Merge 206796d6b37d0af9e8e3699a30d3b1301b7e2c06 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

@@ -669,6 +669,10 @@ from .markiza import (
     MarkizaPageIE,
 )
 from .massengeschmacktv import MassengeschmackTVIE
+from .masterclass import (
+    MasterClassIE,
+    MasterClassCourseIE,
+)
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .medaltv import MedalTVIE

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/masterclass.py

@@ -0,0 +1,137 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    url_or_none,
+    parse_duration,
+    unified_strdate
+)
+
+
+class MasterClassBaseIE(InfoExtractor):
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
+    BRIGHTCOVE_ACCOUNT_ID = '5344802162001'
+
+    def _call_api(self, course_id, csrf, video_id):
+        headers = {"Content-Type": "application/vnd.api+json",
+                   "X-CSRF-Token": csrf,
+                   "Accept": "application/vnd.api+json"}
+
+        return self._download_json('https://www.masterclass.com/jsonapi/v1/courses/%s?include=instructors%%2Cchapters.annotations' % course_id,
+                                   video_id, headers=headers, fatal=True)
+
+
+class MasterClassIE(MasterClassBaseIE):
+    IE_NAME = 'masterclass'
+    _VALID_URL = r'https?://(?:www\.)?masterclass\.com/classes/(?P<course>[a-z0-9\-]+)/chapters/(?P<id>[a-z0-9\-]+)'
+    _TESTS = [{
+        'url': 'https://www.masterclass.com/classes/gordon-ramsay-teaches-cooking-restaurant-recipes-at-home/chapters/pomme-puree',
+        'md5': '5fbe8736e761c2cc61ed0ee2841e8f47',
+        'info_dict': {
+            'id': '5834174464001',
+            'ext': 'mp4',
+            'title': 'GR2_Trailer_v9a_Brightcove_v2',
+            'timestamp': 1536792485,
+            'upload_date': '20180912',
+            'uploader_id': '5344802162001',
+            'duration': 93.44
+        }
+    }]
+
+    def _real_extract(self, url):
+        course_id, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, video_id)
+
+        match_free = re.search(r'\"embedUrl\":\"(.+?)\"}</script>', webpage)
+        if match_free:  # match free trailer video
+            clip_url = match_free.groups()[0]
+            return self.url_result(clip_url)
+
+        csrf = self._html_search_regex(r'name=\"csrf-token\" content=\"(.+?)(?=\" \/)', webpage, 'csrf', fatal=True)
+        meta = self._call_api(course_id, csrf, video_id)
+
+        chapter = meta.get('data').get('attributes').get('title')
+        release_date = unified_strdate(meta.get('data').get('attributes').get('available_at'))
+        for json_data in meta['included']:
+            json_data = json_data['attributes']
+            if (json_data['slug'] == video_id):
+                brightcove_id = json_data['brightcove_video_id']
+                brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % (self.BRIGHTCOVE_ACCOUNT_ID, brightcove_id)
+
+                title = json_data['title']
+                chapter_number = int_or_none(json_data.get('number'))
+                duration = int_or_none(parse_duration(json_data.get('duration')))
+                description = json_data.get('abstract')
+                thumbnail = url_or_none(json_data.get('video_thumb_url'))
+
+                return ({
+                    '_type': 'url_transparent',
+                    'url': brightcove_url,
+                    'ie_key': BrightcoveNewIE.ie_key(),
+                    'id': video_id,
+                    'title': title,
+                    'chapter': chapter,
+                    'chapter_number': chapter_number,
+                    'release_date': release_date,
+                    'duration': duration,
+                    'description': description,
+                    'thumbnail': thumbnail
+                })
+
+
+class MasterClassCourseIE(MasterClassBaseIE):
+    IE_NAME = "masterclass:course"
+    _VALID_URL = r'https?://(?:www\.)?masterclass\.com/classes/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://www.masterclass.com/classes/alicia-keys-teaches-songwriting-and-producing',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.masterclass.com/classes/matthew-walker-teaches-the-science-of-better-sleep',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+        webpage = self._download_webpage(url, course_id, fatal=True)
+
+        csrf = self._html_search_regex(r'name=\"csrf-token\" content=\"(.+?)(?=\" \/)', webpage, 'csrf', fatal=True)
+        meta = self._call_api(course_id, csrf, course_id)
+
+        chapter = meta.get('data').get('attributes').get('title')
+        release_date = unified_strdate(meta.get('data').get('attributes').get('available_at'))
+        entries = []
+        for json_data in meta['included']:
+            if (json_data['type'] == 'chapter'):
+                json_data = json_data['attributes']
+                brightcove_id = json_data['brightcove_video_id']
+                brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % (self.BRIGHTCOVE_ACCOUNT_ID, brightcove_id)
+
+                title = json_data['title']
+                video_id = json_data.get('slug')
+                chapter_number = int_or_none(json_data.get('number'))
+                duration = int_or_none(parse_duration(json_data.get('duration')))
+                description = json_data.get('abstract')
+                thumbnail = url_or_none(json_data.get('video_thumb_url'))
+
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': brightcove_url,
+                    'ie_key': BrightcoveNewIE.ie_key(),
+                    'id': video_id,
+                    'title': title,
+                    'chapter': chapter,
+                    'chapter_number': chapter_number,
+                    'release_date': release_date,
+                    'duration': duration,
+                    'description': description,
+                    'thumbnail': thumbnail
+                })
+
+        entries = sorted(entries, key=lambda i: int(i.get("chapter_number")))
+        title = meta['data']['attributes']['title']
+        description = meta.get('data').get('attributes').get('overview')
+        return self.playlist_result(entries, course_id, title, description)

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: