b785-ad830009a23f',
+            'title': 'League Leaders with Nicole Livingstone',
+        },
+        'playlist_mincount': 15,
+    }, {
+        'url': 'https://omny.fm/shows/afl-daily',
+        'only_matching': True,
+    }]
+
+    def _fetch_page(self, org_id, playlist_id, page):
+        return self._download_json(f'https://api.omny.fm/orgs/{org_id}/programs/{playlist_id}/clips?cursor={page}&pageSize={self._PAGE_SIZE}', f'{playlist_id}_{page}')
+
+    def _entries(self, org_id, playlist_id, first_page_data, page):
+        data = first_page_data if not page else self._fetch_page(org_id, playlist_id, page + 1)
+        for clip in data.get('Clips', {}):
+            yield traverse_obj(clip, {
+                'id': ('Id', {str_or_none}),
+                'title': ('Title', {str_or_none}),
+                'description': ('Description', {clean_html}),
+                'thumbnail': (('ImageUrl', 'ArtworkUrl'), {url_or_none}, any),
+                'duration': ('DurationSeconds', {float_or_none}),
+                'url': ('AudioUrl', {url_or_none}),
+                'season_number': ('Season', {int_or_none}),
+                'episode_number': ('Episode', {int_or_none}),
+                'timestamp': ('PublishedUtc', {unified_strdate}, {int_or_none}),
+                'filesize': ('PublishedAudioSizeInBytes', {int}),
+            })
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        page_url = 'https://omny.fm/shows/' + display_id
+        webpage = self._download_webpage(page_url, display_id)
+
+        data = self._search_nextjs_data(webpage, display_id)
+        org_id = traverse_obj(data, ('props', 'pageProps', 'program', 'OrganizationId', {str_or_none}))
+        playlist_id = traverse_obj(data, ('props', 'pageProps', 'program', 'Id', {str_or_none}))
+        playlist_count = traverse_obj(data, ('props', 'pageProps', 'program', 'DefaultPlaylist', 'NumberOfClips', {int_or_none}))
+        title = traverse_obj(data, ('props', 'pageProps', 'program', 'Name', {str_or_none}))
+        first_page_data = traverse_obj(data, ('props', 'pageProps', 'clips', {dict}))
+        total_pages = math.ceil(playlist_count / self._PAGE_SIZE)
+
+        return self.playlist_result(InAdvancePagedList(
+            functools.partial(self._entries, org_id, playlist_id, first_page_data),
+            total_pages, self._PAGE_SIZE), playlist_id, title)