Merge 10f38086d4 into c5098961b0

test/test_utils.py

@@ -1603,14 +1603,11 @@ Line 1
 
     def test_get_element_by_class(self):
         html = '''
-            <span class="foo bar baz-bam">nice</span>
+            <span class="foo bar">nice</span>
         '''
 
         self.assertEqual(get_element_by_class('foo', html), 'nice')
-        self.assertEqual(get_element_by_class('bar', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
-        self.assertEqual(get_element_by_class('baz', html), None)
-        self.assertEqual(get_element_by_class('bam', html), None)
 
     def test_get_element_by_attribute(self):
         html = '''
@@ -1629,13 +1626,10 @@ Line 1
 
     def test_get_elements_by_class(self):
         html = '''
-            <span class="foo bar baz-bam">nice</span><span class="foo bar">also nice</span>
+            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
         '''
 
         self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
-        self.assertEqual(get_elements_by_class('bar', html), ['nice', 'also nice'])
-        self.assertEqual(get_elements_by_class('baz', html), [])
-        self.assertEqual(get_elements_by_class('bam', html), [])
         self.assertEqual(get_elements_by_class('no-such-class', html), [])
 
     def test_get_elements_by_attribute(self):

youtube_dl/extractor/generic.py

@@ -31,14 +31,10 @@ from ..utils import (
     parse_resolution,
     sanitized_Request,
     smuggle_url,
-    strip_or_none,
-    T,
-    traverse_obj,
     unescapeHTML,
     unified_timestamp,
     unsmuggle_url,
     UnsupportedError,
-    update_url_query,
     url_or_none,
     urljoin,
     xpath_attr,
@@ -2241,7 +2237,6 @@ class GenericIE(InfoExtractor):
                 'display_id': 'kelis-4th-of-july',
                 'ext': 'mp4',
                 'title': 'Kelis - 4th Of July',
-                'description': 'Kelis - 4th Of July',
                 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
             },
         }, {
@@ -2251,7 +2246,7 @@ class GenericIE(InfoExtractor):
                 'id': '105',
                 'display_id': 'kelis-4th-of-july',
                 'ext': 'mp4',
-                'title': r're:Kelis - 4th Of July(?: / Embed Player)?$',
+                'title': 'Kelis - 4th Of July / Embed Player',
                 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
             },
             'params': {
@@ -2302,32 +2297,6 @@ class GenericIE(InfoExtractor):
                 'title': 'Syren De Mer  onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
                 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
             },
-            'skip': 'needs Referer ?',
-        }, {
-            # KVS Player v10
-            'url': 'https://www.cambro.tv/588174/marleny-1/',
-            'md5': '759d2050590986c6fc341da0592c4d8e',
-            'info_dict': {
-                'id': '588174',
-                'display_id': 'marleny-1',
-                'ext': 'mp4',
-                'title': 'marleny 1',
-                'description': 'la maestra de tic toc',
-                'thumbnail': r're:https?://www\.cambro\.tv/contents/videos_screenshots/588000/588174/preview\.jpg',
-                'age_limit': 18,
-            },
-        }, {
-            # KVS Player v10 embed, NSFW
-            'url': 'https://www.cambro.tv/embed/436185',
-            'md5': '24338dc8b182900a2c9eda075a0a46c0',
-            'info_dict': {
-                'id': '436185',
-                'display_id': 'jaeandbailey-chaturbate-webcam-porn-videos',
-                'ext': 'mp4',
-                'title': 'jaeandbailey Chaturbate webcam porn videos',
-                'thumbnail': r're:https?://www\.cambro\.tv/contents/videos_screenshots/436000/436185/preview\.jpg',
-                'age_limit': 18,
-            },
         }, {
             'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
             'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
@@ -2340,16 +2309,14 @@ class GenericIE(InfoExtractor):
                 'height': 720,
                 'age_limit': 18,
             },
-            # 'skip': 'Geo-blocked in some mjurisdictions',
         }, {
-            # KVS Player v2
             'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
             'md5': 'e2f0a4c329f7986280b7328e24036d60',
             'info_dict': {
                 'id': '284002',
                 'display_id': 'just-out-of-the-shower-joi',
                 'ext': 'mp4',
-                'title': r're:Just Out Of The Shower JOI(?: - Shooshtime)?$',
+                'title': 'Just Out Of The Shower JOI - Shooshtime',
                 'height': 720,
                 'age_limit': 18,
             },
@@ -2515,12 +2482,9 @@ class GenericIE(InfoExtractor):
             return '/'.join(urlparts) + '?' + url_query
 
         flashvars = self._search_regex(
-            r'''(?<![=!+*-])=\s*kt_player\s*\(\s*'kt_player'\s*,\s*[^)]+,\s*([\w$]+)\s*\)''',
+            r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
-            webpage, 'flashvars name', default='flashvars')
+            webpage, 'flashvars')
-        flashvars = self._search_json(
+        flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
-            r'<script(?:\s[^>]*)?>[\s\S]*?var\s+%s\s*=' % (flashvars,),
-            webpage, 'flashvars', video_id, end_pattern=r';[\s\S]*?</script>',
-            transform_source=js_to_json)
 
         # extract the part after the last / as the display_id from the
         # canonical URL.
@@ -2529,7 +2493,12 @@ class GenericIE(InfoExtractor):
             r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
             webpage, 'display_id', fatal=False
         )
-        title = flashvars.get('video_title') or self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
+        title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
+
+        thumbnail = flashvars['preview_url']
+        if thumbnail.startswith('//'):
+            protocol, _, _ = url.partition('/')
+            thumbnail = protocol + thumbnail
 
         url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
         formats = []
@@ -2537,13 +2506,9 @@ class GenericIE(InfoExtractor):
             if '/get_file/' not in flashvars[key]:
                 continue
             format_id = flashvars.get(key + '_text', key)
-            f_url = urljoin(url, getrealurl(flashvars[key], flashvars['license_code']))
-            rnd = flashvars.get('rnd', key)
-            if rnd:
-                f_url = update_url_query(f_url, {'rnd': rnd})
             formats.append(merge_dicts(
                 parse_resolution(format_id) or parse_resolution(flashvars[key]), {
-                    'url': f_url,
+                    'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
                     'format_id': format_id,
                     'ext': 'mp4',
                     'http_headers': {'Referer': url},
@@ -2553,31 +2518,13 @@ class GenericIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        csv2list = (T(lambda s: s.split(',')), Ellipsis, T(strip_or_none))
+        return {
-        info = traverse_obj(flashvars, {
-            'tags': ('video_tags',) + csv2list,
-            'categories': ('video_categories',) + csv2list,
-            'thumbnails': (
-                T(dict.items), lambda _, k_v: k_v[0].startswith('preview_url'), {
-                    'url': (1, T(lambda u: urljoin(url, u))),
-                    'preference': (0, T(lambda k: 100 - len(k))),
-                }),
-        })
-        info = merge_dicts(info, {
             'id': flashvars['video_id'],
             'display_id': display_id,
             'title': title,
+            'thumbnail': thumbnail,
             'formats': formats,
-        })
+        }
-
-        # check-porn test for embed pages
-        if 'age_limit' not in info and traverse_obj(info, (
-                ('title', (('tags', 'categories'), Ellipsis) or []),
-                T(lambda t: bool(re.search(r'(?i)(?:^|\s+)porn(?:$|\s+)', t)) or None)),
-                get_all=False):
-            info['age_limit'] = 18
-
-        return info
 
     def _real_extract(self, url):
         if url.startswith('//'):
@@ -3651,7 +3598,7 @@ class GenericIE(InfoExtractor):
              ), webpage, 'KVS player', group='ver', default=False)
         if found:
             self.report_extraction('%s: KVS Player' % (video_id, ))
-            if found.split('.')[0] not in ('2', '4', '5', '6', '10'):
+            if found.split('.')[0] not in ('4', '5', '6'):
                 self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
             return merge_dicts(
                 self._extract_kvs(url, webpage, video_id),

youtube_dl/extractor/xfileshare.py

@@ -12,9 +12,7 @@ from ..utils import (
     clean_html,
     decode_packed_codes,
     determine_ext,
-    extract_attributes,
     ExtractorError,
-    get_element_by_class,
     get_element_by_id,
     int_or_none,
     merge_dicts,
@@ -58,40 +56,39 @@ def aa_decode(aa_code):
 
 class XFileShareIE(InfoExtractor):
     _SITES = (
-        # status check 2024-10: site availability, G site: search
+        # status check 2024-02: site availability, G site: search
-        (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstream.tv
+        (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstreeam.tv
-        (r'filemoon\.(?:sx|to|in)', 'FileMoon'),
+        (r'filemoon\.sx/.', 'FileMoon'),
-        # (r'gounlimited\.to', 'GoUnlimited'),  # domain not found
+        (r'gounlimited\.to', 'GoUnlimited'),  # no media pages listed
         (r'govid\.me', 'GoVid'),  # no media pages listed
-        (r'highstream\.tv', 'HighStream'),  # Cloudflare says host error 522, clipwatching.com now dead
+        (r'highstream\.tv', 'HighStream'),  # clipwatching.com redirects here
-        (r'holavid\.com', 'HolaVid'),  # hoster default home page
+        (r'holavid\.com', 'HolaVid'),  # Cloudflare says host error 522
-        # (r'streamty\.com', 'Streamty'),  # spam parking domain
+        # (r'streamty\.com', 'Streamty'),  # no media pages listed, connection timeout
-        # (r'thevideobee\.to', 'TheVideoBee'),  # domain for sale
+        # (r'thevideobee\.to', 'TheVideoBee'),  # no pages listed, refuses connection
-        (r'uqload\.ws', 'Uqload'),  # .com, .co, .to redirect here
+        (r'uqload\.to', 'Uqload'),  # .com, .co redirect here
-        # (r'(vadbam.net', 'VadBam'),  # domain not found
+        (r'(?:vedbam\.xyz|vadbam.net)', 'V?dB?m'),  # vidbom.com redirects here, but no valid media pages listed
-        (r'(?:vedbam\.xyz|vadbam\.net|vbn\d.\vdbtm\.shop)', 'V?dB?m'),  # vidbom.com redirects here, but no valid media pages listed
         (r'vidlo\.us', 'vidlo'),  # no valid media pages listed
         (r'vidlocker\.xyz', 'VidLocker'),  # no media pages listed
-        (r'(?:w\d\.)?viidshar\.com', 'VidShare'),  # vidshare.tv parked
+        (r'(?:w\d\.)?viidshar\.com', 'VidShare'),  # vidshare.tv redirects here
         # (r'vup\.to', 'VUp'),  # domain not found
-        # (r'wolfstream\.tv', 'WolfStream'),  # domain not found
+        (r'wolfstream\.tv', 'WolfStream'),
-        (r'xvideosharing\.com', 'XVideoSharing'),
+        (r'xvideosharing\.com', 'XVideoSharing'),  # just started showing 'maintenance mode'
     )
 
     IE_DESC = 'XFileShare-based sites: %s' % ', '.join(list(zip(*_SITES))[1])
-    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?P<sub>[a-z]/|)(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                   % '|'.join(site for site in list(zip(*_SITES))[0]))
     _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
 
     _FILE_NOT_FOUND_REGEXES = (
-        r'>\s*(?:404 - )?File Not Found\s*<',
+        r'>(?:404 - )?File Not Found<',
-        r'>\s*The file was removed by administrator\s*<',
+        r'>The file was removed by administrator<',
     )
     _TITLE_REGEXES = (
         r'style="z-index: [0-9]+;">([^<]+)</span>',
         r'<td nowrap>([^<]+)</td>',
         r'h4-fine[^>]*>([^<]+)<',
-        r'>Watch (.+?)(?: mp4)?(?: The Ultimate Free Video Hosting Solution for Webmasters and Bloggers)?<',
+        r'>Watch (.+)[ <]',
         r'<h2 class="video-page-head">([^<]+)</h2>',
         r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to (dead)
         r'title\s*:\s*"([^"]+)"',  # govid.me
@@ -109,41 +106,38 @@ class XFileShareIE(InfoExtractor):
 
     _TESTS = [{
         'note': 'link in `sources`',
-        'url': 'https://uqload.ws/4sah252totrk.html',
+        'url': 'https://uqload.to/dcsu06gdb45o',
-        'md5': '1f11151b5044862fbc3c112732f9f7d8',
+        'md5': '7f8db187b254379440bf4fcad094ae86',
         'info_dict': {
-            'id': '4sah252totrk',
+            'id': 'dcsu06gdb45o',
             'ext': 'mp4',
-            'title': 'JEONGHAN WONWOO Interview With Allure Korea Arabic Sub',
+            'title': 'f2e31015957e74c8c8427982e161c3fc mp4',
             'thumbnail': r're:https://.*\.jpg'
         },
         'params': {
             'nocheckcertificate': True,
         },
-        # 'expected_warnings': ['Unable to extract JWPlayer data'],
+        'expected_warnings': ['Unable to extract JWPlayer data'],
     }, {
-        'note': 'link in Playerjs',  # need test with 'link in decoded `sources`'
+        'note': 'link in decoded `sources`',
-        'url': 'https://xvideosharing.com/8cnupzc1z8xq.html',
+        'url': 'https://xvideosharing.com/1tlg6agrrdgc',
-        'md5': '9725ca7229e8f3046f2417da3bd5eddc',
+        'md5': '2608ce41932c1657ae56258a64e647d9',
         'info_dict': {
-            'id': '8cnupzc1z8xq',
+            'id': '1tlg6agrrdgc',
             'ext': 'mp4',
-            'title': 'HEVC X265 Big Buck Bunny 1080 10s 20MB',
+            'title': '0121',
             'thumbnail': r're:https?://.*\.jpg',
         },
+        'skip': 'This server is in maintenance mode.',
     }, {
-        'note': 'JWPlayer link in un-p,a,c,k,e,d JS, in player frame',
+        'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
-        'url': 'https://filemoon.sx/d/fbsxidybremo',
+        'url': 'https://filemoon.sx/e/dw40rxrzruqz',
-        'md5': '82007a71661630f60e866f0d6ed31b2a',
+        'md5': '5a713742f57ac4aef29b74733e8dda01',
         'info_dict': {
-            'id': 'fbsxidybremo',
+            'id': 'dw40rxrzruqz',
-            'title': 'Uchouten',
+            'title': 'dw40rxrzruqz',
             'ext': 'mp4'
         },
-        'params': {
-            'skip_download': 'ffmpeg',
-        },
-        'expected_warnings': ['hlsnative has detected features it does not support'],
     }, {
         'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
         'url': 'https://vadbam.net/6lnbkci96wly.html',
@@ -156,7 +150,7 @@ class XFileShareIE(InfoExtractor):
     }, {
         'note': 'JWPlayer link in clear',
         'url': 'https://w1.viidshar.com/nnibe0xf0h79.html',
-        'md5': 'b95b97978093bc287c322307c689bd94',
+        'md5': 'f0a580ce9df06cc61b4a5c979d672367',
         'info_dict': {
             'id': 'nnibe0xf0h79',
             'title': 'JaGa 68ar',
@@ -166,6 +160,15 @@ class XFileShareIE(InfoExtractor):
             'skip_download': 'ffmpeg',
         },
         'expected_warnings': ['hlsnative has detected features it does not support'],
+    }, {
+        'note': 'JWPlayer link in clear',
+        'url': 'https://wolfstream.tv/a3drtehyrg52.html',
+        'md5': '1901d86a79c5e0c6a51bdc9a4cfd3769',
+        'info_dict': {
+            'id': 'a3drtehyrg52',
+            'title': 'NFL 2023 W04 DET@GB',
+            'ext': 'mp4'
+        },
     }, {
         'url': 'https://aparat.cam/n4d6dh0wvlpr',
         'only_matching': True,
@@ -178,12 +181,6 @@ class XFileShareIE(InfoExtractor):
     }, {
         'url': 'https://vedbam.xyz/6lnbkci96wly.html',
         'only_matching': True,
-    }, {
-        'url': 'https://vbn2.vdbtm.shop/6lnbkci96wly.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://filemoon.in/e/5abn1ze9jifb',
-        'only_matching': True,
     }]
 
     @classmethod
@@ -197,26 +194,17 @@ class XFileShareIE(InfoExtractor):
         return list(yield_urls())
 
     def _real_extract(self, url):
-        host, sub, video_id = self._match_valid_url(url).group('host', 'sub', 'id')
+        host, video_id = self._match_valid_url(url).group('host', 'id')
 
-        url = 'https://%s/%s%s' % (
+        url = 'https://%s/%s' % (
-            host, sub,
+            host,
             'embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
         webpage = self._download_webpage(url, video_id)
-        main = self._search_regex(
+        container_div = get_element_by_id('container', webpage) or webpage
-            r'(?s)<main>(.+)</main>', webpage, 'main', default=webpage)
-        container_div = (
-            get_element_by_id('container', main)
-            or get_element_by_class('container', main)
-            or webpage)
         if self._search_regex(
                 r'>This server is in maintenance mode\.', container_div,
                 'maint error', group=0, default=None):
             raise ExtractorError(clean_html(container_div), expected=True)
-        if self._search_regex(
-                'not available in your country', container_div,
-                'geo block', group=0, default=None):
-            self.raise_geo_restricted()
         if self._search_regex(
                 self._FILE_NOT_FOUND_REGEXES, container_div,
                 'missing video error', group=0, default=None):
@@ -240,41 +228,38 @@ class XFileShareIE(InfoExtractor):
 
         title = (
             self._search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
-            or self._og_search_title(webpage, default='')).strip()
+            or self._og_search_title(webpage, default=None)
+            or video_id).strip()
 
-        def deobfuscate(html):
+        obf_code = True
+        while obf_code:
             for regex, func in (
                     (r'(?s)(?<!-)\b(eval\(function\(p,a,c,k,e,d\)\{(?:(?!</script>).)+\)\))',
                      decode_packed_codes),
                     (r'(ﾟ.+)', aa_decode)):
-                obf_code = self._search_regex(regex, html, 'obfuscated code', default=None)
+                obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
                 if obf_code:
-                    return html.replace(obf_code, func(obf_code))
+                    webpage = webpage.replace(obf_code, func(obf_code))
+                    break
 
-        def jw_extract(html):
         jwplayer_data = self._find_jwplayer_data(
-                html.replace(r'\'', '\''), video_id)
+            webpage.replace(r'\'', '\''), video_id)
         result = self._parse_jwplayer_data(
             jwplayer_data, video_id, require_title=False,
             m3u8_id='hls', mpd_id='dash')
-            result = traverse_obj(result, (
+
-                (None, ('entries', 0)), T(lambda r: r if r['formats'] else None)),
+        if not traverse_obj(result, 'formats'):
-                get_all=False) or {}
+            if jwplayer_data:
-            if not result and jwplayer_data:
                 self.report_warning(
                     'Failed to extract JWPlayer formats', video_id=video_id)
-            return result
-
-        def extract_from_links(html):
             urls = set()
             for regex in self._SOURCE_URL_REGEXES:
-                for mobj in re.finditer(regex, html):
+                for mobj in re.finditer(regex, webpage):
                     urls.add(mobj.group('url'))
 
-            sources = self._search_json(
+            sources = self._search_regex(
-                r'\bsources\s*:', webpage, 'sources', video_id,
+                r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
-                contains_pattern=r'\[(?!{)[^\]]+\]', default=[])
+            urls.update(traverse_obj(sources, (T(lambda s: self._parse_json(s, video_id)), Ellipsis)))
-            urls.update(sources)
 
             formats = []
             for video_url in traverse_obj(urls, (Ellipsis, T(url_or_none))):
@@ -288,33 +273,7 @@ class XFileShareIE(InfoExtractor):
                         'url': video_url,
                         'format_id': 'sd',
                     })
-            return {'formats': formats}
+            result = {'formats': formats}
-
-        def extract_info(html):
-            html = deobfuscate(html) or html
-            result = jw_extract(html)
-            if not result.get('formats'):
-                result = extract_from_links(html)
-            return result
-
-        def pages_to_extract(html):
-            yield html
-            # page with separate protected download page also has player link
-            player_iframe = self._search_regex(
-                r'(<iframe\s[^>]+>)',
-                get_element_by_id('iframe-holder', html) or '',
-                'player iframe', default='')
-            player_url = extract_attributes(player_iframe).get('src')
-            if player_url:
-                html = self._download_webpage(player_url, video_id, note='Downloading player page', fatal=False)
-            if html:
-                yield html
-
-        result = {}
-        for html in pages_to_extract(webpage):
-            result = extract_info(html)
-            if result.get('formats'):
-                break
 
         self._sort_formats(result['formats'])
 

youtube_dl/extractor/yandexmusic.py

@@ -30,20 +30,17 @@ class YandexMusicBaseIE(InfoExtractor):
     @staticmethod
     def _raise_captcha():
         raise ExtractorError(
-            'YandexMusic has considered youtube-dl requests automated '
+            'YandexMusic has considered youtube-dl requests automated and '
-            'and asks you to solve a CAPTCHA. You can wait for some time '
+            'asks you to solve a CAPTCHA. You can either wait for some '
-            'until unblocked and optionally use --sleep-interval in future; '
+            'time until unblocked and optionally use --sleep-interval '
-            'otherwise solve the CAPTCHA at https://music.yandex.ru/, '
+            'in future or alternatively you can go to https://music.yandex.ru/ '
-            'then export cookies and pass the cookie file to youtube-dl '
+            'solve CAPTCHA, then export cookies and pass cookie file to '
-            'with --cookies.',
+            'youtube-dl with --cookies',
             expected=True)
 
     def _download_webpage_handle(self, *args, **kwargs):
         webpage = super(YandexMusicBaseIE, self)._download_webpage_handle(*args, **kwargs)
-        blocked_ip_msg = (
+        if 'Нам очень жаль, но запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage:
-            'Нам очень жаль, но запросы, поступившие с '
-            'вашего IP-адреса, похожи на автоматические.')
-        if blocked_ip_msg in (webpage or [''])[0]:
             self._raise_captcha()
         return webpage
 

youtube_dl/utils.py

@@ -1960,7 +1960,7 @@ def get_element_by_attribute(attribute, value, html, escape_value=True):
 def get_elements_by_class(class_name, html):
     """Return the content of all tags with the specified class in the passed HTML document as a list"""
     return get_elements_by_attribute(
-        'class', r'[^\'"]*(?<!-)\b%s\b(?!-)[^\'"]*' % re.escape(class_name),
+        'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
@@ -4498,7 +4498,7 @@ def strip_jsonp(code):
 def js_to_json(code, *args, **kwargs):
 
     # vars is a dict of (var, val) pairs to substitute
-    js_vars = args[0] if len(args) > 0 else kwargs.get('vars', {})
+    vars = args[0] if len(args) > 0 else kwargs.get('vars', {})
     strict = kwargs.get('strict', False)
 
     STRING_QUOTES = '\'"`'
@@ -4523,13 +4523,9 @@ def js_to_json(code, *args, **kwargs):
                 else escape)
 
     def template_substitute(match):
-        evaluated = js_to_json(match.group(1), js_vars, strict=strict)
+        evaluated = js_to_json(match.group(1), vars, strict=strict)
         if evaluated[0] == '"':
-            try:
             return json.loads(evaluated)
-            except JSONDecodeError:
-                if strict:
-                    raise
         return evaluated
 
     def fix_kv(m):
@@ -4563,14 +4559,14 @@ def js_to_json(code, *args, **kwargs):
                 i = int(im.group(1), base)
                 return ('"%s":' if v.endswith(':') else '%s') % inv(i)
 
-        if v in js_vars:
+        if v in vars:
             try:
                 if not strict:
-                    json.loads(js_vars[v])
+                    json.loads(vars[v])
             except JSONDecodeError:
-                return inv(json.dumps(js_vars[v]))
+                return inv(json.dumps(vars[v]))
             else:
-                return inv(js_vars[v])
+                return inv(vars[v])
 
         if not strict:
             v = try_call(inv, args=(v,), default=v)
@@ -4581,7 +4577,7 @@ def js_to_json(code, *args, **kwargs):
         raise ValueError('Unknown value: ' + v)
 
     def create_map(mobj):
-        return json.dumps(dict(json.loads(js_to_json(mobj.group(1) or '[]', vars=js_vars))))
+        return json.dumps(dict(json.loads(js_to_json(mobj.group(1) or '[]', vars=vars))))
 
     code = re.sub(r'new Map\((\[.*?\])?\)', create_map, code)
     if not strict:
@@ -6719,8 +6715,3 @@ class _UnsafeExtensionError(Exception):
                 raise cls(extension)
 
         return extension
-
-
-def json_stringify(json_data, **kwargs):
-    kwargs.setdefault('separators', (',', ':'))
-    return json.dumps(json_data, **kwargs).decode('utf-8')