Merge 4ba906565442e36afaa9ccb3c09bcb6b4f4bebcb into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/alphaporno.py

@@ -20,10 +20,9 @@ class AlphaPornoIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Sensual striptease porn with Samantha Alexandra',
             'thumbnail': r're:https?://.*\.jpg$',
-            'timestamp': 1418694611,
+            'timestamp': 1418701811,
             'upload_date': '20141216',
             'duration': 387,
-            'filesize_approx': 54120000,
             'tbr': 1145,
             'categories': list,
             'age_limit': 18,
@@ -36,42 +35,53 @@ class AlphaPornoIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         video_id = self._search_regex(
-            r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
+            [r"video_id\s*:\s*'([^']+)'", r"\['video_id'\]\s*=\s*(.+?);"], webpage, 'video id')
 
-        video_url = self._search_regex(
+        entries = self._parse_html5_media_entries('https://alphaporno.com', webpage, video_id)
-            r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
+        info = {}
-        ext = self._html_search_meta(
+        if len(entries) > 0:
-            'encodingFormat', webpage, 'ext', default='.mp4')[1:]
+            info = entries[0]
+            for fmt in info['formats']:
+                fmt['tbr'] = int_or_none(self._search_regex(r"br=(\d+)", fmt['url'], 'bitrate', default=None))
+        else:
+            video_url = self._search_regex(
+                r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
+            ext = self._html_search_meta(
+                'encodingFormat', webpage, 'ext', default='.mp4')[1:]
+            bitrate = int_or_none(self._html_search_meta(
+                'bitrate', webpage, 'bitrate', default=None))
+            info = {
+                'url': video_url,
+                'ext': ext,
+                'tbr': bitrate,
+            }
 
         title = self._search_regex(
             [r'<meta content="([^"]+)" itemprop="description">',
-             r'class="title" itemprop="name">([^<]+)<'],
+             r'class="title" itemprop="name">([^<]+)<',
+             r'<h1>(.*?)</h1>'],
             webpage, 'title')
-        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
+        thumbnail = self._html_search_meta(['og:image', 'thumbnail'], webpage, 'thumbnail')
-        timestamp = parse_iso8601(self._html_search_meta(
+        timestamp = parse_iso8601(self._og_search_property('video:release_date', webpage, 'upload date', fatal=False),
-            'uploadDate', webpage, 'upload date'))
+                                  delimiter=' ') or parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
         duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration'))
+            ['duration', 'og:video:duration'], webpage, 'duration'))
         filesize_approx = parse_filesize(self._html_search_meta(
-            'contentSize', webpage, 'file size'))
+            'contentSize', webpage, 'file size', default=None))
-        bitrate = int_or_none(self._html_search_meta(
-            'bitrate', webpage, 'bitrate'))
         categories = self._html_search_meta(
             'keywords', webpage, 'categories', default='').split(',')
 
         age_limit = self._rta_search(webpage)
 
-        return {
+        info.update({
             'id': video_id,
             'display_id': display_id,
-            'url': video_url,
-            'ext': ext,
             'title': title,
             'thumbnail': thumbnail,
             'timestamp': timestamp,
             'duration': duration,
             'filesize_approx': filesize_approx,
-            'tbr': bitrate,
             'categories': categories,
             'age_limit': age_limit,
-        }
+        })
+        return info

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/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: