yt_dlp/extractor/xhamster.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     clean_html,
   8     determine_ext,
   9     dict_get,
  10     extract_attributes,
  11     float_or_none,
  12     int_or_none,
  13     parse_duration,
  14     str_or_none,
  15     try_get,
  16     unified_strdate,
  17     url_or_none,
  18     urljoin,
  19 )
  20
  21
  22 class XHamsterIE(InfoExtractor):
  23     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
  24     _VALID_URL = rf'''(?x)
  25                     https?://
  26                         (?:[^/?#]+\.)?{_DOMAINS}/
  27                         (?:
  28                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
  29                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
  30                         )
  31                     '''
  32     _TESTS = [{
  33         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  34         'md5': '34e1ab926db5dc2750fed9e1f34304bb',
  35         'info_dict': {
  36             'id': '1509445',
  37             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  38             'ext': 'mp4',
  39             'title': 'FemaleAgent Shy beauty takes the bait',
  40             'timestamp': 1350194821,
  41             'upload_date': '20121014',
  42             'uploader': 'Ruseful2011',
  43             'uploader_id': 'ruseful2011',
  44             'duration': 893,
  45             'age_limit': 18,
  46         },
  47     }, {
  48         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  49         'info_dict': {
  50             'id': '2221348',
  51             'display_id': 'britney-spears-sexy-booty',
  52             'ext': 'mp4',
  53             'title': 'Britney Spears  Sexy Booty',
  54             'timestamp': 1379123460,
  55             'upload_date': '20130914',
  56             'uploader': 'jojo747400',
  57             'duration': 200,
  58             'age_limit': 18,
  59         },
  60         'params': {
  61             'skip_download': True,
  62         },
  63     }, {
  64         # empty seo, unavailable via new URL schema
  65         'url': 'http://xhamster.com/movies/5667973/.html',
  66         'info_dict': {
  67             'id': '5667973',
  68             'ext': 'mp4',
  69             'title': '....',
  70             'timestamp': 1454948101,
  71             'upload_date': '20160208',
  72             'uploader': 'parejafree',
  73             'uploader_id': 'parejafree',
  74             'duration': 72,
  75             'age_limit': 18,
  76         },
  77         'params': {
  78             'skip_download': True,
  79         },
  80     }, {
  81         # mobile site
  82         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  83         'only_matching': True,
  84     }, {
  85         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  86         'only_matching': True,
  87     }, {
  88         # This video is visible for marcoalfa123456's friends only
  89         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  90         'only_matching': True,
  91     }, {
  92         # new URL schema
  93         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  94         'only_matching': True,
  95     }, {
  96         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  97         'only_matching': True,
  98     }, {
  99         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 100         'only_matching': True,
 101     }, {
 102         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 103         'only_matching': True,
 104     }, {
 105         'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 106         'only_matching': True,
 107     }, {
 108         'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 109         'only_matching': True,
 110     }, {
 111         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 112         'only_matching': True,
 113     }, {
 114         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 115         'only_matching': True,
 116     }, {
 117         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
 118         'only_matching': True,
 119     }, {
 120         'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
 121         'only_matching': True,
 122     }, {
 123         'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
 124         'only_matching': True,
 125     }]
 126
 127     def _real_extract(self, url):
 128         mobj = self._match_valid_url(url)
 129         video_id = mobj.group('id') or mobj.group('id_2')
 130         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 131
 132         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 133         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 134
 135         error = self._html_search_regex(
 136             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 137             webpage, 'error', default=None)
 138         if error:
 139             raise ExtractorError(error, expected=True)
 140
 141         age_limit = self._rta_search(webpage)
 142
 143         def get_height(s):
 144             return int_or_none(self._search_regex(
 145                 r'^(\d+)[pP]', s, 'height', default=None))
 146
 147         initials = self._parse_json(
 148             self._search_regex(
 149                 (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
 150                  r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
 151                 default='{}'),
 152             video_id, fatal=False)
 153         if initials:
 154             video = initials['videoModel']
 155             title = video['title']
 156             formats = []
 157             format_urls = set()
 158             format_sizes = {}
 159             sources = try_get(video, lambda x: x['sources'], dict) or {}
 160             for format_id, formats_dict in sources.items():
 161                 if not isinstance(formats_dict, dict):
 162                     continue
 163                 download_sources = try_get(sources, lambda x: x['download'], dict) or {}
 164                 for quality, format_dict in download_sources.items():
 165                     if not isinstance(format_dict, dict):
 166                         continue
 167                     format_sizes[quality] = float_or_none(format_dict.get('size'))
 168                 for quality, format_item in formats_dict.items():
 169                     if format_id == 'download':
 170                         # Download link takes some time to be generated,
 171                         # skipping for now
 172                         continue
 173                     format_url = format_item
 174                     format_url = url_or_none(format_url)
 175                     if not format_url or format_url in format_urls:
 176                         continue
 177                     format_urls.add(format_url)
 178                     formats.append({
 179                         'format_id': f'{format_id}-{quality}',
 180                         'url': format_url,
 181                         'ext': determine_ext(format_url, 'mp4'),
 182                         'height': get_height(quality),
 183                         'filesize': format_sizes.get(quality),
 184                         'http_headers': {
 185                             'Referer': urlh.url,
 186                         },
 187                     })
 188             xplayer_sources = try_get(
 189                 initials, lambda x: x['xplayerSettings']['sources'], dict)
 190             if xplayer_sources:
 191                 hls_sources = xplayer_sources.get('hls')
 192                 if isinstance(hls_sources, dict):
 193                     for hls_format_key in ('url', 'fallback'):
 194                         hls_url = hls_sources.get(hls_format_key)
 195                         if not hls_url:
 196                             continue
 197                         hls_url = urljoin(url, hls_url)
 198                         if not hls_url or hls_url in format_urls:
 199                             continue
 200                         format_urls.add(hls_url)
 201                         formats.extend(self._extract_m3u8_formats(
 202                             hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 203                             m3u8_id='hls', fatal=False))
 204                 standard_sources = xplayer_sources.get('standard')
 205                 if isinstance(standard_sources, dict):
 206                     for format_id, formats_list in standard_sources.items():
 207                         if not isinstance(formats_list, list):
 208                             continue
 209                         for standard_format in formats_list:
 210                             if not isinstance(standard_format, dict):
 211                                 continue
 212                             for standard_format_key in ('url', 'fallback'):
 213                                 standard_url = standard_format.get(standard_format_key)
 214                                 if not standard_url:
 215                                     continue
 216                                 standard_url = urljoin(url, standard_url)
 217                                 if not standard_url or standard_url in format_urls:
 218                                     continue
 219                                 format_urls.add(standard_url)
 220                                 ext = determine_ext(standard_url, 'mp4')
 221                                 if ext == 'm3u8':
 222                                     formats.extend(self._extract_m3u8_formats(
 223                                         standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
 224                                         m3u8_id='hls', fatal=False))
 225                                     continue
 226                                 quality = (str_or_none(standard_format.get('quality'))
 227                                            or str_or_none(standard_format.get('label'))
 228                                            or '')
 229                                 formats.append({
 230                                     'format_id': f'{format_id}-{quality}',
 231                                     'url': standard_url,
 232                                     'ext': ext,
 233                                     'height': get_height(quality),
 234                                     'filesize': format_sizes.get(quality),
 235                                     'http_headers': {
 236                                         'Referer': standard_url,
 237                                     },
 238                                 })
 239
 240             categories_list = video.get('categories')
 241             if isinstance(categories_list, list):
 242                 categories = []
 243                 for c in categories_list:
 244                     if not isinstance(c, dict):
 245                         continue
 246                     c_name = c.get('name')
 247                     if isinstance(c_name, str):
 248                         categories.append(c_name)
 249             else:
 250                 categories = None
 251
 252             uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
 253             return {
 254                 'id': video_id,
 255                 'display_id': display_id,
 256                 'title': title,
 257                 'description': video.get('description'),
 258                 'timestamp': int_or_none(video.get('created')),
 259                 'uploader': try_get(
 260                     video, lambda x: x['author']['name'], str),
 261                 'uploader_url': uploader_url,
 262                 'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
 263                 'thumbnail': video.get('thumbURL'),
 264                 'duration': int_or_none(video.get('duration')),
 265                 'view_count': int_or_none(video.get('views')),
 266                 'like_count': int_or_none(try_get(
 267                     video, lambda x: x['rating']['likes'], int)),
 268                 'dislike_count': int_or_none(try_get(
 269                     video, lambda x: x['rating']['dislikes'], int)),
 270                 'comment_count': int_or_none(video.get('views')),
 271                 'age_limit': age_limit if age_limit is not None else 18,
 272                 'categories': categories,
 273                 'formats': formats,
 274             }
 275
 276         # Old layout fallback
 277
 278         title = self._html_search_regex(
 279             [r'<h1[^>]*>([^<]+)</h1>',
 280              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 281              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 282             webpage, 'title')
 283
 284         formats = []
 285         format_urls = set()
 286
 287         sources = self._parse_json(
 288             self._search_regex(
 289                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 290                 default='{}'),
 291             video_id, fatal=False)
 292         for format_id, format_url in sources.items():
 293             format_url = url_or_none(format_url)
 294             if not format_url:
 295                 continue
 296             if format_url in format_urls:
 297                 continue
 298             format_urls.add(format_url)
 299             formats.append({
 300                 'format_id': format_id,
 301                 'url': format_url,
 302                 'height': get_height(format_id),
 303             })
 304
 305         video_url = self._search_regex(
 306             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 307              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 308              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 309             webpage, 'video url', group='mp4', default=None)
 310         if video_url and video_url not in format_urls:
 311             formats.append({
 312                 'url': video_url,
 313             })
 314
 315         # Only a few videos have an description
 316         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 317         description = mobj.group(1) if mobj else None
 318
 319         upload_date = unified_strdate(self._search_regex(
 320             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 321             webpage, 'upload date', fatal=False))
 322
 323         uploader = self._html_search_regex(
 324             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 325             webpage, 'uploader', default='anonymous')
 326
 327         thumbnail = self._search_regex(
 328             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 329              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 330             webpage, 'thumbnail', fatal=False, group='thumbnail')
 331
 332         duration = parse_duration(self._search_regex(
 333             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 334              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 335             'duration', fatal=False))
 336
 337         view_count = int_or_none(self._search_regex(
 338             r'content=["\']User(?:View|Play)s:(\d+)',
 339             webpage, 'view count', fatal=False))
 340
 341         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 342         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 343
 344         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 345         comment_count = mobj.group('commentcount') if mobj else 0
 346
 347         categories_html = self._search_regex(
 348             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 349             'categories', default=None)
 350         categories = [clean_html(category) for category in re.findall(
 351             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 352
 353         return {
 354             'id': video_id,
 355             'display_id': display_id,
 356             'title': title,
 357             'description': description,
 358             'upload_date': upload_date,
 359             'uploader': uploader,
 360             'uploader_id': uploader.lower() if uploader else None,
 361             'thumbnail': thumbnail,
 362             'duration': duration,
 363             'view_count': view_count,
 364             'like_count': int_or_none(like_count),
 365             'dislike_count': int_or_none(dislike_count),
 366             'comment_count': int_or_none(comment_count),
 367             'age_limit': age_limit,
 368             'categories': categories,
 369             'formats': formats,
 370         }
 371
 372
 373 class XHamsterEmbedIE(InfoExtractor):
 374     _VALID_URL = rf'https?://(?:[^/?#]+\.)?{XHamsterIE._DOMAINS}/xembed\.php\?video=(?P<id>\d+)'
 375     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1']
 376     _TEST = {
 377         'url': 'http://xhamster.com/xembed.php?video=3328539',
 378         'info_dict': {
 379             'id': '3328539',
 380             'ext': 'mp4',
 381             'title': 'Pen Masturbation',
 382             'timestamp': 1406581861,
 383             'upload_date': '20140728',
 384             'uploader': 'ManyakisArt',
 385             'duration': 5,
 386             'age_limit': 18,
 387         },
 388     }
 389
 390     def _real_extract(self, url):
 391         video_id = self._match_id(url)
 392
 393         webpage = self._download_webpage(url, video_id)
 394
 395         video_url = self._search_regex(
 396             rf'href="(https?://xhamster\.com/(?:movies/{video_id}/[^"]*\.html|videos/[^/]*-{video_id})[^"]*)"',
 397             webpage, 'xhamster url', default=None)
 398
 399         if not video_url:
 400             player_vars = self._parse_json(
 401                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 402                 video_id)
 403             video_url = dict_get(player_vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 404
 405         return self.url_result(video_url, 'XHamster')
 406
 407
 408 class XHamsterUserIE(InfoExtractor):
 409     _VALID_URL = rf'https?://(?:[^/?#]+\.)?{XHamsterIE._DOMAINS}/(?:(?P<user>users)|creators)/(?P<id>[^/?#&]+)'
 410     _TESTS = [{
 411         # Paginated user profile
 412         'url': 'https://xhamster.com/users/netvideogirls/videos',
 413         'info_dict': {
 414             'id': 'netvideogirls',
 415         },
 416         'playlist_mincount': 267,
 417     }, {
 418         # Non-paginated user profile
 419         'url': 'https://xhamster.com/users/firatkaan/videos',
 420         'info_dict': {
 421             'id': 'firatkaan',
 422         },
 423         'playlist_mincount': 1,
 424     }, {
 425         'url': 'https://xhamster.com/creators/squirt-orgasm-69',
 426         'info_dict': {
 427             'id': 'squirt-orgasm-69',
 428         },
 429         'playlist_mincount': 150,
 430     }, {
 431         'url': 'https://xhday.com/users/mobhunter',
 432         'only_matching': True,
 433     }, {
 434         'url': 'https://xhvid.com/users/pelushe21',
 435         'only_matching': True,
 436     }]
 437
 438     def _entries(self, user_id, is_user):
 439         prefix, suffix = ('users', 'videos') if is_user else ('creators', 'exclusive')
 440         next_page_url = f'https://xhamster.com/{prefix}/{user_id}/{suffix}/1'
 441         for pagenum in itertools.count(1):
 442             page = self._download_webpage(
 443                 next_page_url, user_id, f'Downloading page {pagenum}')
 444             for video_tag in re.findall(
 445                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 446                     page):
 447                 video = extract_attributes(video_tag)
 448                 video_url = url_or_none(video.get('href'))
 449                 if not video_url or not XHamsterIE.suitable(video_url):
 450                     continue
 451                 video_id = XHamsterIE._match_id(video_url)
 452                 yield self.url_result(
 453                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 454             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 455             if not mobj:
 456                 break
 457             next_page = extract_attributes(mobj.group(0))
 458             next_page_url = url_or_none(next_page.get('href'))
 459             if not next_page_url:
 460                 break
 461
 462     def _real_extract(self, url):
 463         user, user_id = self._match_valid_url(url).group('user', 'id')
 464         return self.playlist_result(self._entries(user_id, bool(user)), user_id)