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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     clean_html,
   9     determine_ext,
  10     dict_get,
  11     ExtractorError,
  12     int_or_none,
  13     parse_duration,
  14     try_get,
  15     unified_strdate,
  16     url_or_none,
  17 )
  18
  19
  20 class XHamsterIE(InfoExtractor):
  21     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
  22     _VALID_URL = r'''(?x)
  23                     https?://
  24                         (?:.+?\.)?%s/
  25                         (?:
  26                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  27                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  28                         )
  29                     ''' % _DOMAINS
  30     _TESTS = [{
  31         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  32         'md5': '98b4687efb1ffd331c4197854dc09e8f',
  33         'info_dict': {
  34             'id': '1509445',
  35             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  36             'ext': 'mp4',
  37             'title': 'FemaleAgent Shy beauty takes the bait',
  38             'timestamp': 1350194821,
  39             'upload_date': '20121014',
  40             'uploader': 'Ruseful2011',
  41             'duration': 893,
  42             'age_limit': 18,
  43         },
  44     }, {
  45         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  46         'info_dict': {
  47             'id': '2221348',
  48             'display_id': 'britney-spears-sexy-booty',
  49             'ext': 'mp4',
  50             'title': 'Britney Spears  Sexy Booty',
  51             'timestamp': 1379123460,
  52             'upload_date': '20130914',
  53             'uploader': 'jojo747400',
  54             'duration': 200,
  55             'age_limit': 18,
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }, {
  61         # empty seo, unavailable via new URL schema
  62         'url': 'http://xhamster.com/movies/5667973/.html',
  63         'info_dict': {
  64             'id': '5667973',
  65             'ext': 'mp4',
  66             'title': '....',
  67             'timestamp': 1454948101,
  68             'upload_date': '20160208',
  69             'uploader': 'parejafree',
  70             'duration': 72,
  71             'age_limit': 18,
  72         },
  73         'params': {
  74             'skip_download': True,
  75         },
  76     }, {
  77         # mobile site
  78         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  79         'only_matching': True,
  80     }, {
  81         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  82         'only_matching': True,
  83     }, {
  84         # This video is visible for marcoalfa123456's friends only
  85         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  86         'only_matching': True,
  87     }, {
  88         # new URL schema
  89         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  90         'only_matching': True,
  91     }, {
  92         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  93         'only_matching': True,
  94     }, {
  95         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  96         'only_matching': True,
  97     }, {
  98         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  99         'only_matching': True,
 100     }, {
 101         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 102         'only_matching': True,
 103     }, {
 104         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 105         'only_matching': True,
 106     }]
 107
 108     def _real_extract(self, url):
 109         mobj = re.match(self._VALID_URL, url)
 110         video_id = mobj.group('id') or mobj.group('id_2')
 111         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 112
 113         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 114         webpage = self._download_webpage(desktop_url, video_id)
 115
 116         error = self._html_search_regex(
 117             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 118             webpage, 'error', default=None)
 119         if error:
 120             raise ExtractorError(error, expected=True)
 121
 122         age_limit = self._rta_search(webpage)
 123
 124         def get_height(s):
 125             return int_or_none(self._search_regex(
 126                 r'^(\d+)[pP]', s, 'height', default=None))
 127
 128         initials = self._parse_json(
 129             self._search_regex(
 130                 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
 131                 default='{}'),
 132             video_id, fatal=False)
 133         if initials:
 134             video = initials['videoModel']
 135             title = video['title']
 136             formats = []
 137             for format_id, formats_dict in video['sources'].items():
 138                 if not isinstance(formats_dict, dict):
 139                     continue
 140                 for quality, format_item in formats_dict.items():
 141                     if format_id == 'download':
 142                         # Download link takes some time to be generated,
 143                         # skipping for now
 144                         continue
 145                         if not isinstance(format_item, dict):
 146                             continue
 147                         format_url = format_item.get('link')
 148                         filesize = int_or_none(
 149                             format_item.get('size'), invscale=1000000)
 150                     else:
 151                         format_url = format_item
 152                         filesize = None
 153                     format_url = url_or_none(format_url)
 154                     if not format_url:
 155                         continue
 156                     formats.append({
 157                         'format_id': '%s-%s' % (format_id, quality),
 158                         'url': format_url,
 159                         'ext': determine_ext(format_url, 'mp4'),
 160                         'height': get_height(quality),
 161                         'filesize': filesize,
 162                     })
 163             self._sort_formats(formats)
 164
 165             categories_list = video.get('categories')
 166             if isinstance(categories_list, list):
 167                 categories = []
 168                 for c in categories_list:
 169                     if not isinstance(c, dict):
 170                         continue
 171                     c_name = c.get('name')
 172                     if isinstance(c_name, compat_str):
 173                         categories.append(c_name)
