Merge 80bc41f018ccc14c1753abe50f350793b5f3cf01 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

@@ -1153,6 +1153,7 @@ from .sky import (
 from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
+from .snapchat import SnapchatIE
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .sonyliv import SonyLIVIE

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/snapchat.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from ..utils import unified_timestamp, parse_duration, try_get, str_or_none, ExtractorError
+from .common import InfoExtractor
+
+
+class SnapchatIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?story.snapchat\.com/o/(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://story.snapchat.com/o/W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+        'md5': 'ab1900981cadcd955aae32a526096cbd',
+        'info_dict': {
+            'id': 'W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+            'ext': 'mp4',
+            'title': 'W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+            'thumbnail': r're:https://s\.sc-cdn\.net/.+\.jpg',
+            'description': '#spotlight',
+            'timestamp': 1622914559,
+            'upload_date': '20210605',
+            'view_count': 72100,
+            'uploader_id': None
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        schema_video_object_raw = self._html_search_regex(r'<script\s[^>]*?data-react-helmet\s*=\s*"true"\s[^>]*?type\s*=\s*"application/ld\+json">(.+?)</script>',
+                                                          webpage, 'schema_video_object')
+        schema_video_object = self._parse_json(schema_video_object_raw, video_id, fatal=True)
+        try:
+            video_url = str_or_none(schema_video_object['contentUrl'])
+            if not video_url:
+                raise ValueError('video_url must be non-empty string')
+        except (TypeError, ValueError) as e:
+            raise ExtractorError('Unexpected format for schema_video_object', cause=e, video_id=video_id)
+
+        title = schema_video_object.get('name')
+        if not title:
+            title = self._generic_title(url)
+
+        views = try_get(schema_video_object.get('interactionStatistic'), lambda x: x['userInteractionCount'])
+
+        uploader_id = try_get(schema_video_object.get('creator'), lambda x: x['alternateName'])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            'thumbnail': schema_video_object.get('thumbnailUrl'),
+            'timestamp': unified_timestamp(schema_video_object.get('uploadDate')),
+            'description': schema_video_object.get('description'),
+            'duration': parse_duration(schema_video_object.get('duration')),
+            'view_count': views,
+            'uploader_id': uploader_id
+        }

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: