Raphaël G. Git Repositories - youtubedl/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     dict_get,
   8     float_or_none,
   9     int_or_none,
  10     unified_strdate,
  11 )
  12
  13
  14 class XHamsterIE(InfoExtractor):
  15     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
  16     _TESTS = [{
  17         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  18         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  19         'info_dict': {
  20             'id': '1509445',
  21             'ext': 'mp4',
  22             'title': 'FemaleAgent Shy beauty takes the bait',
  23             'upload_date': '20121014',
  24             'uploader': 'Ruseful2011',
  25             'duration': 893.52,
  26             'age_limit': 18,
  27         },
  28     }, {
  29         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  30         'info_dict': {
  31             'id': '2221348',
  32             'ext': 'mp4',
  33             'title': 'Britney Spears  Sexy Booty',
  34             'upload_date': '20130914',
  35             'uploader': 'jojo747400',
  36             'duration': 200.48,
  37             'age_limit': 18,
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42     }, {
  43         # empty seo
  44         'url': 'http://xhamster.com/movies/5667973/.html',
  45         'info_dict': {
  46             'id': '5667973',
  47             'ext': 'mp4',
  48             'title': '....',
  49             'upload_date': '20160208',
  50             'uploader': 'parejafree',
  51             'duration': 72.0,
  52             'age_limit': 18,
  53         },
  54         'params': {
  55             'skip_download': True,
  56         },
  57     }, {
  58         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         def extract_video_url(webpage, name):
  64             return self._search_regex(
  65                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  66                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  67                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  68                 webpage, name, group='mp4')
  69
  70         def is_hd(webpage):
  71             return '<div class=\'icon iconHD\'' in webpage
  72
  73         mobj = re.match(self._VALID_URL, url)
  74
  75         video_id = mobj.group('id')
  76         seo = mobj.group('seo')
  77         proto = mobj.group('proto')
  78         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  79         webpage = self._download_webpage(mrss_url, video_id)
  80
  81         title = self._html_search_regex(
  82             [r'<h1[^>]*>([^<]+)</h1>',
  83              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
  84              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
  85             webpage, 'title')
  86
  87         # Only a few videos have an description
  88         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  89         description = mobj.group(1) if mobj else None
  90
  91         upload_date = unified_strdate(self._search_regex(
  92             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
  93             webpage, 'upload date', fatal=False))
  94
  95         uploader = self._html_search_regex(
  96             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
  97             webpage, 'uploader', default='anonymous')
  98
  99         thumbnail = self._search_regex(
 100             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 101              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 102             webpage, 'thumbnail', fatal=False, group='thumbnail')
 103
 104         duration = float_or_none(self._search_regex(
 105             r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
 106             webpage, 'duration', fatal=False, group='duration'))
 107
 108         view_count = int_or_none(self._search_regex(
 109             r'content=["\']User(?:View|Play)s:(\d+)',
 110             webpage, 'view count', fatal=False))
 111
 112         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
 113         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 114
 115         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 116         comment_count = mobj.group('commentcount') if mobj else 0
 117
 118         age_limit = self._rta_search(webpage)
 119
 120         hd = is_hd(webpage)
 121
 122         format_id = 'hd' if hd else 'sd'
 123
 124         video_url = extract_video_url(webpage, format_id)
 125         formats = [{
 126             'url': video_url,
 127             'format_id': 'hd' if hd else 'sd',
 128             'preference': 1,
 129         }]
 130
 131         if not hd:
 132             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 133             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 134             if is_hd(webpage):
 135                 video_url = extract_video_url(webpage, 'hd')
 136                 formats.append({
 137                     'url': video_url,
 138                     'format_id': 'hd',
 139                     'preference': 2,
 140                 })
 141
 142         self._sort_formats(formats)
 143
 144         return {
 145             'id': video_id,
 146             'title': title,
 147             'description': description,
 148             'upload_date': upload_date,
 149             'uploader': uploader,
 150             'thumbnail': thumbnail,
 151             'duration': duration,
 152             'view_count': view_count,
 153             'like_count': int_or_none(like_count),
 154             'dislike_count': int_or_none(dislike_count),
 155             'comment_count': int_or_none(comment_count),
 156             'age_limit': age_limit,
 157             'formats': formats,
 158         }
 159
 160
 161 class XHamsterEmbedIE(InfoExtractor):
 162     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 163     _TEST = {
 164         'url': 'http://xhamster.com/xembed.php?video=3328539',
 165         'info_dict': {
 166             'id': '3328539',
 167             'ext': 'mp4',
 168             'title': 'Pen Masturbation',
 169             'upload_date': '20140728',
 170             'uploader_id': 'anonymous',
 171             'duration': 5,
 172             'age_limit': 18,
 173         }
 174     }
 175
 176     @staticmethod
 177     def _extract_urls(webpage):
 178         return [url for _, url in re.findall(
 179             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 180             webpage)]
 181
 182     def _real_extract(self, url):
 183         video_id = self._match_id(url)
 184
 185         webpage = self._download_webpage(url, video_id)
 186
 187         video_url = self._search_regex(
 188             r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
 189             webpage, 'xhamster url', default=None)
 190
 191         if not video_url:
 192             vars = self._parse_json(
 193                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 194                 video_id)
 195             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 196
 197         return self.url_result(video_url, 'XHamster')