_ 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 ..utils import (
   7     clean_html,
   8     dict_get,
   9     ExtractorError,
  10     int_or_none,
  11     parse_duration,
  12     unified_strdate,
  13 )
  14
  15
  16 class XHamsterIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     https?://
  19                         (?:.+?\.)?xhamster\.com/
  20                         (?:
  21                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  22                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  23                         )
  24                     '''
  25
  26     _TESTS = [{
  27         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  28         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  29         'info_dict': {
  30             'id': '1509445',
  31             'ext': 'mp4',
  32             'title': 'FemaleAgent Shy beauty takes the bait',
  33             'upload_date': '20121014',
  34             'uploader': 'Ruseful2011',
  35             'duration': 893,
  36             'age_limit': 18,
  37             'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
  38         },
  39     }, {
  40         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  41         'info_dict': {
  42             'id': '2221348',
  43             'ext': 'mp4',
  44             'title': 'Britney Spears  Sexy Booty',
  45             'upload_date': '20130914',
  46             'uploader': 'jojo747400',
  47             'duration': 200,
  48             'age_limit': 18,
  49             'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
  50         },
  51         'params': {
  52             'skip_download': True,
  53         },
  54     }, {
  55         # empty seo
  56         'url': 'http://xhamster.com/movies/5667973/.html',
  57         'info_dict': {
  58             'id': '5667973',
  59             'ext': 'mp4',
  60             'title': '....',
  61             'upload_date': '20160208',
  62             'uploader': 'parejafree',
  63             'duration': 72,
  64             'age_limit': 18,
  65             'categories': ['Amateur', 'Blowjobs'],
  66         },
  67         'params': {
  68             'skip_download': True,
  69         },
  70     }, {
  71         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  72         'only_matching': True,
  73     }, {
  74         # This video is visible for marcoalfa123456's friends only
  75         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  76         'only_matching': True,
  77     }, {
  78         # new URL schema
  79         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  80         'only_matching': True,
  81     }]
  82
  83     def _real_extract(self, url):
  84         def extract_video_url(webpage, name):
  85             return self._search_regex(
  86                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  87                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  88                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  89                 webpage, name, group='mp4')
  90
  91         def is_hd(webpage):
  92             return '<div class=\'icon iconHD\'' in webpage
  93
  94         mobj = re.match(self._VALID_URL, url)
  95
  96         video_id = mobj.group('id') or mobj.group('id_2')
  97         display_id = mobj.group('display_id') or mobj.group('display_id_2')
  98
  99         webpage = self._download_webpage(url, video_id)
 100
 101         error = self._html_search_regex(
 102             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 103             webpage, 'error', default=None)
 104         if error:
 105             raise ExtractorError(error, expected=True)
 106
 107         title = self._html_search_regex(
 108             [r'<h1[^>]*>([^<]+)</h1>',
 109              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 110              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 111             webpage, 'title')
 112
 113         # Only a few videos have an description
 114         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 115         description = mobj.group(1) if mobj else None
 116
 117         upload_date = unified_strdate(self._search_regex(
 118             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 119             webpage, 'upload date', fatal=False))
 120
 121         uploader = self._html_search_regex(
 122             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 123             webpage, 'uploader', default='anonymous')
 124
 125         thumbnail = self._search_regex(
 126             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 127              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 128             webpage, 'thumbnail', fatal=False, group='thumbnail')
 129
 130         duration = parse_duration(self._search_regex(
 131             r'Runtime:\s*</span>\s*([\d:]+)', webpage,
 132             'duration', fatal=False))
 133
 134         view_count = int_or_none(self._search_regex(
 135             r'content=["\']User(?:View|Play)s:(\d+)',
 136             webpage, 'view count', fatal=False))
 137
 138         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 139         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 140
 141         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 142         comment_count = mobj.group('commentcount') if mobj else 0
 143
 144         age_limit = self._rta_search(webpage)
 145
 146         hd = is_hd(webpage)
 147
 148         format_id = 'hd' if hd else 'sd'
 149
 150         video_url = extract_video_url(webpage, format_id)
 151         formats = [{
 152             'url': video_url,
 153             'format_id': 'hd' if hd else 'sd',
 154             'preference': 1,
 155         }]
 156
 157         if not hd:
 158             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 159             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 160             if is_hd(webpage):
 161                 video_url = extract_video_url(webpage, 'hd')
 162                 formats.append({
 163                     'url': video_url,
 164                     'format_id': 'hd',
 165                     'preference': 2,
 166                 })
 167
 168         self._sort_formats(formats)
 169
 170         categories_html = self._search_regex(
 171             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 172             'categories', default=None)
 173         categories = [clean_html(category) for category in re.findall(
 174             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 175
 176         return {
 177             'id': video_id,
 178             'title': title,
 179             'description': description,
 180             'upload_date': upload_date,
 181             'uploader': uploader,
 182             'thumbnail': thumbnail,
 183             'duration': duration,
 184             'view_count': view_count,
 185             'like_count': int_or_none(like_count),
 186             'dislike_count': int_or_none(dislike_count),
 187             'comment_count': int_or_none(comment_count),
 188             'age_limit': age_limit,
 189             'categories': categories,
 190             'formats': formats,
 191         }
 192
 193
 194 class XHamsterEmbedIE(InfoExtractor):
 195     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 196     _TEST = {
 197         'url': 'http://xhamster.com/xembed.php?video=3328539',
 198         'info_dict': {
 199             'id': '3328539',
 200             'ext': 'mp4',
 201             'title': 'Pen Masturbation',
 202             'upload_date': '20140728',
 203             'uploader_id': 'anonymous',
 204             'duration': 5,
 205             'age_limit': 18,
 206         }
 207     }
 208
 209     @staticmethod
 210     def _extract_urls(webpage):
 211         return [url for _, url in re.findall(
 212             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 213             webpage)]
 214
 215     def _real_extract(self, url):
 216         video_id = self._match_id(url)
 217
 218         webpage = self._download_webpage(url, video_id)
 219
 220         video_url = self._search_regex(
 221             r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
 222             webpage, 'xhamster url', default=None)
 223
 224         if not video_url:
 225             vars = self._parse_json(
 226                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 227                 video_id)
 228             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 229
 230         return self.url_result(video_url, 'XHamster')