yt_dlp/extractor/pornhub.py

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