Merge f2c109e5d65a633ebedf4966dcdc761faab1bdc5 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/doodstream.py

@@ -0,0 +1,89 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import string
+import time
+
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    parse_duration,
+    parse_filesize,
+    unified_strdate,
+)
+
+from .common import (
+    InfoExtractor,
+    update_url_query,
+)
+
+
+class DoodStreamIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:dood\.(?:to|la|li|pm|re|sh|ws|one|watch)|ds2play\.com)/[ed]/(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'https://dood.li/e/h7ecgw5oqn8k',
+        'md5': '90f2af170551c17fc78bee7426890054',
+        'info_dict': {
+            'id': 'h7ecgw5oqn8k',
+            'ext': 'mp4',
+            'title': 'Free-Slow-Music',
+            'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
+        }
+    }, {
+        'url': 'http://dood.watch/d/h7ecgw5oqn8k',
+        'only_matching': True,
+    }, {
+        'url': 'https://dood.li/d/wlihoael8uog',
+        'md5': '2c14444c89788cc309738c1560abe278',
+        'info_dict': {
+            'id': 'wlihoael8uog',
+            'ext': 'mp4',
+            'title': 'VID 20220319 161659',
+            'thumbnail': 'https://img.doodcdn.co/splash/rmpnhb8ckkk79cge.jpg',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        host = 'dood.li'
+        url = 'https://%s/e/%s' % (host, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta(['og:title', 'twitter:title'],
+                                       webpage, default=None) or self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', webpage, 'title', fatal=False)
+        thumb = self._html_search_meta(['og:image', 'twitter:image', 'poster'],
+                                       webpage, default=None)
+        pass_md5, token = self._search_regex(
+            r'["\']/(?P<pm>pass_md5/[\da-f-]+/(?P<tok>[\da-z]+))', webpage, 'tokens',
+            group=('pm', 'tok'))
+
+        auth_url = ('https://%s/' % host) + pass_md5
+        headers = {'Referer': url}
+        authpage = self._download_webpage(auth_url, video_id, headers=headers)
+        final_url = update_url_query(
+            authpage + ''.join((random.choice(string.ascii_letters + string.digits) for _ in range(10))),
+            {
+                'token': token,
+                'expiry': int(time.time() * 1000),
+            }
+        )
+        description = self._html_search_meta(
+            ['og:description', 'description', 'twitter:description'],
+            webpage, default=None)
+
+        def get_class_text(x):
+            return clean_html(get_element_by_class(x, webpage))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': final_url,
+            'http_headers': headers,
+            'ext': 'mp4',
+            'upload_date': unified_strdate(get_class_text('uploadate')),
+            'duration': parse_duration(get_class_text('length')),
+            'filesize_approx': parse_filesize(get_class_text('size')),
+            'description': description,
+            'thumbnail': thumb,
+        }

youtube_dl/extractor/extractors.py

@@ -309,6 +309,7 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
+from .doodstream import DoodStreamIE
 from .dplay import (
     DPlayIE,
     DiscoveryPlusIE,

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: