Merge dce1e146109d60949e5660ea134fcec95441438e 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

@@ -1701,3 +1701,4 @@ from .zingmp3 import (
 )
 from .zoom import ZoomIE
 from .zype import ZypeIE
+from .wikimedia import WikimediaIE

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/wikimedia.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import re
+
+from ..utils import (
+    clean_html,
+    determine_ext,
+    get_element_by_class,
+    urljoin,
+    compat_parse_qs,
+    ExtractorError)
+
+
+class WikimediaIE(InfoExtractor):
+    IE_NAME = 'wikimedia.org'
+    _NETRC_MACHINE = 'wikimediaorg'
+    _API_BASE_URL = 'https://commons.wikimedia.org/'
+    _VALID_URL = 'https://commons.wikimedia.org/wiki/File:(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'https://commons.wikimedia.org/wiki/File:Die_Temperaturkurve_der_Erde_(ZDF,_Terra_X)_720p_HD_50FPS.webm',
+        'info_dict': {
+            'description': 'md5:7cd84f76e7081f1be033d0b155b4a460',
+            'ext': 'webm', 'id': 'Die_Temperaturkurve_der_Erde_(ZDF,_Terra_X)_720p_HD_50FPS',
+            'title': 'Die Temperaturkurve der Erde (ZDF, Terra X) 720p HD 50FPS.webm - Wikimedia Commons',
+            'license': 'md5:62907cddf705a9f7ae7076c15407a977',
+            'author': None, 'subtitles': {'de': [{'ext': 'srt',
+                                                  'url': 'https?://commons.wikimedia.org/w/api.php'}],
+                                          'en-gb': [{'ext': 'srt',
+                                                     'url': 'https?://commons.wikimedia.org/w/api.php'}],
+                                          'nl': [{'ext': 'srt',
+                                                  'url': 'https?://commons.wikimedia.org/w/api.php'}],
+                                          'en': [{'ext': 'srt',
+                                                  'url': 're:https?://commons.wikimedia.org/w/api.php'}]}}
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        ext = determine_ext(url, None)
+        if ext is None:
+            raise ExtractorError('invalid video url', expected=True)
+        webpage = self._download_webpage(url, video_id)
+        self.report_extraction(video_id)
+        video_url = self._html_search_regex('<source [^>]*src="([^"]+)"', webpage,
+                                            'video URL')
+        license = get_element_by_class('layouttemplate licensetpl mw-content-ltr', webpage)
+        license = clean_html(license)
+
+        description = get_element_by_class('description', webpage)
+        author = self._html_search_regex(r'>\s*Author\s*</td>\s*<td\b[^>]*>\s*([^<]+?)\s*</td>',
+                                         webpage, 'video author', default=None)
+        info = {'url': video_url, 'description': clean_html(description), 'ext': ext,
+                'id': video_id.replace('.' + ext, ''), 'title': self._og_search_title(webpage).replace('File:', ''),
+                'license': license, 'author': author}
+
+        subtitles = {}
+        for sub in re.findall(r'''\bsrc\s*=\s*[\"\'](\/w\/api(.*?)[\s\"])\b''', webpage):
+            sub = sub[0].replace('"', '''''')
+            sub = urljoin('https://commons.wikimedia.org', sub)
+            qs = compat_parse_qs(sub)
+            lang = qs.get('lang', [None])[-1]
+            if not lang:
+                continue
+            subtitles[lang] = [{'ext': 'srt', 'url': sub}]
+        info['subtitles'] = subtitles
+        return info