Merge 853a2a22394d5f1d0b7dca7afe8fc60b6807802c 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/cnbc.py

@@ -1,71 +1,23 @@
-# coding: utf-8
 from __future__ import unicode_literals
-
 import re
-
 from .common import InfoExtractor
 from ..utils import smuggle_url
 
-
 class CNBCIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
+    _VALID_URL = 'https?://video\\.cnbc\\.com/gallery/\\?video=(?P<id>[0-9]+)'
-    _TEST = {
+    _TEST = {'url': 'http://video.cnbc.com/gallery/?video=3000503714', 'info_dict': {'id': '3000503714', 'ext': 'mp4', 'title': 'Fighting zombies is big business', 'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e', 'timestamp': 1459332000, 'upload_date': '20160330', 'uploader': 'NBCU-CNBC'}, 'params': {'skip_download': True}}
-        'url': 'http://video.cnbc.com/gallery/?video=3000503714',
-        'info_dict': {
-            'id': '3000503714',
-            'ext': 'mp4',
-            'title': 'Fighting zombies is big business',
-            'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
-            'timestamp': 1459332000,
-            'upload_date': '20160330',
-            'uploader': 'NBCU-CNBC',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
 
     def _real_extract(self, url):
+        """Auto-generated docstring for function _real_extract."""
         video_id = self._match_id(url)
-        return {
+        return {'_type': 'url_transparent', 'ie_key': 'ThePlatform', 'url': smuggle_url('http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id, {'force_smil_url': True}), 'id': video_id}
-            '_type': 'url_transparent',
-            'ie_key': 'ThePlatform',
-            'url': smuggle_url(
-                'http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id,
-                {'force_smil_url': True}),
-            'id': video_id,
-        }
-
 
 class CNBCVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\.html)'
+    _VALID_URL = 'https?://(?:www\\.)?cnbc\\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\\.html)'
-    _TEST = {
+    _TEST = {'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': {'id': '7000031301', 'ext': 'mp4', 'title': "Trump: I don't necessarily agree with raising rates", 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', 'timestamp': 1531958400, 'upload_date': '20180719', 'uploader': 'NBCU-CNBC'}, 'params': {'skip_download': True}}
-        'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
-        'info_dict': {
-            'id': '7000031301',
-            'ext': 'mp4',
-            'title': "Trump: I don't necessarily agree with raising rates",
-            'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
-            'timestamp': 1531958400,
-            'upload_date': '20180719',
-            'uploader': 'NBCU-CNBC',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }
 
     def _real_extract(self, url):
+        """Auto-generated docstring for function _real_extract."""
         path, display_id = re.match(self._VALID_URL, url).groups()
-        video_id = self._download_json(
+        video_id = self._download_json('https://webql-redesign.cnbcfm.com/graphql', display_id, query={'query': '{\n  page(path: "%s") {\n    vcpsId\n  }\n}' % path})['data']['page']['vcpsId']
-            'https://webql-redesign.cnbcfm.com/graphql', display_id, query={
+        return self.url_result('http://video.cnbc.com/gallery/?video=%d' % video_id, CNBCIE.ie_key())
-                'query': '''{
-  page(path: "%s") {
-    vcpsId
-  }
-}''' % path,
-            })['data']['page']['vcpsId']
-        return self.url_result(
-            'http://video.cnbc.com/gallery/?video=%d' % video_id,
-            CNBCIE.ie_key())

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/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',