yt_dlp/extractor/pornhub.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import functools
   5 import itertools
   6 import operator
   7 import re
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_HTTPError,
  12     compat_str,
  13     compat_urllib_request,
  14 )
  15 from .openload import PhantomJSwrapper
  16 from ..utils import (
  17     clean_html,
  18     determine_ext,
  19     ExtractorError,
  20     int_or_none,
  21     merge_dicts,
  22     NO_DEFAULT,
  23     orderedSet,
  24     remove_quotes,
  25     str_to_int,
  26     update_url_query,
  27     urlencode_postdata,
  28     url_or_none,
  29 )
  30
  31
  32 class PornHubBaseIE(InfoExtractor):
  33     _NETRC_MACHINE = 'pornhub'
  34     _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubthbh7ap3u\.onion)'
  35
  36     def _download_webpage_handle(self, *args, **kwargs):
  37         def dl(*args, **kwargs):
  38             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
  39
  40         ret = dl(*args, **kwargs)
  41
  42         if not ret:
  43             return ret
  44
  45         webpage, urlh = ret
  46
  47         if any(re.search(p, webpage) for p in (
  48                 r'<body\b[^>]+\bonload=["\']go\(\)',
  49                 r'document\.cookie\s*=\s*["\']RNKEY=',
  50                 r'document\.location\.reload\(true\)')):
  51             url_or_request = args[0]
  52             url = (url_or_request.get_full_url()
  53                    if isinstance(url_or_request, compat_urllib_request.Request)
  54                    else url_or_request)
  55             phantom = PhantomJSwrapper(self, required_version='2.0')
  56             phantom.get(url, html=webpage)
  57             webpage, urlh = dl(*args, **kwargs)
  58
  59         return webpage, urlh
  60
  61     def _real_initialize(self):
  62         self._logged_in = False
  63
  64     def _login(self, host):
  65         if self._logged_in:
  66             return
  67
  68         site = host.split('.')[0]
  69
  70         # Both sites pornhub and pornhubpremium have separate accounts
  71         # so there should be an option to provide credentials for both.
  72         # At the same time some videos are available under the same video id
  73         # on both sites so that we have to identify them as the same video.
  74         # For that purpose we have to keep both in the same extractor
  75         # but under different netrc machines.
  76         username, password = self._get_login_info(netrc_machine=site)
  77         if username is None:
  78             return
  79
  80         login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
  81         login_page = self._download_webpage(
  82             login_url, None, 'Downloading %s login page' % site)
  83
  84         def is_logged(webpage):
  85             return any(re.search(p, webpage) for p in (
  86                 r'class=["\']signOut',
  87                 r'>Sign\s+[Oo]ut\s*<'))
  88
  89         if is_logged(login_page):
  90             self._logged_in = True
  91             return
  92
  93         login_form = self._hidden_inputs(login_page)
  94
  95         login_form.update({
  96             'username': username,
  97             'password': password,
  98         })
  99
 100         response = self._download_json(
 101             'https://www.%s/front/authenticate' % host, None,
 102             'Logging in to %s' % site,
 103             data=urlencode_postdata(login_form),
 104             headers={
 105                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 106                 'Referer': login_url,
 107                 'X-Requested-With': 'XMLHttpRequest',
 108             })
 109
 110         if response.get('success') == '1':
 111             self._logged_in = True
 112             return
 113
 114         message = response.get('message')
 115         if message is not None:
 116             raise ExtractorError(
 117                 'Unable to login: %s' % message, expected=True)
 118
 119         raise ExtractorError('Unable to log in')
 120
 121
 122 class PornHubIE(PornHubBaseIE):
 123     IE_DESC = 'PornHub and Thumbzilla'
 124     _VALID_URL = r'''(?x)
 125                     https?://
 126                         (?:
 127                             (?:[^/]+\.)?
