Merge 48d0994b5b3ef6714dba9510656808883e40df40 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

@@ -371,7 +371,6 @@ from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .expotv import ExpoTVIE
 from .expressen import ExpressenIE
-from .extremetube import ExtremeTubeIE
 from .eyedotv import EyedoTVIE
 from .facebook import (
     FacebookIE,
@@ -562,7 +561,6 @@ from .kaltura import KalturaIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
-from .keezmovies import KeezMoviesIE
 from .ketnet import KetnetIE
 from .khanacademy import (
     KhanAcademyIE,
@@ -713,10 +711,6 @@ from .mlb import (
 )
 from .mnet import MnetIE
 from .moevideo import MoeVideoIE
-from .mofosex import (
-    MofosexIE,
-    MofosexEmbedIE,
-)
 from .mojvideo import MojvideoIE
 from .morningstar import MorningstarIE
 from .motherless import (

youtube_dl/extractor/extremetube.py

@@ -1,50 +0,0 @@
-from __future__ import unicode_literals
-
-from ..utils import str_to_int
-from .keezmovies import KeezMoviesIE
-
-
-class ExtremeTubeIE(KeezMoviesIE):
-    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
-    _TESTS = [{
-        'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '92feaafa4b58e82f261e5419f39c60cb',
-        'info_dict': {
-            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-            'ext': 'mp4',
-            'title': 'Music Video 14 british euro brit european cumshots swallow',
-            'uploader': 'anonim',
-            'view_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        'url': 'http://www.extremetube.com/gay/video/abcde-1234',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.extremetube.com/video/652431',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
-
-        if not info['title']:
-            info['title'] = self._search_regex(
-                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
-
-        uploader = self._html_search_regex(
-            r'Uploaded by:\s*</[^>]+>\s*<a[^>]+>(.+?)</a>',
-            webpage, 'uploader', fatal=False)
-        view_count = str_to_int(self._search_regex(
-            r'Views:\s*</[^>]+>\s*<[^>]+>([\d,\.]+)</',
-            webpage, 'view count', fatal=False))
-
-        info.update({
-            'uploader': uploader,
-            'view_count': view_count,
-        })
-
-        return info

youtube_dl/extractor/generic.py

@@ -66,7 +66,6 @@ from .tnaflix import TNAFlixNetworkEmbedIE
 from .drtuber import DrTuberIE
 from .redtube import RedTubeIE
 from .tube8 import Tube8IE
-from .mofosex import MofosexEmbedIE
 from .spankwire import SpankwireIE
 from .youporn import YouPornIE
 from .vimeo import (
@@ -3044,11 +3043,6 @@ class GenericIE(InfoExtractor):
         if tube8_urls:
             return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
 
-        # Look for embedded Mofosex player
-        mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
-        if mofosex_urls:
-            return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
-
         # Look for embedded Spankwire player
         spankwire_urls = SpankwireIE._extract_urls(webpage)
         if spankwire_urls:

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/keezmovies.py

@@ -1,133 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..aes import aes_decrypt_text
-from ..compat import compat_urllib_parse_unquote
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    int_or_none,
-    str_to_int,
-    strip_or_none,
-    url_or_none,
-)
-
-
-class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
-        'md5': '2ac69cdb882055f71d82db4311732a1a',
-        'info_dict': {
-            'id': '18070681',
-            'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
-            'ext': 'mp4',
-            'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
-            'thumbnail': None,
-            'view_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        'url': 'http://www.keezmovies.com/video/18070681',
-        'only_matching': True,
-    }]
-
-    def _extract_info(self, url, fatal=True):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = (mobj.group('display_id')
-                      if 'display_id' in mobj.groupdict()
-                      else None) or mobj.group('id')
-
-        webpage = self._download_webpage(
-            url, display_id, headers={'Cookie': 'age_verified=1'})
-
-        formats = []
-        format_urls = set()
-
-        title = None
-        thumbnail = None
-        duration = None
-        encrypted = False
-
-        def extract_format(format_url, height=None):
-            format_url = url_or_none(format_url)
-            if not format_url or not format_url.startswith(('http', '//')):
-                return
-            if format_url in format_urls:
-                return
-            format_urls.add(format_url)
-            tbr = int_or_none(self._search_regex(
-                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
-            if not height:
-                height = int_or_none(self._search_regex(
-                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
-            if encrypted:
-                format_url = aes_decrypt_text(
-                    video_url, title, 32).decode('utf-8')
-            formats.append({
-                'url': format_url,
-                'format_id': '%dp' % height if height else None,
-                'height': height,
-                'tbr': tbr,
-            })
-
-        flashvars = self._parse_json(
-            self._search_regex(
-                r'flashvars\s*=\s*({.+?});', webpage,
-                'flashvars', default='{}'),
-            display_id, fatal=False)
-
-        if flashvars:
-            title = flashvars.get('video_title')
-            thumbnail = flashvars.get('image_url')
-            duration = int_or_none(flashvars.get('video_duration'))
-            encrypted = flashvars.get('encrypted') is True
-            for key, value in flashvars.items():
-                mobj = re.search(r'quality_(\d+)[pP]', key)
-                if mobj:
-                    extract_format(value, int(mobj.group(1)))
-            video_url = flashvars.get('video_url')
-            if video_url and determine_ext(video_url, None):
-                extract_format(video_url)
-
-        video_url = self._html_search_regex(
-            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
-            webpage, 'video url', default=None, group='url')
-        if video_url:
-            extract_format(compat_urllib_parse_unquote(video_url))
-
-        if not formats:
-            if 'title="This video is no longer available"' in webpage:
-                raise ExtractorError(
-                    'Video %s is no longer available' % video_id, expected=True)
-
-        try:
-            self._sort_formats(formats)
-        except ExtractorError:
-            if fatal:
-                raise
-
-        if not title:
-            title = self._html_search_regex(
-                r'<h1[^>]*>([^<]+)', webpage, 'title')
-
-        return webpage, {
-            'id': video_id,
-            'display_id': display_id,
-            'title': strip_or_none(title),
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'age_limit': 18,
-            'formats': formats,
-        }
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url, fatal=False)
-        if not info['formats']:
-            return self.url_result(url, 'Generic')
-        info['view_count'] = str_to_int(self._search_regex(
-            r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
-        return info

youtube_dl/extractor/mofosex.py

@@ -1,79 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    str_to_int,
-    unified_strdate,
-)
-from .keezmovies import KeezMoviesIE
-
-
-class MofosexIE(KeezMoviesIE):
-    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
-    _TESTS = [{
-        'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
-        'md5': '558fcdafbb63a87c019218d6e49daf8a',
-        'info_dict': {
-            'id': '318131',
-            'display_id': 'amateur-teen-playing-and-masturbating-318131',
-            'ext': 'mp4',
-            'title': 'amateur teen playing and masturbating',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20121114',
-            'view_count': int,
-            'like_count': int,
-            'dislike_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        # This video is no longer available
-        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
-
-        view_count = str_to_int(self._search_regex(
-            r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
-        like_count = int_or_none(self._search_regex(
-            r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
-            'like count', fatal=False))
-        dislike_count = int_or_none(self._search_regex(
-            r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
-            'like count', fatal=False))
-        upload_date = unified_strdate(self._html_search_regex(
-            r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
-
-        info.update({
-            'view_count': view_count,
-            'like_count': like_count,
-            'dislike_count': dislike_count,
-            'upload_date': upload_date,
-            'thumbnail': self._og_search_thumbnail(webpage),
-        })
-
-        return info
-
-
-class MofosexEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
-        'only_matching': True,
-    }]
-
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)',
-            webpage)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self.url_result(
-            'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id),
-            ie=MofosexIE.ie_key(), video_id=video_id)

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/tube8.py

@@ -3,32 +3,33 @@ from __future__ import unicode_literals
 import re
 
 from ..utils import (
+    determine_ext,
+    ExtractorError,
     int_or_none,
     str_to_int,
+    url_or_none,
 )
-from .keezmovies import KeezMoviesIE
+from .common import InfoExtractor
+from ..aes import aes_decrypt_text
+from ..compat import compat_urllib_parse_unquote
 
 
-class Tube8IE(KeezMoviesIE):
+class Tube8IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
+        'url': 'https://www.tube8.com/erotic/playtime/81807731/',
-        'md5': '65e20c48e6abff62ed0c3965fff13a39',
+        'md5': 'fefa69ff76debaa63aa59374bfc51c95',
         'info_dict': {
-            'id': '229795',
+            'id': '81807731',
-            'display_id': 'kasia-music-video',
+            'display_id': 'playtime',
             'ext': 'mp4',
-            'description': 'hot teen Kasia grinding',
+            'uploader': 'kikkijay-ph',
-            'uploader': 'unknown',
+            'title': 'Playtime',
-            'title': 'Kasia music video',
             'age_limit': 18,
-            'duration': 230,
+            'duration': 988,
-            'categories': ['Teen'],
+            'categories': ['Erotic'],
-            'tags': ['dancing'],
+            'tags': ['adult toys', 'big boobs', 'butt', 'masturbate'],
         },
-    }, {
-        'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
-        'only_matching': True,
     }]
 
     @staticmethod
@@ -38,49 +39,121 @@ class Tube8IE(KeezMoviesIE):
             webpage)
 
     def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        if not info['title']:
+        webpage = self._download_webpage(
-            info['title'] = self._html_search_regex(
+            url, display_id, headers={'Cookie': 'age_verified=1'})
-                r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
 
-        description = self._html_search_regex(
+        formats = []
-            r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
+        format_urls = set()
-        uploader = self._html_search_regex(
+
-            r'<span class="username">\s*(.+?)\s*<',
+        title = None
-            webpage, 'uploader', fatal=False)
+        thumbnail = None
+        duration = None
+        encrypted = False
+
+        def extract_format(format_url, height=None):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//')):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            uploader = flashvars.get('sponsor')
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(compat_urllib_parse_unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                raise ExtractorError(
+                    'Video %s is no longer available' % video_id, expected=True)
+
+        self._sort_formats(formats)
+
+        if not title:
+            title = self._html_search_regex([
+                r'<h1[^>]*>([^<]+)'
+                r'videoTitle\s*=\s*"([^"]+)'], webpage, 'title', default=display_id.capitalize())
 
         like_count = int_or_none(self._search_regex(
-            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
+            r'rupVar\s*=\s*(\d+);', webpage, 'like count', fatal=False))
         dislike_count = int_or_none(self._search_regex(
-            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
+            r'rdownVar\s*=\s*(\d+);', webpage, 'dislike count', fatal=False))
         view_count = str_to_int(self._search_regex(
             r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._search_regex(
-            r'<span id="allCommentsCount">(\d+)</span>',
+            r'<span id="allCommentsCount">\((\d+)\)</span>',
             webpage, 'comment count', fatal=False))
 
         category = self._search_regex(
-            r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
+            r'videoCategoryByName\s*=\s*"([^"]+)";',
             webpage, 'category', fatal=False)
         categories = [category] if category else None
 
         tags_str = self._search_regex(
-            r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
+            r"(?s)<li\s+class\s*=\s*'video-tag'\s+data-esp-node\s*=\s*'tag'>(.*?)</div>",
             webpage, 'tags', fatal=False)
         tags = [t for t in re.findall(
             r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
 
-        info.update({
+        return {
-            'description': description,
             'uploader': uploader,
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
+            'formats': formats,
             'view_count': view_count,
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,
             'categories': categories,
             'tags': tags,
-        })
+        }
-
-        return info

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: