yt_dlp/extractor/pornhub.py

   1 import functools
   2 import itertools
   3 import math
   4 import operator
   5 import re
   6
   7 from .common import InfoExtractor
   8 from .openload import PhantomJSwrapper
   9 from ..compat import compat_str
  10 from ..networking import Request
  11 from ..networking.exceptions import HTTPError
  12 from ..utils import (
  13     NO_DEFAULT,
  14     ExtractorError,
  15     clean_html,
  16     determine_ext,
  17     format_field,
  18     int_or_none,
  19     merge_dicts,
  20     orderedSet,
  21     remove_quotes,
  22     remove_start,
  23     str_to_int,
  24     update_url_query,
  25     url_or_none,
  26     urlencode_postdata,
  27 )
  28
  29
  30 class PornHubBaseIE(InfoExtractor):
  31     _NETRC_MACHINE = 'pornhub'
  32     _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)'
  33
  34     def _download_webpage_handle(self, *args, **kwargs):
  35         def dl(*args, **kwargs):
  36             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
  37
  38         ret = dl(*args, **kwargs)
  39
  40         if not ret:
  41             return ret
  42
  43         webpage, urlh = ret
  44
  45         if any(re.search(p, webpage) for p in (
  46                 r'<body\b[^>]+\bonload=["\']go\(\)',
  47                 r'document\.cookie\s*=\s*["\']RNKEY=',
  48                 r'document\.location\.reload\(true\)')):
  49             url_or_request = args[0]
  50             url = (url_or_request.url
  51                    if isinstance(url_or_request, Request)
  52                    else url_or_request)
  53             phantom = PhantomJSwrapper(self, required_version='2.0')
  54             phantom.get(url, html=webpage)
  55             webpage, urlh = dl(*args, **kwargs)
  56
  57         return webpage, urlh
  58
  59     def _real_initialize(self):
  60         self._logged_in = False
  61
  62     def _set_age_cookies(self, host):
  63         self._set_cookie(host, 'age_verified', '1')
  64         self._set_cookie(host, 'accessAgeDisclaimerPH', '1')
  65         self._set_cookie(host, 'accessAgeDisclaimerUK', '1')
  66         self._set_cookie(host, 'accessPH', '1')
  67
  68     def _login(self, host):
  69         if self._logged_in:
  70             return
  71
  72         site = host.split('.')[0]
  73
  74         # Both sites pornhub and pornhubpremium have separate accounts
  75         # so there should be an option to provide credentials for both.
  76         # At the same time some videos are available under the same video id
  77         # on both sites so that we have to identify them as the same video.
  78         # For that purpose we have to keep both in the same extractor
  79         # but under different netrc machines.
  80         username, password = self._get_login_info(netrc_machine=site)
  81         if username is None:
  82             return
  83
  84         login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
  85         login_page = self._download_webpage(
  86             login_url, None, 'Downloading %s login page' % site)
  87
  88         def is_logged(webpage):
  89             return any(re.search(p, webpage) for p in (
  90                 r'id="profileMenuDropdown"',
  91                 r'class="ph-icon-logout"'))
  92
  93         if is_logged(login_page):
  94             self._logged_in = True
  95             return
  96
  97         login_form = self._hidden_inputs(login_page)
  98
  99         login_form.update({
 100             'email': username,
 101             'password': password,
 102         })
 103
 104         response = self._download_json(
 105             'https://www.%s/front/authenticate' % host, None,
 106             'Logging in to %s' % site,
 107             data=urlencode_postdata(login_form),
 108             headers={
 109                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 110                 'Referer': login_url,
 111                 'X-Requested-With': 'XMLHttpRequest',
 112             })
 113
 114         if response.get('success') == '1':
 115             self._logged_in = True
 116             return
 117
 118         message = response.get('message')
 119         if message is not None:
 120             raise ExtractorError(
 121                 'Unable to login: %s' % message, expected=True)
 122
 123         raise ExtractorError('Unable to log in')
 124
 125
 126 class PornHubIE(PornHubBaseIE):
 127     IE_DESC = 'PornHub and Thumbzilla'
 128     _VALID_URL = r'''(?x)
 129                     https?://
 130                         (?:
 131                             (?:[^/]+\.)?
 132                             %s
 133                             /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
 134                             (?:www\.)?thumbzilla\.com/video/
 135                         )
 136                         (?P<id>[\da-z]+)
 137                     ''' % PornHubBaseIE._PORNHUB_HOST_RE
 138     _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
 139     _TESTS = [{
 140         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
 141         'md5': 'a6391306d050e4547f62b3f485dd9ba9',
 142         'info_dict': {
 143             'id': '648719015',
 144             'ext': 'mp4',
 145             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
 146             'uploader': 'Babes',
 147             'upload_date': '20130628',
 148             'timestamp': 1372447216,
 149             'duration': 361,
 150             'view_count': int,
 151             'like_count': int,
 152             'dislike_count': int,
 153             'comment_count': int,
 154             'age_limit': 18,
 155             'tags': list,
 156             'categories': list,
 157             'cast': list,
 158         },
 159     }, {
 160         # non-ASCII title
 161         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
 162         'info_dict': {
 163             'id': '1331683002',
 164             'ext': 'mp4',
 165             'title': '重庆婷婷女王足交',
 166             'upload_date': '20150213',
 167             'timestamp': 1423804862,
 168             'duration': 1753,
 169             'view_count': int,
 170             'like_count': int,
 171             'dislike_count': int,
 172             'comment_count': int,
 173             'age_limit': 18,
 174             'tags': list,
 175             'categories': list,
 176         },
 177         'params': {
 178             'skip_download': True,
 179         },
 180         'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
 181     }, {
 182         # subtitles
 183         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
 184         'info_dict': {
 185             'id': 'ph5af5fef7c2aa7',
 186             'ext': 'mp4',
 187             'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
 188             'uploader': 'BFFs',
 189             'duration': 622,
 190             'view_count': int,
 191             'like_count': int,
 192             'dislike_count': int,
 193             'comment_count': int,
 194             'age_limit': 18,
 195             'tags': list,
 196             'categories': list,
 197             'subtitles': {
 198                 'en': [{
 199                     "ext": 'srt'
 200                 }]
 201             },
 202         },
 203         'params': {
 204             'skip_download': True,
 205         },
 206         'skip': 'This video has been disabled',
 207     }, {
 208         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph601dc30bae19a',
 209         'info_dict': {
 210             'id': 'ph601dc30bae19a',
 211             'uploader': 'Projekt Melody',
 212             'uploader_id': 'projekt-melody',
 213             'upload_date': '20210205',
 214             'title': '"Welcome to My Pussy Mansion" - CB Stream (02/03/21)',
 215             'thumbnail': r're:https?://.+',
 216         },
 217     }, {
 218         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
 219         'only_matching': True,
 220     }, {
 221         # removed at the request of cam4.com
 222         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
 223         'only_matching': True,
 224     }, {
 225         # removed at the request of the copyright owner
 226         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
 227         'only_matching': True,
 228     }, {
 229         # removed by uploader
 230         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
 231         'only_matching': True,
 232     }, {
 233         # private video
 234         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
 235         'only_matching': True,
 236     }, {
 237         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
 238         'only_matching': True,
 239     }, {
 240         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
 241         'only_matching': True,
 242     }, {
 243         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
 244         'only_matching': True,
 245     }, {
 246         'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933',
 247         'only_matching': True,
 248     }, {
 249         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
 250         'only_matching': True,
 251     }, {
 252         # Some videos are available with the same id on both premium
 253         # and non-premium sites (e.g. this and the following test)
 254         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 255         'only_matching': True,
 256     }, {
 257         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 258         'only_matching': True,
 259     }, {
 260         # geo restricted
 261         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156',
 262         'only_matching': True,
 263     }, {
 264         'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/view_video.php?viewkey=ph5a9813bfa7156',
 265         'only_matching': True,
 266     }]
 267
 268     def _extract_count(self, pattern, webpage, name):
 269         return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
 270
 271     def _real_extract(self, url):
 272         mobj = self._match_valid_url(url)
 273         host = mobj.group('host') or 'pornhub.com'
 274         video_id = mobj.group('id')
 275
 276         self._login(host)
 277         self._set_age_cookies(host)
 278
 279         def dl_webpage(platform):
 280             self._set_cookie(host, 'platform', platform)
 281             return self._download_webpage(
 282                 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
 283                 video_id, 'Downloading %s webpage' % platform)
 284
 285         webpage = dl_webpage('pc')
 286
 287         error_msg = self._html_search_regex(
 288             (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 289              r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
 290             webpage, 'error message', default=None, group='error')
 291         if error_msg:
 292             error_msg = re.sub(r'\s+', ' ', error_msg)
 293             raise ExtractorError(
 294                 'PornHub said: %s' % error_msg,
 295                 expected=True, video_id=video_id)
 296
 297         if any(re.search(p, webpage) for p in (
 298                 r'class=["\']geoBlocked["\']',
 299                 r'>\s*This content is unavailable in your country')):
 300             self.raise_geo_restricted()
 301
 302         # video_title from flashvars contains whitespace instead of non-ASCII (see
 303         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 304         # on that anymore.
 305         title = self._html_search_meta(
 306             'twitter:title', webpage, default=None) or self._html_search_regex(
 307             (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>',
 308              r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1',
 309              r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
 310             webpage, 'title', group='title')
 311
 312         video_urls = []
 313         video_urls_set = set()
 314         subtitles = {}
 315
 316         flashvars = self._parse_json(
 317             self._search_regex(
 318                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 319             video_id)
 320         if flashvars:
 321             subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
 322             if subtitle_url:
 323                 subtitles.setdefault('en', []).append({
 324                     'url': subtitle_url,
 325                     'ext': 'srt',
 326                 })
 327             thumbnail = flashvars.get('image_url')
 328             duration = int_or_none(flashvars.get('video_duration'))
 329             media_definitions = flashvars.get('mediaDefinitions')
 330             if isinstance(media_definitions, list):
 331                 for definition in media_definitions:
 332                     if not isinstance(definition, dict):
 333                         continue
 334                     video_url = definition.get('videoUrl')
 335                     if not video_url or not isinstance(video_url, compat_str):
 336                         continue
 337                     if video_url in video_urls_set:
 338                         continue
 339                     video_urls_set.add(video_url)
 340                     video_urls.append(
 341                         (video_url, int_or_none(definition.get('quality'))))
 342         else:
 343             thumbnail, duration = [None] * 2
 344
 345         def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
 346             assignments = self._search_regex(
 347                 pattern, webpage, 'encoded url', default=default)
 348             if not assignments:
 349                 return {}
 350
 351             assignments = assignments.split(';')
 352
 353             js_vars = {}
 354
 355             def parse_js_value(inp):
 356                 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
 357                 if '+' in inp:
 358                     inps = inp.split('+')
 359                     return functools.reduce(
 360                         operator.concat, map(parse_js_value, inps))
 361                 inp = inp.strip()
 362                 if inp in js_vars:
 363                     return js_vars[inp]
 364                 return remove_quotes(inp)
 365
 366             for assn in assignments:
 367                 assn = assn.strip()
 368                 if not assn:
 369                     continue
 370                 assn = re.sub(r'var\s+', '', assn)
 371                 vname, value = assn.split('=', 1)
 372                 js_vars[vname] = parse_js_value(value)
 373             return js_vars
 374
 375         def add_video_url(video_url):
 376             v_url = url_or_none(video_url)
 377             if not v_url:
 378                 return
 379             if v_url in video_urls_set:
 380                 return
 381             video_urls.append((v_url, None))
 382             video_urls_set.add(v_url)
 383
 384         def parse_quality_items(quality_items):
 385             q_items = self._parse_json(quality_items, video_id, fatal=False)
 386             if not isinstance(q_items, list):
 387                 return
 388             for item in q_items:
 389                 if isinstance(item, dict):
 390                     add_video_url(item.get('url'))
 391
 392         if not video_urls:
 393             FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
 394             js_vars = extract_js_vars(
 395                 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
 396                 default=None)
 397             if js_vars:
 398                 for key, format_url in js_vars.items():
 399                     if key.startswith(FORMAT_PREFIXES[-1]):
 400                         parse_quality_items(format_url)
 401                     elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
 402                         add_video_url(format_url)
 403             if not video_urls and re.search(
 404                     r'<[^>]+\bid=["\']lockedPlayer', webpage):
 405                 raise ExtractorError(
 406                     'Video %s is locked' % video_id, expected=True)
 407
 408         if not video_urls:
 409             js_vars = extract_js_vars(
 410                 dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
 411             add_video_url(js_vars['mediastring'])
 412
 413         for mobj in re.finditer(
 414                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
 415                 webpage):
 416             video_url = mobj.group('url')
 417             if video_url not in video_urls_set:
 418                 video_urls.append((video_url, None))
 419                 video_urls_set.add(video_url)
 420
 421         upload_date = None
 422         formats = []
 423
 424         def add_format(format_url, height=None):
 425             ext = determine_ext(format_url)
 426             if ext == 'mpd':
 427                 formats.extend(self._extract_mpd_formats(
 428                     format_url, video_id, mpd_id='dash', fatal=False))
 429                 return
 430             if ext == 'm3u8':
 431                 formats.extend(self._extract_m3u8_formats(
 432                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 433                     m3u8_id='hls', fatal=False))
 434                 return
 435             if not height:
 436                 height = int_or_none(self._search_regex(
 437                     r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height',
 438                     default=None))
 439             formats.append({
 440                 'url': format_url,
 441                 'format_id': format_field(height, None, '%dp'),
 442                 'height': height,
 443             })
 444
 445         for video_url, height in video_urls:
 446             if not upload_date:
 447                 upload_date = self._search_regex(
 448                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
 449                 if upload_date:
 450                     upload_date = upload_date.replace('/', '')
 451             if '/video/get_media' in video_url:
 452                 medias = self._download_json(video_url, video_id, fatal=False)
 453                 if isinstance(medias, list):
 454                     for media in medias:
 455                         if not isinstance(media, dict):
 456                             continue
 457                         video_url = url_or_none(media.get('videoUrl'))
 458                         if not video_url:
 459                             continue
 460                         height = int_or_none(media.get('quality'))
 461                         add_format(video_url, height)
 462                 continue
 463             add_format(video_url)
 464
 465         model_profile = self._search_json(
 466             r'var\s+MODEL_PROFILE\s*=', webpage, 'model profile', video_id, fatal=False)
 467         video_uploader = self._html_search_regex(
 468             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
 469             webpage, 'uploader', default=None) or model_profile.get('username')
 470
 471         def extract_vote_count(kind, name):
 472             return self._extract_count(
 473                 (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
 474                  r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
 475                 webpage, name)
 476
 477         view_count = self._extract_count(
 478             r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
 479         like_count = extract_vote_count('Up', 'like')
 480         dislike_count = extract_vote_count('Down', 'dislike')
 481         comment_count = self._extract_count(
 482             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 483
 484         def extract_list(meta_key):
 485             div = self._search_regex(
 486                 r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
 487                 % meta_key, webpage, meta_key, default=None)
 488             if div:
 489                 return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
 490
 491         info = self._search_json_ld(webpage, video_id, default={})
 492         # description provided in JSON-LD is irrelevant
 493         info['description'] = None
 494
 495         return merge_dicts({
 496             'id': video_id,
 497             'uploader': video_uploader,
 498             'uploader_id': remove_start(model_profile.get('modelProfileLink'), '/model/'),
 499             'upload_date': upload_date,
 500             'title': title,
 501             'thumbnail': thumbnail,
 502             'duration': duration,
 503             'view_count': view_count,
 504             'like_count': like_count,
 505             'dislike_count': dislike_count,
 506             'comment_count': comment_count,
 507             'formats': formats,
 508             'age_limit': 18,
 509             'tags': extract_list('tags'),
 510             'categories': extract_list('categories'),
 511             'cast': extract_list('pornstars'),
 512             'subtitles': subtitles,
 513         }, info)
 514
 515
 516 class PornHubPlaylistBaseIE(PornHubBaseIE):
 517     def _extract_page(self, url):
 518         return int_or_none(self._search_regex(
 519             r'\bpage=(\d+)', url, 'page', default=None))
 520
 521     def _extract_entries(self, webpage, host):
 522         # Only process container div with main playlist content skipping
 523         # drop-down menu that uses similar pattern for videos (see
 524         # https://github.com/ytdl-org/youtube-dl/issues/11594).
 525         container = self._search_regex(
 526             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 527             'container', default=webpage)
 528
 529         return [
 530             self.url_result(
 531                 'http://www.%s/%s' % (host, video_url),
 532                 PornHubIE.ie_key(), video_title=title)
 533             for video_url, title in orderedSet(re.findall(
 534                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 535                 container))
 536         ]
 537
 538
 539 class PornHubUserIE(PornHubPlaylistBaseIE):
 540     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
 541     _TESTS = [{
 542         'url': 'https://www.pornhub.com/model/zoe_ph',
 543         'playlist_mincount': 118,
 544     }, {
 545         'url': 'https://www.pornhub.com/pornstar/liz-vicious',
 546         'info_dict': {
 547             'id': 'liz-vicious',
 548         },
 549         'playlist_mincount': 118,
 550     }, {
 551         'url': 'https://www.pornhub.com/users/russianveet69',
 552         'only_matching': True,
 553     }, {
 554         'url': 'https://www.pornhub.com/channels/povd',
 555         'only_matching': True,
 556     }, {
 557         'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
 558         'only_matching': True,
 559     }, {
 560         # Unavailable via /videos page, but available with direct pagination
 561         # on pornstar page (see [1]), requires premium
 562         # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 563         'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
 564         'only_matching': True,
 565     }, {
 566         # Same as before, multi page
 567         'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
 568         'only_matching': True,
 569     }, {
 570         'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph',
 571         'only_matching': True,
 572     }]
 573
 574     def _real_extract(self, url):
 575         mobj = self._match_valid_url(url)
 576         user_id = mobj.group('id')
 577         videos_url = '%s/videos' % mobj.group('url')
 578         self._set_age_cookies(mobj.group('host'))
 579         page = self._extract_page(url)
 580         if page:
 581             videos_url = update_url_query(videos_url, {'page': page})
 582         return self.url_result(
 583             videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
 584
 585
 586 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
 587     @staticmethod
 588     def _has_more(webpage):
 589         return re.search(
 590             r'''(?x)
 591                 <li[^>]+\bclass=["\']page_next|
 592                 <link[^>]+\brel=["\']next|
 593                 <button[^>]+\bid=["\']moreDataBtn
 594             ''', webpage) is not None
 595
 596     def _entries(self, url, host, item_id):
 597         page = self._extract_page(url)
 598
 599         VIDEOS = '/videos'
 600
 601         def download_page(base_url, num, fallback=False):
 602             note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
 603             return self._download_webpage(
 604                 base_url, item_id, note, query={'page': num})
 605
 606         def is_404(e):
 607             return isinstance(e.cause, HTTPError) and e.cause.status == 404
 608
 609         base_url = url
 610         has_page = page is not None
 611         first_page = page if has_page else 1
 612         for page_num in (first_page, ) if has_page else itertools.count(first_page):
 613             try:
 614                 try:
 615                     webpage = download_page(base_url, page_num)
 616                 except ExtractorError as e:
 617                     # Some sources may not be available via /videos page,
 618                     # trying to fallback to main page pagination (see [1])
 619                     # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 620                     if is_404(e) and page_num == first_page and VIDEOS in base_url:
 621                         base_url = base_url.replace(VIDEOS, '')
 622                         webpage = download_page(base_url, page_num, fallback=True)
 623                     else:
 624                         raise
 625             except ExtractorError as e:
 626                 if is_404(e) and page_num != first_page:
 627                     break
 628                 raise
 629             page_entries = self._extract_entries(webpage, host)
 630             if not page_entries:
 631                 break
 632             for e in page_entries:
 633                 yield e
 634             if not self._has_more(webpage):
 635                 break
 636
 637     def _real_extract(self, url):
 638         mobj = self._match_valid_url(url)
 639         host = mobj.group('host')
 640         item_id = mobj.group('id')
 641
 642         self._login(host)
 643         self._set_age_cookies(host)
 644
 645         return self.playlist_result(self._entries(url, host, item_id), item_id)
 646
 647
 648 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
 649     _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
 650     _TESTS = [{
 651         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
 652         'only_matching': True,
 653     }, {
 654         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 655         'only_matching': True,
 656     }, {
 657         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
 658         'info_dict': {
 659             'id': 'pornstar/jenny-blighe/videos',
 660         },
 661         'playlist_mincount': 149,
 662     }, {
 663         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
 664         'info_dict': {
 665             'id': 'pornstar/jenny-blighe/videos',
 666         },
 667         'playlist_mincount': 40,
 668     }, {
 669         # default sorting as Top Rated Videos
 670         'url': 'https://www.pornhub.com/channels/povd/videos',
 671         'info_dict': {
 672             'id': 'channels/povd/videos',
 673         },
 674         'playlist_mincount': 293,
 675     }, {
 676         # Top Rated Videos
 677         'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
 678         'only_matching': True,
 679     }, {
 680         # Most Recent Videos
 681         'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
 682         'only_matching': True,
 683     }, {
 684         # Most Viewed Videos
 685         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
 686         'only_matching': True,
 687     }, {
 688         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 689         'only_matching': True,
 690     }, {
 691         # Most Viewed Videos
 692         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
 693         'only_matching': True,
 694     }, {
 695         # Top Rated Videos
 696         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
 697         'only_matching': True,
 698     }, {
 699         # Longest Videos
 700         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
 701         'only_matching': True,
 702     }, {
 703         # Newest Videos
 704         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
 705         'only_matching': True,
 706     }, {
 707         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
 708         'only_matching': True,
 709     }, {
 710         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
 711         'only_matching': True,
 712     }, {
 713         'url': 'https://www.pornhub.com/video',
 714         'only_matching': True,
 715     }, {
 716         'url': 'https://www.pornhub.com/video?page=3',
 717         'only_matching': True,
 718     }, {
 719         'url': 'https://www.pornhub.com/video/search?search=123',
 720         'only_matching': True,
 721     }, {
 722         'url': 'https://www.pornhub.com/categories/teen',
 723         'only_matching': True,
 724     }, {
 725         'url': 'https://www.pornhub.com/categories/teen?page=3',
 726         'only_matching': True,
 727     }, {
 728         'url': 'https://www.pornhub.com/hd',
 729         'only_matching': True,
 730     }, {
 731         'url': 'https://www.pornhub.com/hd?page=3',
 732         'only_matching': True,
 733     }, {
 734         'url': 'https://www.pornhub.com/described-video',
 735         'only_matching': True,
 736     }, {
 737         'url': 'https://www.pornhub.com/described-video?page=2',
 738         'only_matching': True,
 739     }, {
 740         'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
 741         'only_matching': True,
 742     }, {
 743         'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos',
 744         'only_matching': True,
 745     }]
 746
 747     @classmethod
 748     def suitable(cls, url):
 749         return (False
 750                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
 751                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 752
 753
 754 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
 755     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
 756     _TESTS = [{
 757         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
 758         'info_dict': {
 759             'id': 'jenny-blighe',
 760         },
 761         'playlist_mincount': 129,
 762     }, {
 763         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
 764         'only_matching': True,
 765     }, {
 766         'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload',
 767         'only_matching': True,
 768     }]
 769
 770
 771 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 772     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
 773     _TESTS = [{
 774         'url': 'https://www.pornhub.com/playlist/44121572',
 775         'info_dict': {
 776             'id': '44121572',
 777         },
 778         'playlist_count': 77,
 779     }, {
 780         'url': 'https://www.pornhub.com/playlist/4667351',
 781         'only_matching': True,
 782     }, {
 783         'url': 'https://de.pornhub.com/playlist/4667351',
 784         'only_matching': True,
 785     }, {
 786         'url': 'https://de.pornhub.com/playlist/4667351?page=2',
 787         'only_matching': True,
 788     }]
 789
 790     def _entries(self, url, host, item_id):
 791         webpage = self._download_webpage(url, item_id, 'Downloading page 1')
 792         playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
 793         video_count = int_or_none(
 794             self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
 795         token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
 796         page_count = math.ceil((video_count - 36) / 40.) + 1
 797         page_entries = self._extract_entries(webpage, host)
 798
 799         def download_page(page_num):
 800             note = 'Downloading page {}'.format(page_num)
 801             page_url = 'https://www.{}/playlist/viewChunked'.format(host)
 802             return self._download_webpage(page_url, item_id, note, query={
 803                 'id': playlist_id,
 804                 'page': page_num,
 805                 'token': token,
 806             })
 807
 808         for page_num in range(1, page_count + 1):
 809             if page_num > 1:
 810                 webpage = download_page(page_num)
 811                 page_entries = self._extract_entries(webpage, host)
 812             if not page_entries:
 813                 break
 814             for e in page_entries:
 815                 yield e
 816
 817     def _real_extract(self, url):
 818         mobj = self._match_valid_url(url)
 819         host = mobj.group('host')
 820         item_id = mobj.group('id')
 821
 822         self._login(host)
 823         self._set_age_cookies(host)
 824
 825         return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)