Merge 8934a232fb1e2491932fb627df3b4329f8318317 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/douyin.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    try_get,
+    orderedSet
+)
+
+
+class DouyinVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.douyin.com/video/6989098563519270181',
+        'md5': '99c5667992b8a8d46c145907f677c92b',
+        'info_dict': {
+            'id': '6989098563519270181',
+            'url': 'https://aweme.snssdk.com/aweme/v1/playwm/?video_id=v0300fg10000c3v47dbc77u9fvb20tbg&ratio=720p&line=0',
+            'title': '杨集#我的家乡 ',
+            'uploader': '🌹永恒的爱🌹',
+            'uploader_id': '104081949894',
+            'timestamp': 1627276320000.0,
+            'ext': 'mp4'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        iteminfo = self._download_json('https://www.douyin.com/web/api/v2/aweme/iteminfo',
+                                       video_id, query={'item_ids': video_id}) or {}
+        status_code = iteminfo.get('status_code', 'status_code missing')
+        if status_code:
+            raise ExtractorError('%s (%s)' % (iteminfo.get('status_msg', 'status_msg missing'), status_code), video_id=video_id)
+
+        item_list = iteminfo.get('item_list')
+        if not item_list:
+            raise ExtractorError('The video you want to download does not exist any more',
+                                 video_id=video_id, expected=True)
+        item = item_list[0]
+
+        return {
+            'id': video_id,
+            'title': item['desc'],
+            'url': item['video']['play_addr']['url_list'][0],
+            'uploader': try_get(item, lambda x: x['author']['nickname'], compat_str),
+            'uploader_id': try_get(item, lambda x: x['author']['uid'], compat_str),
+            'duration': int_or_none(item.get('duration') or try_get(item, lambda x: x['video']['duration'], int), scale=1000),
+            'timestamp': int_or_none(item.get('create_time'), invscale=1000),
+            'width': try_get(item, lambda x: x['video']['width'], int),
+            'height': try_get(item, lambda x: x['video']['height'], int),
+            'vbr': try_get(item, lambda x: x['video']['bit_rate'], int),
+            'ext': 'mp4'
+        }
+
+
+class DouyinUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?douyin\.com/user/(?P<id>[a-zA-Z0-9_\-]+)'
+    _TEST = {
+        'url': 'https://www.douyin.com/user/MS4wLjABAAAAP5Q7Z-SwleIzAACYIu-LrwGbEZzN2dc5PT3hGNSTkSM',
+        'info_dict': {
+            'id': 'MS4wLjABAAAAP5Q7Z-SwleIzAACYIu-LrwGbEZzN2dc5PT3hGNSTkSM'
+        },
+        'playlist_mincount': 31
+    }
+
+    def _real_extract(self, url):
+        sec_uid = self._match_id(url)
+
+        has_more = True
+        max_cursor = ''
+
+        entries = []
+        while has_more:
+            post = self._download_json('https://www.douyin.com/web/api/v2/aweme/post',
+                                       sec_uid, query={'sec_uid': sec_uid, 'max_cursor': max_cursor, 'count': 50}) or {}
+            status_code = post.get('status_code', 'status_code missing')
+            if status_code:
+                raise ExtractorError('%s (%s)' % (post.get('status_msg', 'status_msg missing'), status_code), video_id=sec_uid)
+
+            aweme_list = post.get('aweme_list')
+            if aweme_list is None:
+                raise ExtractorError('JSON response does not contain aweme_list', video_id=sec_uid)
+
+            entries.extend([self.url_result('https://www.douyin.com/video/%s' % aweme_id,
+                                            ie=DouyinVideoIE.ie_key(), video_id=aweme_id)
+                            for aweme_id in filter(None,
+                                                   (aweme.get('aweme_id') for aweme in aweme_list
+                                                    if isinstance(aweme, dict)))])
+
+            has_more = post.get('has_more')
+            max_cursor = post.get('max_cursor')
+
+        return self.playlist_result(orderedSet(entries), sec_uid)

youtube_dl/extractor/extractors.py

@@ -305,6 +305,10 @@ from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
 from .dotsub import DotsubIE
+from .douyin import (
+    DouyinVideoIE,
+    DouyinUserIE
+)
 from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,

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/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: