Merge 7ac17d4b4469d23e575c3483695a790a309b2ff8 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/extractors.py

@@ -1274,7 +1274,10 @@ from .telequebec import (
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .tennistv import TennisTVIE
-from .tenplay import TenPlayIE
+from .tenplay import (
+    TenPlayIE,
+    TenPlaySeasonIE,
+)
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .tfo import TFOIE

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/extractor/tenplay.py

@@ -1,70 +1,203 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import functools
+
 from .common import InfoExtractor
+from ..compat import (
+    compat_itertools_count,
+    compat_kwargs,
+)
 from ..utils import (
+    get_elements_by_attribute,
     HEADRequest,
-    parse_age_limit,
+    float_or_none,
-    parse_iso8601,
+    int_or_none,
-    # smuggle_url,
+    merge_dicts,
+    NO_DEFAULT,
+    T,
+    traverse_obj,
+    txt_or_none,
+    url_or_none,
+    urljoin,
 )
 
 
-class TenPlayIE(InfoExtractor):
+class TenPlayBase(InfoExtractor):
+    _GEO_COUNTRIES = ['AU']
+    _GEO_BYPASS = False
+
+    def raise_geo_restricted(self, *args, **kwargs):
+        countries = args[1] if len(args) > 1 else kwargs.get('countries', NO_DEFAULT)
+        if countries is NO_DEFAULT:
+            kwargs['countries'] = self._GEO_COUNTRIES
+            kwargs = compat_kwargs(kwargs)
+        super(TenPlayBase, self).raise_geo_restricted(*args, **kwargs)
+
+    def _download_webpage_handle(self, url_or_request, video_id, *args, **kwargs):
+        res = super(TenPlayBase, self)._download_webpage_handle(url_or_request, video_id, *args, **kwargs)
+        if res and any('Sorry, 10 play is not available in your region.' in e
+                       for e in get_elements_by_attribute('class', 'iserror__text', res[0])):
+            self.raise_geo_restricted()
+        return res
+
+
+class TenPlayIE(TenPlayBase):
     _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})'
+    _NETRC_MACHINE = '10play'
     _TESTS = [{
-        'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga',
+        'url': 'https://10play.com.au/neighbours/web-extras/season-41/heres-a-first-look-at-mischa-bartons-neighbours-debut/tpv230911hyxnz',
         'info_dict': {
-            'id': '6060533435001',
+            'id': '6336940246112',
             'ext': 'mp4',
-            'title': 'MasterChef - S1 Ep. 1',
+            'title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
-            'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c',
+            'alt_title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
-            'age_limit': 10,
+            'description': 'Neighbours Premieres Monday, September 18 At 4:30pm On 10 And 10 Play And 6:30pm On 10 Peach',
-            'timestamp': 1240828200,
+            'duration': 74,
-            'upload_date': '20090427',
+            'season': 'Season 41',
+            'season_number': 41,
+            'series': 'Neighbours',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': 'Channel 10',
+            'age_limit': 15,
+            'timestamp': 1694386800,
+            'upload_date': '20230910',
             'uploader_id': '2199827728001',
         },
         'params': {
-            # 'format': 'bestvideo',
             'skip_download': True,
-        }
+        },
+        'skip': 'Only available in Australia',
+    }, {
+        'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
+        'info_dict': {
+            'id': '9000000000091177',
+            'ext': 'mp4',
+            'title': 'Neighbours - S42 Ep. 9107',
+            'alt_title': 'Thu 05 Sep',
+            'description': 'md5:37a1f4271be34b9ee2b533426a5fbaef',
+            'duration': 1388,
+            'episode': 'Episode 9107',
+            'episode_number': 9107,
+            'season': 'Season 42',
+            'season_number': 42,
+            'series': 'Neighbours',
+            'thumbnail': r're:https://.*\.jpg',
+            'age_limit': 15,
+            'timestamp': 1725517860,
+            'upload_date': '20240905',
+            'uploader': 'Channel 10',
+            'uploader_id': '2199827728001',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Only available in Australia',
     }, {
         'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
         'only_matching': True,
     }]
-    # BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s'
+
-    _GEO_BYPASS = False
+    _AUS_AGES = {
-    _FASTLY_URL_TEMPL = 'https://10-selector.global.ssl.fastly.net/s/kYEXFC/media/%s?mbr=true&manifest=m3u&format=redirect'
+        'G': 0,
+        'PG': 15,
+        'M': 15,
+        'MA': 15,
+        'MA15+': 15,
+        'R': 18,
+        'X': 18,
+    }
 
     def _real_extract(self, url):
         content_id = self._match_id(url)
         data = self._download_json(
-            'https://10play.com.au/api/video/' + content_id, content_id)
+            'https://10play.com.au/api/v1/videos/' + content_id, content_id)
-        video = data.get('video') or {}
+
-        metadata = data.get('metaData') or {}
+        video_data = self._download_json(
-        brightcove_id = video.get('videoId') or metadata['showContentVideoId']
+            'https://vod.ten.com.au/api/videos/bcquery?command=find_videos_by_id&video_id={0}'.format(data['altId']),
-        # brightcove_url = smuggle_url(
+            content_id, 'Downloading video JSON')
-        #     self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+        m3u8_url = self._request_webpage(
-        #     {'geo_countries': ['AU']})
+            HEADRequest(video_data['items'][0]['HLSURL']),
-        m3u8_url = self._request_webpage(HEADRequest(
+            content_id, 'Checking stream URL').url
-            self._FASTLY_URL_TEMPL % brightcove_id), brightcove_id).geturl()
         if '10play-not-in-oz' in m3u8_url:
-            self.raise_geo_restricted(countries=['AU'])
+            self.raise_geo_restricted()
-        formats = self._extract_m3u8_formats(m3u8_url, brightcove_id, 'mp4')
+        # Attempt to get a higher quality stream
+        m3u8_url = m3u8_url.replace(',150,75,55,0000', ',300,150,75,55,0000')
+        formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4')
         self._sort_formats(formats)
 
-        return {
+        return merge_dicts({
-            # '_type': 'url_transparent',
+            'id': content_id,
-            # 'url': brightcove_url,
             'formats': formats,
-            'id': brightcove_id,
+            'uploader': 'Channel 10',
-            'title': video.get('title') or metadata.get('pageContentName') or metadata['showContentName'],
-            'description': video.get('description'),
-            'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')),
-            'series': metadata.get('showName'),
-            'season': metadata.get('showContentSeason'),
-            'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')),
-            'thumbnail': video.get('poster'),
             'uploader_id': '2199827728001',
-            # 'ie_key': 'BrightcoveNew',
+        }, traverse_obj(data, {
-        }
+            'subtitles': ('captionUrl', T(lambda x: None if x is None
+                                          else {'en': [{'url': x}]})),
+            'id': ('altId', T(txt_or_none)),
+            'duration': ('duration', T(float_or_none)),
+            'title': ('subtitle', T(txt_or_none)),
+            'alt_title': ('title', T(txt_or_none)),
+            'description': ('description', T(txt_or_none)),
+            'age_limit': ('classification', T(self._AUS_AGES.get)),
+            'series': ('tvShow', T(txt_or_none)),
+            'season_number': ('season', T(int_or_none)),
+            'episode_number': ('episode', T(int_or_none)),
+            'timestamp': ('published', T(int_or_none)),
+            'thumbnail': ('imageUrl', T(url_or_none)),
+        }), rev=True)
+
+
+class TenPlaySeasonIE(TenPlayBase):
+    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://10play.com.au/masterchef/episodes/season-14',
+        'info_dict': {
+            'title': 'Season 14',
+            'id': 'MjMyOTIy',
+        },
+        'playlist_mincount': 64,
+        'skip': 'Only available in Australia',
+    }, {
+        'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2022',
+        'info_dict': {
+            'title': 'Season 2022',
+            'id': 'Mjc0OTIw',
+        },
+        'playlist_mincount': 256,
+        'skip': 'Only available in Australia',
+    }]
+
+    def _entries(self, load_more_url, display_id=None):
+        skip_ids = []
+        for page in compat_itertools_count(1):
+            episodes_carousel = self._download_json(
+                load_more_url, display_id, query={'skipIds[]': skip_ids},
+                note='Fetching episodes page {0}'.format(page))
+
+            episodes_chunk = episodes_carousel['items']
+            skip_ids.extend(ep['id'] for ep in episodes_chunk)
+
+            for ep in episodes_chunk:
+                yield ep['cardLink']
+            if not episodes_carousel.get('hasMore'):
+                break
+
+    def _real_extract(self, url):
+        show, season = self._match_valid_url(url).group('show', 'season')
+        season_info = self._download_json(*(s.format(show=show, season=season) for s in (
+            'https://10play.com.au/api/shows/{show}/episodes/{season}', '{show}/{season}')
+        ))
+
+        episodes_carousel = traverse_obj(season_info, (
+            'content', 0, 'components', (
+                lambda _, v: v['title'].lower() == 'episodes',
+                (Ellipsis, T(dict)),
+            )), any) or {}
+
+        playlist_id = episodes_carousel['tpId']
+
+        return self.playlist_from_matches(
+            self._entries(urljoin(url, episodes_carousel['loadMoreUrl']), playlist_id),
+            playlist_id, traverse_obj(season_info, ('content', 0, 'title', T(txt_or_none))),
+            getter=functools.partial(urljoin, url))