 174             else:
 175                 categories = None
 176
 177             return {
 178                 'id': video_id,
 179                 'display_id': display_id,
 180                 'title': title,
 181                 'description': video.get('description'),
 182                 'timestamp': int_or_none(video.get('created')),
 183                 'uploader': try_get(
 184                     video, lambda x: x['author']['name'], compat_str),
 185                 'thumbnail': video.get('thumbURL'),
 186                 'duration': int_or_none(video.get('duration')),
 187                 'view_count': int_or_none(video.get('views')),
 188                 'like_count': int_or_none(try_get(
 189                     video, lambda x: x['rating']['likes'], int)),
 190                 'dislike_count': int_or_none(try_get(
 191                     video, lambda x: x['rating']['dislikes'], int)),
 192                 'comment_count': int_or_none(video.get('views')),
 193                 'age_limit': age_limit,
 194                 'categories': categories,
 195                 'formats': formats,
 196             }
 197
 198         # Old layout fallback
 199
 200         title = self._html_search_regex(
 201             [r'<h1[^>]*>([^<]+)</h1>',
 202              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 203              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 204             webpage, 'title')
 205
 206         formats = []
 207         format_urls = set()
 208
 209         sources = self._parse_json(
 210             self._search_regex(
 211                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 212                 default='{}'),
 213             video_id, fatal=False)
 214         for format_id, format_url in sources.items():
 215             format_url = url_or_none(format_url)
 216             if not format_url:
 217                 continue
 218             if format_url in format_urls:
 219                 continue
 220             format_urls.add(format_url)
 221             formats.append({
 222                 'format_id': format_id,
 223                 'url': format_url,
 224                 'height': get_height(format_id),
 225             })
 226
 227         video_url = self._search_regex(
 228             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 229              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 230              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 231             webpage, 'video url', group='mp4', default=None)
 232         if video_url and video_url not in format_urls:
 233             formats.append({
 234                 'url': video_url,
 235             })
 236
 237         self._sort_formats(formats)
 238
 239         # Only a few videos have an description
 240         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 241         description = mobj.group(1) if mobj else None
 242
 243         upload_date = unified_strdate(self._search_regex(
 244             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 245             webpage, 'upload date', fatal=False))
 246
 247         uploader = self._html_search_regex(
 248             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 249             webpage, 'uploader', default='anonymous')
 250
 251         thumbnail = self._search_regex(
 252             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 253              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 254             webpage, 'thumbnail', fatal=False, group='thumbnail')
 255
 256         duration = parse_duration(self._search_regex(
 257             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 258              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 259             'duration', fatal=False))
 260
 261         view_count = int_or_none(self._search_regex(
 262             r'content=["\']User(?:View|Play)s:(\d+)',
 263             webpage, 'view count', fatal=False))
 264
 265         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 266         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 267
 268         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 269         comment_count = mobj.group('commentcount') if mobj else 0
 270
 271         categories_html = self._search_regex(
 272             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 273             'categories', default=None)
 274         categories = [clean_html(category) for category in re.findall(
 275             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 276
 277         return {
 278             'id': video_id,
 279             'display_id': display_id,
 280             'title': title,
 281             'description': description,
 282             'upload_date': upload_date,
 283             'uploader': uploader,
 284             'thumbnail': thumbnail,
 285             'duration': duration,
 286             'view_count': view_count,
 287             'like_count': int_or_none(like_count),
 288             'dislike_count': int_or_none(dislike_count),
 289             'comment_count': int_or_none(comment_count),
 290             'age_limit': age_limit,
 291             'categories': categories,
 292             'formats': formats,
 293         }
 294
 295
 296 class XHamsterEmbedIE(InfoExtractor):
 297     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 298     _TEST = {
 299         'url': 'http://xhamster.com/xembed.php?video=3328539',
 300         'info_dict': {
 301             'id': '3328539',
 302             'ext': 'mp4',
 303             'title': 'Pen Masturbation',
 304             'timestamp': 1406581861,
 305             'upload_date': '20140728',
 306             'uploader': 'ManyakisArt',
 307             'duration': 5,
 308             'age_limit': 18,
 309         }
 310     }
 311
 312     @staticmethod
 313     def _extract_urls(webpage):
 314         return [url for _, url in re.findall(
 315             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 316             webpage)]
 317
 318     def _real_extract(self, url):
 319         video_id = self._match_id(url)
 320
 321         webpage = self._download_webpage(url, video_id)
 322
 323         video_url = self._search_regex(
 324             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 325             webpage, 'xhamster url', default=None)
 326
 327         if not video_url:
 328             vars = self._parse_json(
 329                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 330                 video_id)
 331             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 332
 333         return self.url_result(video_url, 'XHamster')