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\d+\.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': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 104         'only_matching': True,
 105     }, {
 106         'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 107         'only_matching': True,
 108     }, {
 109         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 110         'only_matching': True,
 111     }, {
 112         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 113         'only_matching': True,
 114     }, {
 115         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
 116         'only_matching': True,
 117     }]
 118
 119     def _real_extract(self, url):
 120         mobj = re.match(self._VALID_URL, url)
 121         video_id = mobj.group('id') or mobj.group('id_2')
 122         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 123
 124         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 125         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 126
 127         error = self._html_search_regex(
 128             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 129             webpage, 'error', default=None)
 130         if error:
 131             raise ExtractorError(error, expected=True)
 132
 133         age_limit = self._rta_search(webpage)
 134
 135         def get_height(s):
 136             return int_or_none(self._search_regex(
 137                 r'^(\d+)[pP]', s, 'height', default=None))
 138
 139         initials = self._parse_json(
 140             self._search_regex(
 141                 r'window\.initials\s*=\s*({.+?})\s*;', webpage, 'initials',
 142                 default='{}'),
 143             video_id, fatal=False)
 144         if initials:
 145             video = initials['videoModel']
 146             title = video['title']
 147             formats = []
 148             for format_id, formats_dict in video['sources'].items():
 149                 if not isinstance(formats_dict, dict):
 150                     continue
 151                 for quality, format_item in formats_dict.items():
 152                     if format_id == 'download':
 153                         # Download link takes some time to be generated,
 154                         # skipping for now
 155                         continue
 156                         if not isinstance(format_item, dict):
 157                             continue
 158                         format_url = format_item.get('link')
 159                         filesize = int_or_none(
 160                             format_item.get('size'), invscale=1000000)
 161                     else:
 162                         format_url = format_item
 163                         filesize = None
 164                     format_url = url_or_none(format_url)
 165                     if not format_url:
 166                         continue
 167                     formats.append({
 168                         'format_id': '%s-%s' % (format_id, quality),
 169                         'url': format_url,
 170                         'ext': determine_ext(format_url, 'mp4'),
 171                         'height': get_height(quality),
 172                         'filesize': filesize,
 173                         'http_headers': {
 174                             'Referer': urlh.geturl(),
 175                         },
 176                     })
 177             self._sort_formats(formats)
 178
 179             categories_list = video.get('categories')
 180             if isinstance(categories_list, list):
 181                 categories = []
 182                 for c in categories_list:
 183                     if not isinstance(c, dict):
 184                         continue
 185                     c_name = c.get('name')
 186                     if isinstance(c_name, compat_str):
 187                         categories.append(c_name)
 188             else:
 189                 categories = None
 190
 191             return {
 192                 'id': video_id,
 193                 'display_id': display_id,
 194                 'title': title,
 195                 'description': video.get('description'),
 196                 'timestamp': int_or_none(video.get('created')),
 197                 'uploader': try_get(
 198                     video, lambda x: x['author']['name'], compat_str),
 199                 'thumbnail': video.get('thumbURL'),
 200                 'duration': int_or_none(video.get('duration')),
 201                 'view_count': int_or_none(video.get('views')),
 202                 'like_count': int_or_none(try_get(
 203                     video, lambda x: x['rating']['likes'], int)),
 204                 'dislike_count': int_or_none(try_get(
 205                     video, lambda x: x['rating']['dislikes'], int)),
 206                 'comment_count': int_or_none(video.get('views')),
 207                 'age_limit': age_limit,
 208                 'categories': categories,
 209                 'formats': formats,
 210             }
 211
 212         # Old layout fallback
 213
 214         title = self._html_search_regex(
 215             [r'<h1[^>]*>([^<]+)</h1>',
 216              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 217              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 218             webpage, 'title')
 219
 220         formats = []
 221         format_urls = set()
 222
 223         sources = self._parse_json(
 224             self._search_regex(
 225                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 226                 default='{}'),
 227             video_id, fatal=False)
 228         for format_id, format_url in sources.items():
 229             format_url = url_or_none(format_url)
 230             if not format_url:
 231                 continue
 232             if format_url in format_urls:
 233                 continue
 234             format_urls.add(format_url)
 235             formats.append({
 236                 'format_id': format_id,
 237                 'url': format_url,
 238                 'height': get_height(format_id),
 239             })
 240
 241         video_url = self._search_regex(
 242             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 243              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 244              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 245             webpage, 'video url', group='mp4', default=None)
 246         if video_url and video_url not in format_urls:
 247             formats.append({
 248                 'url': video_url,
 249             })
 250
 251         self._sort_formats(formats)
 252
 253         # Only a few videos have an description
 254         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 255         description = mobj.group(1) if mobj else None
 256
 257         upload_date = unified_strdate(self._search_regex(
 258             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 259             webpage, 'upload date', fatal=False))
 260
 261         uploader = self._html_search_regex(
 262             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 263             webpage, 'uploader', default='anonymous')
 264
 265         thumbnail = self._search_regex(
 266             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 267              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 268             webpage, 'thumbnail', fatal=False, group='thumbnail')
 269
 270         duration = parse_duration(self._search_regex(
 271             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 272              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 273             'duration', fatal=False))
 274
 275         view_count = int_or_none(self._search_regex(
 276             r'content=["\']User(?:View|Play)s:(\d+)',
 277             webpage, 'view count', fatal=False))
 278
 279         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 280         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 281
 282         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 283         comment_count = mobj.group('commentcount') if mobj else 0
 284
 285         categories_html = self._search_regex(
 286             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 287             'categories', default=None)
 288         categories = [clean_html(category) for category in re.findall(
 289             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 290
 291         return {
 292             'id': video_id,
 293             'display_id': display_id,
 294             'title': title,
 295             'description': description,
 296             'upload_date': upload_date,
 297             'uploader': uploader,
 298             'thumbnail': thumbnail,
 299             'duration': duration,
 300             'view_count': view_count,
 301             'like_count': int_or_none(like_count),
 302             'dislike_count': int_or_none(dislike_count),
 303             'comment_count': int_or_none(comment_count),
 304             'age_limit': age_limit,
 305             'categories': categories,
 306             'formats': formats,
 307         }
 308
 309
 310 class XHamsterEmbedIE(InfoExtractor):
 311     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 312     _TEST = {
 313         'url': 'http://xhamster.com/xembed.php?video=3328539',
 314         'info_dict': {
 315             'id': '3328539',
 316             'ext': 'mp4',
 317             'title': 'Pen Masturbation',
 318             'timestamp': 1406581861,
 319             'upload_date': '20140728',
 320             'uploader': 'ManyakisArt',
 321             'duration': 5,
 322             'age_limit': 18,
 323         }
 324     }
 325
 326     @staticmethod
 327     def _extract_urls(webpage):
 328         return [url for _, url in re.findall(
 329             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 330             webpage)]
 331
 332     def _real_extract(self, url):
 333         video_id = self._match_id(url)
 334
 335         webpage = self._download_webpage(url, video_id)
 336
 337         video_url = self._search_regex(
 338             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 339             webpage, 'xhamster url', default=None)
 340
 341         if not video_url:
 342             vars = self._parse_json(
 343                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 344                 video_id)
 345             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 346
 347         return self.url_result(video_url, 'XHamster')
 348
 349
 350 class XHamsterUserIE(InfoExtractor):
 351     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
 352     _TESTS = [{
 353         # Paginated user profile
 354         'url': 'https://xhamster.com/users/netvideogirls/videos',
 355         'info_dict': {
 356             'id': 'netvideogirls',
 357         },
 358         'playlist_mincount': 267,
 359     }, {
 360         # Non-paginated user profile
 361         'url': 'https://xhamster.com/users/firatkaan/videos',
 362         'info_dict': {
 363             'id': 'firatkaan',
 364         },
 365         'playlist_mincount': 1,
 366     }]
 367
 368     def _entries(self, user_id):
 369         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
 370         for pagenum in itertools.count(1):
 371             page = self._download_webpage(
 372                 next_page_url, user_id, 'Downloading page %s' % pagenum)
 373             for video_tag in re.findall(
 374                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 375                     page):
 376                 video = extract_attributes(video_tag)
 377                 video_url = url_or_none(video.get('href'))
 378                 if not video_url or not XHamsterIE.suitable(video_url):
 379                     continue
 380                 video_id = XHamsterIE._match_id(video_url)
 381                 yield self.url_result(
 382                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 383             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 384             if not mobj:
 385                 break
 386             next_page = extract_attributes(mobj.group(0))
 387             next_page_url = url_or_none(next_page.get('href'))
 388             if not next_page_url:
 389                 break
 390
 391     def _real_extract(self, url):
 392         user_id = self._match_id(url)
 393         return self.playlist_result(self._entries(user_id), user_id)