Merge b804854e3bd4c663dfa6c264968a663d739a64d7 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/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/xnxx.py

@@ -6,9 +6,11 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
+    float_or_none,
     int_or_none,
     NO_DEFAULT,
     str_to_int,
+    urljoin,
 )
 
 
@@ -16,7 +18,7 @@ class XNXXIE(InfoExtractor):
     _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/'
     _TESTS = [{
         'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
-        'md5': '7583e96c15c0f21e9da3453d9920fbba',
+        'md5': '73c071a361a09aae7e7d60008221fd13',
         'info_dict': {
             'id': '55awb78',
             'ext': 'mp4',
@@ -25,7 +27,29 @@ class XNXXIE(InfoExtractor):
             'duration': 469,
             'view_count': int,
             'age_limit': 18,
+            'tags': ['video game', 'skyrim', '3d', 'game', '3d game', 'video games', 'rule34', 'test', 'rough', 'sfm', 'fallout', 'porno game', 'skyrim hentai', 'h game', '3d horse', '3d porno anime', 'xx video wwxxx cartoon cartoons', 'gaming', 'games', '3d porno desenho'],
+            'uploader': 'Glurp',
+            'uploader_id': 'Glurp',
+            'uploader_url': '/porn-maker/glurp',
         },
+    }, {
+        'url': 'https://www.xnxx.com/video-h46klf8/babes_-_come_back_to_bed_starring_abella_danger_and_darcie_dolce_clip',
+        'md5': 'b8b4a594b4091de46ce05d0a9d45317c',
+        'info_dict': {
+            'id': 'h46klf8',
+            'ext': 'mp4',
+            'title': 'Babes - Come Back to Bed  starring  Abella Danger and Darcie Dolce clip',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 480,
+            'view_count': int,
+            'age_limit': 18,
+            'tags': ['lesbicas', 'darcie dolce', 'darcie dolce lesbian', 'abella danger lesbian', 'babes', 'lesb', 'abella danger', 'mmf', 'come', 'darcie', 'lesbianas', 'mulher chupando peito da outra', 'abella', 'girl on girl', 'darcie dolce abella danger', 'chupando peitos', 'para', 'lesbian', 'chupando peitos lesbicas', 'black lesbians'],
+            'uploader': 'Babes Network',
+            'uploader_id': 'Babes Network',
+            'uploader_url': '/porn-maker/babes3',
+            'actors': [{'given_name': 'darcie dolce', 'url': 'https://www.xnxx.com/search/darcie%20dolce'}, {'given_name': 'darcie dolce lesbian', 'url': 'https://www.xnxx.com/search/darcie%20dolce%20lesbian'}, {'given_name': 'abella danger lesbian', 'url': 'https://www.xnxx.com/search/abella%20danger%20lesbian'}, {'given_name': 'abella danger', 'url': 'https://www.xnxx.com/search/abella%20danger'}, {'given_name': 'darcie dolce abella danger', 'url': 'https://www.xnxx.com/search/darcie%20dolce%20abella%20danger'}],
+            'average_rating': float,
+        }
     }, {
         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
         'only_matching': True,
@@ -70,8 +94,27 @@ class XNXXIE(InfoExtractor):
             'ThumbUrl', fatal=False) or get('ThumbUrl169', fatal=False)
         duration = int_or_none(self._og_search_property('duration', webpage))
         view_count = str_to_int(self._search_regex(
-            r'id=["\']nb-views-number[^>]+>([\d,.]+)', webpage, 'view count',
-            default=None))
+            r'-.+?\t+- (?P<views>.+?) <span class="icon-f icf-eye">', webpage, 'view count', group='views',
+            default=0))
+
+        tags = self._search_regex(r'<meta name="keywords" content="porn,porn movies,free porn,free porn movies,sex,porno,free sex,tube porn,tube,videos,full porn,xxnx,xnxxx,xxx,pussy,(?P<tags>.+?)"', webpage, 'tags', group='tags', default='').split(',')
+
+        uploader_data = re.findall(r'<a class=".+?-plate" href="(?P<uploader_url>.+?)">(?P<uploader_name>.+?)</a>', webpage)
+        uploader_id = None
+        uploader_url = None
+        if uploader_data != []:
+            uploader_url, uploader_id = uploader_data[0][0:2]
+
+        actors_data = re.findall(r'<a class="is-pornstar" href="(?P<actor_url>.+?)">(?P<actor_name>.+?)</a>', webpage)
+        actors = []
+        if actors_data != []:
+            for actor_tuple in actors_data:
+                actors.append({
+                    'given_name': actor_tuple[1],
+                    'url': urljoin(url, actor_tuple[0]),
+                })
+
+        rating = float_or_none(self._search_regex(r'<span class="rating-box value">(?P<rating>.+?)%</span>', webpage, 'rating', group='rating'))
 
         return {
             'id': video_id,
@@ -81,4 +124,11 @@ class XNXXIE(InfoExtractor):
             'view_count': view_count,
             'age_limit': 18,
             'formats': formats,
+            'tags': tags,
+            'creator': uploader_id,
+            'uploader': uploader_id,
+            'uploader_id': uploader_id,
+            'uploader_url': uploader_url,
+            'actors': actors,
+            'average_rating': rating,
         }

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: