_ Git - youtube-dl/blob - youtube_dl/extractor/xhamster.py

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     clean_html,
  10     determine_ext,
  11     dict_get,
  12     extract_attributes,
  13     ExtractorError,
  14     int_or_none,
  15     parse_duration,
  16     try_get,
  17     unified_strdate,
  18     url_or_none,
  19 )
  20
  21
  22 class XHamsterIE(InfoExtractor):
  23     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
  24     _VALID_URL = r'''(?x)
  25                     https?://
  26                         (?:.+?\.)?%s/
  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                     ''' % _DOMAINS
  32     _TESTS = [{
  33         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  34         'md5': '98b4687efb1ffd331c4197854dc09e8f',
  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             'duration': 893,
  44             'age_limit': 18,
  45         },
  46     }, {
  47         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  48         'info_dict': {
  49             'id': '2221348',
  50             'display_id': 'britney-spears-sexy-booty',
  51             'ext': 'mp4',
  52             'title': 'Britney Spears  Sexy Booty',
  53             'timestamp': 1379123460,
  54             'upload_date': '20130914',
  55             'uploader': 'jojo747400',
  56             'duration': 200,
  57             'age_limit': 18,
  58         },
  59         'params': {
  60             'skip_download': True,
  61         },
  62     }, {
  63         # empty seo, unavailable via new URL schema
  64         'url': 'http://xhamster.com/movies/5667973/.html',
  65         'info_dict': {
  66             'id': '5667973',
  67             'ext': 'mp4',
  68             'title': '....',
  69             'timestamp': 1454948101,
  70             'upload_date': '20160208',
  71             'uploader': 'parejafree',
  72             'duration': 72,
  73             'age_limit': 18,
  74         },
  75         'params': {
  76             'skip_download': True,
  77         },
  78     }, {
  79         # mobile site
  80         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  81         'only_matching': True,
  82     }, {
  83         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  84         'only_matching': True,
  85     }, {
  86         # This video is visible for marcoalfa123456's friends only
  87         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  88         'only_matching': True,
  89     }, {
  90         # new URL schema
  91         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  92         'only_matching': True,
  93     }, {
  94         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  95         'only_matching': True,
  96     }, {
  97         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  98         'only_matching': True,
  99     }, {
 100         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 101         'only_matching': True,
 102     }, {
 103         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 104         'only_matching': True,
 105     }, {
 106         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 107         'only_matching': True,
 108     }, {
 109         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
 110         'only_matching': True,
 111     }]
 112
 113     def _real_extract(self, url):
 114         mobj = re.match(self._VALID_URL, url)
 115         video_id = mobj.group('id') or mobj.group('id_2')
 116         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 117
 118         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 119         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 120
 121         error = self._html_search_regex(
 122             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 123             webpage, 'error', default=None)
 124         if error:
 125             raise ExtractorError(error, expected=True)
 126
 127         age_limit = self._rta_search(webpage)
 128
 129         def get_height(s):
 130             return int_or_none(self._search_regex(
 131                 r'^(\d+)[pP]', s, 'height', default=None))
 132
 133         initials = self._parse_json(
 134             self._search_regex(
 135                 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
 136                 default='{}'),
 137             video_id, fatal=False)
 138         if initials:
 139             video = initials['videoModel']
 140             title = video['title']
 141             formats = []
 142             for format_id, formats_dict in video['sources'].items():
 143                 if not isinstance(formats_dict, dict):
 144                     continue
 145                 for quality, format_item in formats_dict.items():
 146                     if format_id == 'download':
 147                         # Download link takes some time to be generated,
 148                         # skipping for now
 149                         continue
 150                         if not isinstance(format_item, dict):
 151                             continue
 152                         format_url = format_item.get('link')
 153                         filesize = int_or_none(
 154                             format_item.get('size'), invscale=1000000)
 155                     else:
 156                         format_url = format_item
 157                         filesize = None
 158                     format_url = url_or_none(format_url)
 159                     if not format_url:
 160                         continue
 161                     formats.append({
 162                         'format_id': '%s-%s' % (format_id, quality),
 163                         'url': format_url,
 164                         'ext': determine_ext(format_url, 'mp4'),
 165                         'height': get_height(quality),
 166                         'filesize': filesize,
 167                         'http_headers': {
 168                             'Referer': urlh.geturl(),
 169                         },
 170                     })
 171             self._sort_formats(formats)
 172
 173             categories_list = video.get('categories')
 174             if isinstance(categories_list, list):
 175                 categories = []
 176                 for c in categories_list:
 177                     if not isinstance(c, dict):
 178                         continue
 179                     c_name = c.get('name')
 180                     if isinstance(c_name, compat_str):
 181                         categories.append(c_name)
 182             else:
 183                 categories = None
 184
 185             return {
 186                 'id': video_id,
 187                 'display_id': display_id,
 188                 'title': title,
 189                 'description': video.get('description'),
 190                 'timestamp': int_or_none(video.get('created')),
 191                 'uploader': try_get(
 192                     video, lambda x: x['author']['name'], compat_str),
 193                 'thumbnail': video.get('thumbURL'),
 194                 'duration': int_or_none(video.get('duration')),
 195                 'view_count': int_or_none(video.get('views')),
 196                 'like_count': int_or_none(try_get(
 197                     video, lambda x: x['rating']['likes'], int)),
 198                 'dislike_count': int_or_none(try_get(
 199                     video, lambda x: x['rating']['dislikes'], int)),
 200                 'comment_count': int_or_none(video.get('views')),
 201                 'age_limit': age_limit,
 202                 'categories': categories,
 203                 'formats': formats,
 204             }
 205
 206         # Old layout fallback
 207
 208         title = self._html_search_regex(
 209             [r'<h1[^>]*>([^<]+)</h1>',
 210              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 211              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 212             webpage, 'title')
 213
 214         formats = []
 215         format_urls = set()
 216
 217         sources = self._parse_json(
 218             self._search_regex(
 219                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 220                 default='{}'),
 221             video_id, fatal=False)
 222         for format_id, format_url in sources.items():
 223             format_url = url_or_none(format_url)
 224             if not format_url:
 225                 continue
 226             if format_url in format_urls:
 227                 continue
 228             format_urls.add(format_url)
 229             formats.append({
 230                 'format_id': format_id,
 231                 'url': format_url,
 232                 'height': get_height(format_id),
 233             })
 234
 235         video_url = self._search_regex(
 236             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 237              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 238              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 239             webpage, 'video url', group='mp4', default=None)
 240         if video_url and video_url not in format_urls:
 241             formats.append({
 242                 'url': video_url,
 243             })
 244
 245         self._sort_formats(formats)
 246
 247         # Only a few videos have an description
 248         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 249         description = mobj.group(1) if mobj else None
 250
 251         upload_date = unified_strdate(self._search_regex(
 252             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 253             webpage, 'upload date', fatal=False))
 254
 255         uploader = self._html_search_regex(
 256             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 257             webpage, 'uploader', default='anonymous')
 258
 259         thumbnail = self._search_regex(
 260             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 261              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 262             webpage, 'thumbnail', fatal=False, group='thumbnail')
 263
 264         duration = parse_duration(self._search_regex(
 265             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 266              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 267             'duration', fatal=False))
 268
 269         view_count = int_or_none(self._search_regex(
 270             r'content=["\']User(?:View|Play)s:(\d+)',
 271             webpage, 'view count', fatal=False))
 272
 273         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 274         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 275
 276         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 277         comment_count = mobj.group('commentcount') if mobj else 0
 278
 279         categories_html = self._search_regex(
 280             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 281             'categories', default=None)
 282         categories = [clean_html(category) for category in re.findall(
 283             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 284
 285         return {
 286             'id': video_id,
 287             'display_id': display_id,
 288             'title': title,
 289             'description': description,
 290             'upload_date': upload_date,
 291             'uploader': uploader,
 292             'thumbnail': thumbnail,
 293             'duration': duration,
 294             'view_count': view_count,
 295             'like_count': int_or_none(like_count),
 296             'dislike_count': int_or_none(dislike_count),
 297             'comment_count': int_or_none(comment_count),
 298             'age_limit': age_limit,
 299             'categories': categories,
 300             'formats': formats,
 301         }
 302
 303
 304 class XHamsterEmbedIE(InfoExtractor):
 305     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 306     _TEST = {
 307         'url': 'http://xhamster.com/xembed.php?video=3328539',
 308         'info_dict': {
 309             'id': '3328539',
 310             'ext': 'mp4',
 311             'title': 'Pen Masturbation',
 312             'timestamp': 1406581861,
 313             'upload_date': '20140728',
 314             'uploader': 'ManyakisArt',
 315             'duration': 5,
 316             'age_limit': 18,
 317         }
 318     }
 319
 320     @staticmethod
 321     def _extract_urls(webpage):
 322         return [url for _, url in re.findall(
 323             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 324             webpage)]
 325
 326     def _real_extract(self, url):
 327         video_id = self._match_id(url)
 328
 329         webpage = self._download_webpage(url, video_id)
 330
 331         video_url = self._search_regex(
 332             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 333             webpage, 'xhamster url', default=None)
 334
 335         if not video_url:
 336             vars = self._parse_json(
 337                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 338                 video_id)
 339             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 340
 341         return self.url_result(video_url, 'XHamster')
 342
 343
 344 class XHamsterUserIE(InfoExtractor):
 345     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
 346     _TESTS = [{
 347         # Paginated user profile
 348         'url': 'https://xhamster.com/users/netvideogirls/videos',
 349         'info_dict': {
 350             'id': 'netvideogirls',
 351         },
 352         'playlist_mincount': 267,
 353     }, {
 354         # Non-paginated user profile
 355         'url': 'https://xhamster.com/users/firatkaan/videos',
 356         'info_dict': {
 357             'id': 'firatkaan',
 358         },
 359         'playlist_mincount': 1,
 360     }]
 361
 362     def _entries(self, user_id):
 363         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
 364         for pagenum in itertools.count(1):
 365             page = self._download_webpage(
 366                 next_page_url, user_id, 'Downloading page %s' % pagenum)
 367             for video_tag in re.findall(
 368                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 369                     page):
 370                 video = extract_attributes(video_tag)
 371                 video_url = url_or_none(video.get('href'))
 372                 if not video_url or not XHamsterIE.suitable(video_url):
 373                     continue
 374                 video_id = XHamsterIE._match_id(video_url)
 375                 yield self.url_result(
 376                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 377             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 378             if not mobj:
 379                 break
 380             next_page = extract_attributes(mobj.group(0))
 381             next_page_url = url_or_none(next_page.get('href'))
 382             if not next_page_url:
 383                 break
 384
 385     def _real_extract(self, url):
 386         user_id = self._match_id(url)
 387         return self.playlist_result(self._entries(user_id), user_id)