 128                             %s
 129                             /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
 130                             (?:www\.)?thumbzilla\.com/video/
 131                         )
 132                         (?P<id>[\da-z]+)
 133                     ''' % PornHubBaseIE._PORNHUB_HOST_RE
 134     _TESTS = [{
 135         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
 136         'md5': 'a6391306d050e4547f62b3f485dd9ba9',
 137         'info_dict': {
 138             'id': '648719015',
 139             'ext': 'mp4',
 140             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
 141             'uploader': 'Babes',
 142             'upload_date': '20130628',
 143             'timestamp': 1372447216,
 144             'duration': 361,
 145             'view_count': int,
 146             'like_count': int,
 147             'dislike_count': int,
 148             'comment_count': int,
 149             'age_limit': 18,
 150             'tags': list,
 151             'categories': list,
 152             'cast': list,
 153         },
 154     }, {
 155         # non-ASCII title
 156         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
 157         'info_dict': {
 158             'id': '1331683002',
 159             'ext': 'mp4',
 160             'title': '重庆婷婷女王足交',
 161             'upload_date': '20150213',
 162             'timestamp': 1423804862,
 163             'duration': 1753,
 164             'view_count': int,
 165             'like_count': int,
 166             'dislike_count': int,
 167             'comment_count': int,
 168             'age_limit': 18,
 169             'tags': list,
 170             'categories': list,
 171         },
 172         'params': {
 173             'skip_download': True,
 174         },
 175         'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
 176     }, {
 177         # subtitles
 178         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
 179         'info_dict': {
 180             'id': 'ph5af5fef7c2aa7',
 181             'ext': 'mp4',
 182             'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
 183             'uploader': 'BFFs',
 184             'duration': 622,
 185             'view_count': int,
 186             'like_count': int,
 187             'dislike_count': int,
 188             'comment_count': int,
 189             'age_limit': 18,
 190             'tags': list,
 191             'categories': list,
 192             'subtitles': {
 193                 'en': [{
 194                     "ext": 'srt'
 195                 }]
 196             },
 197         },
 198         'params': {
 199             'skip_download': True,
 200         },
 201         'skip': 'This video has been disabled',
 202     }, {
 203         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
 204         'only_matching': True,
 205     }, {
 206         # removed at the request of cam4.com
 207         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
 208         'only_matching': True,
 209     }, {
 210         # removed at the request of the copyright owner
 211         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
 212         'only_matching': True,
 213     }, {
 214         # removed by uploader
 215         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
 216         'only_matching': True,
 217     }, {
 218         # private video
 219         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
 220         'only_matching': True,
 221     }, {
 222         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
 223         'only_matching': True,
 224     }, {
 225         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
 226         'only_matching': True,
 227     }, {
 228         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
 229         'only_matching': True,
 230     }, {
 231         'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933',
 232         'only_matching': True,
 233     }, {
 234         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
 235         'only_matching': True,
 236     }, {
 237         # Some videos are available with the same id on both premium
 238         # and non-premium sites (e.g. this and the following test)
 239         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 240         'only_matching': True,
 241     }, {
 242         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 243         'only_matching': True,
 244     }, {
 245         # geo restricted
 246         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156',
 247         'only_matching': True,
 248     }, {
 249         'url': 'http://pornhubthbh7ap3u.onion/view_video.php?viewkey=ph5a9813bfa7156',
 250         'only_matching': True,
 251     }]
 252
 253     @staticmethod
 254     def _extract_urls(webpage):
 255         return re.findall(
 256             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
 257             webpage)
 258
 259     def _extract_count(self, pattern, webpage, name):
 260         return str_to_int(self._search_regex(
 261             pattern, webpage, '%s count' % name, fatal=False))
 262
 263     def _real_extract(self, url):
 264         mobj = re.match(self._VALID_URL, url)
 265         host = mobj.group('host') or 'pornhub.com'
 266         video_id = mobj.group('id')
 267
 268         self._login(host)
 269
 270         self._set_cookie(host, 'age_verified', '1')
 271
 272         def dl_webpage(platform):
 273             self._set_cookie(host, 'platform', platform)
 274             return self._download_webpage(
 275                 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
 276                 video_id, 'Downloading %s webpage' % platform)
 277
 278         webpage = dl_webpage('pc')
 279
 280         error_msg = self._html_search_regex(
 281             (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 282              r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
 283             webpage, 'error message', default=None, group='error')
 284         if error_msg:
 285             error_msg = re.sub(r'\s+', ' ', error_msg)
 286             raise ExtractorError(
 287                 'PornHub said: %s' % error_msg,
 288                 expected=True, video_id=video_id)
 289
 290         if any(re.search(p, webpage) for p in (
 291                 r'class=["\']geoBlocked["\']',
 292                 r'>\s*This content is unavailable in your country')):
 293             self.raise_geo_restricted()
 294
 295         # video_title from flashvars contains whitespace instead of non-ASCII (see
 296         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 297         # on that anymore.
 298         title = self._html_search_meta(
 299             'twitter:title', webpage, default=None) or self._html_search_regex(
 300             (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>',
 301              r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1',
 302              r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
 303             webpage, 'title', group='title')
 304
 305         video_urls = []
 306         video_urls_set = set()
 307         subtitles = {}
 308
 309         flashvars = self._parse_json(
 310             self._search_regex(
 311                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 312             video_id)
 313         if flashvars:
 314             subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
 315             if subtitle_url:
 316                 subtitles.setdefault('en', []).append({
 317                     'url': subtitle_url,
 318                     'ext': 'srt',
 319                 })
 320             thumbnail = flashvars.get('image_url')
 321             duration = int_or_none(flashvars.get('video_duration'))
 322             media_definitions = flashvars.get('mediaDefinitions')
 323             if isinstance(media_definitions, list):
 324                 for definition in media_definitions:
 325                     if not isinstance(definition, dict):
 326                         continue
 327                     video_url = definition.get('videoUrl')
 328                     if not video_url or not isinstance(video_url, compat_str):
 329                         continue
 330                     if video_url in video_urls_set:
 331                         continue
 332                     video_urls_set.add(video_url)
 333                     video_urls.append(
 334                         (video_url, int_or_none(definition.get('quality'))))
 335         else:
 336             thumbnail, duration = [None] * 2
 337
 338         def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
 339             assignments = self._search_regex(
 340                 pattern, webpage, 'encoded url', default=default)
 341             if not assignments:
 342                 return {}
 343
 344             assignments = assignments.split(';')
 345
 346             js_vars = {}
 347
 348             def parse_js_value(inp):
 349                 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
 350                 if '+' in inp:
 351                     inps = inp.split('+')
 352                     return functools.reduce(
 353                         operator.concat, map(parse_js_value, inps))
 354                 inp = inp.strip()
 355                 if inp in js_vars:
 356                     return js_vars[inp]
 357                 return remove_quotes(inp)
 358
 359             for assn in assignments:
 360                 assn = assn.strip()
 361                 if not assn:
 362                     continue
 363                 assn = re.sub(r'var\s+', '', assn)
 364                 vname, value = assn.split('=', 1)
 365                 js_vars[vname] = parse_js_value(value)
 366             return js_vars
 367
 368         def add_video_url(video_url):
 369             v_url = url_or_none(video_url)
 370             if not v_url:
 371                 return
 372             if v_url in video_urls_set:
 373                 return
 374             video_urls.append((v_url, None))
 375             video_urls_set.add(v_url)
 376
 377         def parse_quality_items(quality_items):
 378             q_items = self._parse_json(quality_items, video_id, fatal=False)
 379             if not isinstance(q_items, list):
 380                 return
 381             for item in q_items:
 382                 if isinstance(item, dict):
 383                     add_video_url(item.get('url'))
 384
 385         if not video_urls:
 386             FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
 387             js_vars = extract_js_vars(
 388                 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
 389                 default=None)
 390             if js_vars:
 391                 for key, format_url in js_vars.items():
 392                     if key.startswith(FORMAT_PREFIXES[-1]):
 393                         parse_quality_items(format_url)
 394                     elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
 395                         add_video_url(format_url)
 396             if not video_urls and re.search(
 397                     r'<[^>]+\bid=["\']lockedPlayer', webpage):
 398                 raise ExtractorError(
 399                     'Video %s is locked' % video_id, expected=True)
 400
 401         if not video_urls:
 402             js_vars = extract_js_vars(
 403                 dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
 404             add_video_url(js_vars['mediastring'])
 405
 406         for mobj in re.finditer(
 407                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
 408                 webpage):
 409             video_url = mobj.group('url')
 410             if video_url not in video_urls_set:
 411                 video_urls.append((video_url, None))
 412                 video_urls_set.add(video_url)
 413
 414         upload_date = None
 415         formats = []
 416
 417         def add_format(format_url, height=None):
 418             ext = determine_ext(format_url)
 419             if ext == 'mpd':
 420                 formats.extend(self._extract_mpd_formats(
 421                     format_url, video_id, mpd_id='dash', fatal=False))
 422                 return
 423             if ext == 'm3u8':
 424                 formats.extend(self._extract_m3u8_formats(
 425                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 426                     m3u8_id='hls', fatal=False))
 427                 return
 428             if not height:
 429                 height = int_or_none(self._search_regex(
 430                     r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height',
 431                     default=None))
 432             formats.append({
 433                 'url': format_url,
 434                 'format_id': '%dp' % height if height else None,
 435                 'height': height,
 436             })
 437
 438         for video_url, height in video_urls:
 439             if not upload_date:
 440                 upload_date = self._search_regex(
 441                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
 442                 if upload_date:
 443                     upload_date = upload_date.replace('/', '')
 444             if '/video/get_media' in video_url:
 445                 medias = self._download_json(video_url, video_id, fatal=False)
 446                 if isinstance(medias, list):
 447                     for media in medias:
 448                         if not isinstance(media, dict):
 449                             continue
 450                         video_url = url_or_none(media.get('videoUrl'))
 451                         if not video_url:
 452                             continue
 453                         height = int_or_none(media.get('quality'))
 454                         add_format(video_url, height)
 455                 continue
 456             add_format(video_url)
 457
 458         # field_preference is unnecessary here, but kept for code-similarity with youtube-dl
 459         self._sort_formats(
 460             formats, field_preference=('height', 'width', 'fps', 'format_id'))
 461
 462         video_uploader = self._html_search_regex(
 463             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
 464             webpage, 'uploader', default=None)
 465
 466         def extract_vote_count(kind, name):
 467             return self._extract_count(
 468                 (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
 469                  r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
 470                 webpage, name)
 471
 472         view_count = self._extract_count(
 473             r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
 474         like_count = extract_vote_count('Up', 'like')
 475         dislike_count = extract_vote_count('Down', 'dislike')
 476         comment_count = self._extract_count(
 477             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 478
 479         def extract_list(meta_key):
 480             div = self._search_regex(
 481                 r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
 482                 % meta_key, webpage, meta_key, default=None)
 483             if div:
 484                 return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
 485
 486         info = self._search_json_ld(webpage, video_id, default={})
 487         # description provided in JSON-LD is irrelevant
 488         info['description'] = None
 489
 490         return merge_dicts({
 491             'id': video_id,
 492             'uploader': video_uploader,
 493             'upload_date': upload_date,
 494             'title': title,
 495             'thumbnail': thumbnail,
 496             'duration': duration,
 497             'view_count': view_count,
 498             'like_count': like_count,
 499             'dislike_count': dislike_count,
 500             'comment_count': comment_count,
 501             'formats': formats,
 502             'age_limit': 18,
 503             'tags': extract_list('tags'),
 504             'categories': extract_list('categories'),
 505             'cast': extract_list('pornstars'),
 506             'subtitles': subtitles,
 507         }, info)
 508
 509
 510 class PornHubPlaylistBaseIE(PornHubBaseIE):
 511     def _extract_page(self, url):
 512         return int_or_none(self._search_regex(
 513             r'\bpage=(\d+)', url, 'page', default=None))
 514
 515     def _extract_entries(self, webpage, host):
 516         # Only process container div with main playlist content skipping
 517         # drop-down menu that uses similar pattern for videos (see
 518         # https://github.com/ytdl-org/youtube-dl/issues/11594).
 519         container = self._search_regex(
 520             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 521             'container', default=webpage)
 522
 523         return [
 524             self.url_result(
 525                 'http://www.%s/%s' % (host, video_url),
 526                 PornHubIE.ie_key(), video_title=title)
 527             for video_url, title in orderedSet(re.findall(
 528                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 529                 container))
 530         ]
 531
 532
 533 class PornHubUserIE(PornHubPlaylistBaseIE):
 534     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
 535     _TESTS = [{
 536         'url': 'https://www.pornhub.com/model/zoe_ph',
 537         'playlist_mincount': 118,
 538     }, {
 539         'url': 'https://www.pornhub.com/pornstar/liz-vicious',
 540         'info_dict': {
 541             'id': 'liz-vicious',
 542         },
 543         'playlist_mincount': 118,
 544     }, {
 545         'url': 'https://www.pornhub.com/users/russianveet69',
 546         'only_matching': True,
 547     }, {
 548         'url': 'https://www.pornhub.com/channels/povd',
 549         'only_matching': True,
 550     }, {
 551         'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
 552         'only_matching': True,
 553     }, {
 554         # Unavailable via /videos page, but available with direct pagination
 555         # on pornstar page (see [1]), requires premium
 556         # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 557         'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
 558         'only_matching': True,
 559     }, {
 560         # Same as before, multi page
 561         'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
 562         'only_matching': True,
 563     }, {
 564         'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph',
 565         'only_matching': True,
 566     }]
 567
 568     def _real_extract(self, url):
 569         mobj = re.match(self._VALID_URL, url)
 570         user_id = mobj.group('id')
 571         videos_url = '%s/videos' % mobj.group('url')
 572         page = self._extract_page(url)
 573         if page:
 574             videos_url = update_url_query(videos_url, {'page': page})
 575         return self.url_result(
 576             videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
 577
 578
 579 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
 580     @staticmethod
 581     def _has_more(webpage):
 582         return re.search(
 583             r'''(?x)
 584                 <li[^>]+\bclass=["\']page_next|
 585                 <link[^>]+\brel=["\']next|
 586                 <button[^>]+\bid=["\']moreDataBtn
 587             ''', webpage) is not None
 588
 589     def _entries(self, url, host, item_id):
 590         page = self._extract_page(url)
 591
 592         VIDEOS = '/videos'
 593
 594         def download_page(base_url, num, fallback=False):
 595             note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
 596             return self._download_webpage(
 597                 base_url, item_id, note, query={'page': num})
 598
 599         def is_404(e):
 600             return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
 601
 602         base_url = url
 603         has_page = page is not None
 604         first_page = page if has_page else 1
 605         for page_num in (first_page, ) if has_page else itertools.count(first_page):
 606             try:
 607                 try:
 608                     webpage = download_page(base_url, page_num)
 609                 except ExtractorError as e:
 610                     # Some sources may not be available via /videos page,
 611                     # trying to fallback to main page pagination (see [1])
 612                     # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 613                     if is_404(e) and page_num == first_page and VIDEOS in base_url:
 614                         base_url = base_url.replace(VIDEOS, '')
 615                         webpage = download_page(base_url, page_num, fallback=True)
 616                     else:
 617                         raise
 618             except ExtractorError as e:
 619                 if is_404(e) and page_num != first_page:
 620                     break
 621                 raise
 622             page_entries = self._extract_entries(webpage, host)
 623             if not page_entries:
 624                 break
 625             for e in page_entries:
 626                 yield e
 627             if not self._has_more(webpage):
 628                 break
 629
 630     def _real_extract(self, url):
 631         mobj = re.match(self._VALID_URL, url)
 632         host = mobj.group('host')
 633         item_id = mobj.group('id')
 634
 635         self._login(host)
 636
 637         return self.playlist_result(self._entries(url, host, item_id), item_id)
 638
 639
 640 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
 641     _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
 642     _TESTS = [{
 643         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
 644         'only_matching': True,
 645     }, {
 646         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 647         'only_matching': True,
 648     }, {
 649         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
 650         'info_dict': {
 651             'id': 'pornstar/jenny-blighe/videos',
 652         },
 653         'playlist_mincount': 149,
 654     }, {
 655         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
 656         'info_dict': {
 657             'id': 'pornstar/jenny-blighe/videos',
 658         },
 659         'playlist_mincount': 40,
 660     }, {
 661         # default sorting as Top Rated Videos
 662         'url': 'https://www.pornhub.com/channels/povd/videos',
 663         'info_dict': {
 664             'id': 'channels/povd/videos',
 665         },
 666         'playlist_mincount': 293,
 667     }, {
 668         # Top Rated Videos
 669         'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
 670         'only_matching': True,
 671     }, {
 672         # Most Recent Videos
 673         'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
 674         'only_matching': True,
 675     }, {
 676         # Most Viewed Videos
 677         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
 678         'only_matching': True,
 679     }, {
 680         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 681         'only_matching': True,
 682     }, {
 683         # Most Viewed Videos
 684         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
 685         'only_matching': True,
 686     }, {
 687         # Top Rated Videos
 688         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
 689         'only_matching': True,
 690     }, {
 691         # Longest Videos
 692         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
 693         'only_matching': True,
 694     }, {
 695         # Newest Videos
 696         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
 697         'only_matching': True,
 698     }, {
 699         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
 700         'only_matching': True,
 701     }, {
 702         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
 703         'only_matching': True,
 704     }, {
 705         'url': 'https://www.pornhub.com/video',
 706         'only_matching': True,
 707     }, {
 708         'url': 'https://www.pornhub.com/video?page=3',
 709         'only_matching': True,
 710     }, {
 711         'url': 'https://www.pornhub.com/video/search?search=123',
 712         'only_matching': True,
 713     }, {
 714         'url': 'https://www.pornhub.com/categories/teen',
 715         'only_matching': True,
 716     }, {
 717         'url': 'https://www.pornhub.com/categories/teen?page=3',
 718         'only_matching': True,
 719     }, {
 720         'url': 'https://www.pornhub.com/hd',
 721         'only_matching': True,
 722     }, {
 723         'url': 'https://www.pornhub.com/hd?page=3',
 724         'only_matching': True,
 725     }, {
 726         'url': 'https://www.pornhub.com/described-video',
 727         'only_matching': True,
 728     }, {
 729         'url': 'https://www.pornhub.com/described-video?page=2',
 730         'only_matching': True,
 731     }, {
 732         'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
 733         'only_matching': True,
 734     }, {
 735         'url': 'https://www.pornhub.com/playlist/44121572',
 736         'info_dict': {
 737             'id': 'playlist/44121572',
 738         },
 739         'playlist_mincount': 132,
 740     }, {
 741         'url': 'https://www.pornhub.com/playlist/4667351',
 742         'only_matching': True,
 743     }, {
 744         'url': 'https://de.pornhub.com/playlist/4667351',
 745         'only_matching': True,
 746     }, {
 747         'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph/videos',
 748         'only_matching': True,
 749     }]
 750
 751     @classmethod
 752     def suitable(cls, url):
 753         return (False
 754                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
 755                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 756
 757
 758 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
 759     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
 760     _TESTS = [{
 761         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
 762         'info_dict': {
 763             'id': 'jenny-blighe',
 764         },
 765         'playlist_mincount': 129,
 766     }, {
 767         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
 768         'only_matching': True,
 769     }, {
 770         'url': 'http://pornhubthbh7ap3u.onion/pornstar/jenny-blighe/videos/upload',
 771         'only_matching': True,
 772     }]