Merge 29e60290cfc508f7823b9191d2a2a124128e9876 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

@@ -585,6 +585,7 @@ from .kuwo import (
     KuwoCategoryIE,
     KuwoMvIE,
 )
+from .la1ere import La1ereExtractorPageIE, La1ereExtractorShowPageIE
 from .la7 import LA7IE
 from .laola1tv import (
     Laola1TvEmbedIE,

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/la1ere.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from urllib.parse import quote
+
+from .common import InfoExtractor
+
+
+class La1ereExrtractorBaseIE(InfoExtractor):
+
+    def _extract_given_title(self, webpage, title):
+
+        # get the ID
+        video_id = self._html_search_regex(r'data-id="([^"]+)"', webpage, 'id')
+
+        # request the mpd-request url
+        json_request_url = 'https://k7.ftven.fr/videos/%s?country_code=FR&w=937&h=527&screen_w=1920&screen_h=1200&player_version=5.116.1&domain=la1ere.francetvinfo.fr&device_type=desktop&browser=chrome&browser_version=126&os=linux&diffusion_mode=tunnel&gmt=-0400&capabilities=drm' % video_id
+        json_request = self._download_json(json_request_url, video_id)
+        mpd_request_url = json_request['video']['url']
+
+        # using the mpd-request url, auth to get the full mpd URL with auth params
+        auth_request_url = 'https://hdfauth.ftven.fr/esi/TA?format=json&url=%s' % quote(mpd_request_url)
+        auth_request = self._download_json(auth_request_url, video_id)
+
+        # this is the full playlist URL with auth params
+        playlist_url = auth_request['url']
+        return video_id, playlist_url
+
+
+class La1ereExtractorPageIE(La1ereExrtractorBaseIE):
+    _VALID_URL = r'https://la1ere.francetvinfo.fr/(?P<region>[^/]+)/programme-video/diffusion/(?P<page>[^\.]+).html'
+    _TEST = {
+        'skip': 'Only available in FR',
+        'url': 'https://la1ere.francetvinfo.fr/martinique/programme-video/diffusion/4774522-origine-kongo.html',
+        'info_dict': {
+            'ext': 'mp4',
+            'title': 'Origine Kongo',
+        }
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, 'la1ere')
+
+        title = self._html_search_regex(r'<h1 .*title.*>(.+?)</h1>', webpage, 'title')
+
+        video_id, playlist_url = self._extract_given_title(webpage, title)
+
+        # get the mpd playlist
+        formats = self._extract_mpd_formats(playlist_url, video_id)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+
+class La1ereExtractorShowPageIE(La1ereExrtractorBaseIE):
+    _VALID_URL = r'https://la1ere.francetvinfo.fr/(?P<region>[^/]+)/programme-video/(?P<show>[^/]+)/diffusion/(?P<page>[^\.]+).html'
+    _TEST = {
+        'skip': 'Only available in FR',
+        'url': 'https://la1ere.francetvinfo.fr/guadeloupe/programme-video/la1ere_guadeloupe_le-13h-en-guadeloupe/diffusion/5643549-emission-du-lundi-29-janvier-2024.html',
+        'info_dict': {
+            'ext': 'mp4',
+            'title': '13H en Guadeloupe - Émission du lundi 29 janvier 2024',
+        }
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, 'la1ere')
+
+        series_name = self._html_search_regex(r'<span class="m-dtv-player-title__subtitle">(.+?)</span>', webpage, 'series_name')
+        episode_name = self._html_search_regex(r'<h1 .*title.*>(.+?)</h1>', webpage, 'episode_name')
+        title = f'{series_name} - {episode_name}'
+
+        video_id, playlist_url = self._extract_given_title(webpage, title)
+
+        # get the m3u8 playlist
+        formats = self._extract_m3u8_formats(playlist_url, video_id)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+
+

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',