yt_dlp/extractor/xhamster.py

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