Merge 14bf10c6488b74cc31ef6ae0e1b239a1505ba47a into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* 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

@@ -562,6 +562,7 @@ from .kaltura import KalturaIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
+from .keep2share import Keep2ShareIE
 from .keezmovies import KeezMoviesIE
 from .ketnet import KetnetIE
 from .khanacademy import (

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/keep2share.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+import json
+import re
+from .common import (
+    InfoExtractor,
+    RegexNotFoundError,
+)
+from ..utils import (
+    clean_html,
+    compat_str,
+    js_to_json,
+    urljoin,
+    try_get,
+)
+
+
+class Keep2ShareIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:k2s\.cc|keep2share\.cc|keep2share\.com)/file/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://k2s.cc/file/d6f565bcb9581/Big_Buck%20Bunny%20Trailer.mp4',
+        'md5': '0dbce91e7d1efc506d1461439eb8a4c0',
+        'info_dict': {
+            'id': 'd6f565bcb9581',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny Trailer.mp4',
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'filesize': 4447915,
+            'duration': 33.019,
+        },
+    }]
+
+    def _get_app_secret(self, video_id):
+        """ retrieve REACT_APP_API_CLIENT_SECRET """
+
+        if getattr(self, '_app_secret', None) is not None:
+            return self._app_secret
+
+        url = 'https://k2s.cc/file/' + video_id
+        webpage = self._download_webpage(url, video_id)
+        scripts = re.finditer(r'<script\s+src="(?P<src>/static/[^"]*)"', webpage)
+        for mobj in scripts:
+            src = urljoin(url, clean_html(mobj.group('src')))
+            script = self._download_webpage(src, video_id)
+            secret = self._search_regex(
+                r'REACT_APP_API_CLIENT_SECRET:\s*(?P<secret>%(string)s)' % {
+                    'string': r'"(?:[^"]|\\")*"' + '|' + r"'(?:[^']|\\')*'",
+                }, script, 'app secret', group='secret', default=None)
+            if secret is not None:
+                self._app_secret = self._parse_json(secret, video_id,
+                                                    transform_source=js_to_json)
+                return self._app_secret
+
+        raise RegexNotFoundError('Unable to extract app secret')
+
+    def _get_access_token(self, video_id):
+        """ retrieve access_token """
+
+        if getattr(self, '_access_token', None) is not None:
+            return self._access_token
+
+        data = {
+            'grant_type': 'client_credentials',
+            'client_id': 'k2s_web_app',
+            'client_secret': self._get_app_secret(video_id),
+        }
+        data = json.dumps(data, separators=(',', ':')).encode('utf-8')
+        headers = {'Content-Type': 'application/json'}
+        tokens = self._download_json('https://api.k2s.cc/v1/auth/token',
+                                     video_id, data=data, headers=headers)
+        self._access_token = tokens['access_token']
+
+        return self._access_token
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        headers = {'Cookie': 'accessToken=' + self._get_access_token(url)}
+        info = self._download_json('https://api.k2s.cc/v1/files/' + video_id,
+                                   video_id, headers=headers)
+
+        return {
+            'id': video_id,
+            'title': info.get('name', 'keep2share-file'),
+            'thumbnail': try_get(info, lambda x: x['videoPreview']['cover'], compat_str),
+            'duration': try_get(info, lambda x: x['videoInfo']['duration'], (int, float)),
+            'formats': [{
+                'url': info['videoPreview']['video'],
+                'ext': 'mp4',
+                'filesize': try_get(info, lambda x: x['size'], int),
+                'width': try_get(info, lambda x: x['videoInfo']['resolution']['width'], int),
+                'height': try_get(info, lambda x: x['videoInfo']['resolution']['height'], int),
+            }],
+        }

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/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: