_ 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     float_or_none,
   8     int_or_none,
   9     str_to_int,
  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         {
  18             'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  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,
  26                 'age_limit': 18,
  27             }
  28         },
  29         {
  30             'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  31             'info_dict': {
  32                 'id': '2221348',
  33                 'ext': 'mp4',
  34                 'title': 'Britney Spears  Sexy Booty',
  35                 'upload_date': '20130914',
  36                 'uploader': 'jojo747400',
  37                 'duration': 200,
  38                 'age_limit': 18,
  39             }
  40         },
  41         {
  42             'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  43             'only_matching': True,
  44         },
  45     ]
  46
  47     def _real_extract(self, url):
  48         def extract_video_url(webpage, name):
  49             return self._search_regex(
  50                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  51                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  52                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  53                 webpage, name, group='mp4')
  54
  55         def is_hd(webpage):
  56             return '<div class=\'icon iconHD\'' in webpage
  57
  58         mobj = re.match(self._VALID_URL, url)
  59
  60         video_id = mobj.group('id')
  61         seo = mobj.group('seo')
  62         proto = mobj.group('proto')
  63         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  64         webpage = self._download_webpage(mrss_url, video_id)
  65
  66         title = self._html_search_regex(
  67             [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>',
  68              r'<h1[^>]*>([^<]+)</h1>',
  69              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title')
  70
  71         # Only a few videos have an description
  72         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  73         description = mobj.group(1) if mobj else None
  74
  75         upload_date = unified_strdate(self._search_regex(
  76             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
  77             webpage, 'upload date', fatal=False))
  78
  79         uploader = self._html_search_regex(
  80             r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
  81             webpage, 'uploader', default='anonymous')
  82
  83         thumbnail = self._search_regex(
  84             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
  85              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
  86             webpage, 'thumbnail', fatal=False, group='thumbnail')
  87
  88         duration = float_or_none(self._search_regex(
  89             r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
  90             webpage, 'duration', fatal=False, group='duration'))
  91
  92         view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
  93         if view_count:
  94             view_count = str_to_int(view_count)
  95
  96         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
  97         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
  98
  99         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 100         comment_count = mobj.group('commentcount') if mobj else 0
 101
 102         age_limit = self._rta_search(webpage)
 103
 104         hd = is_hd(webpage)
 105
 106         format_id = 'hd' if hd else 'sd'
 107
 108         video_url = extract_video_url(webpage, format_id)
 109         formats = [{
 110             'url': video_url,
 111             'format_id': 'hd' if hd else 'sd',
 112             'preference': 1,
 113         }]
 114
 115         if not hd:
 116             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 117             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 118             if is_hd(webpage):
 119                 video_url = extract_video_url(webpage, 'hd')
 120                 formats.append({
 121                     'url': video_url,
 122                     'format_id': 'hd',
 123                     'preference': 2,
 124                 })
 125
 126         self._sort_formats(formats)
 127
 128         return {
 129             'id': video_id,
 130             'title': title,
 131             'description': description,
 132             'upload_date': upload_date,
 133             'uploader': uploader,
 134             'thumbnail': thumbnail,
 135             'duration': duration,
 136             'view_count': view_count,
 137             'like_count': int_or_none(like_count),
 138             'dislike_count': int_or_none(dislike_count),
 139             'comment_count': int_or_none(comment_count),
 140             'age_limit': age_limit,
 141             'formats': formats,
 142         }
 143
 144
 145 class XHamsterEmbedIE(InfoExtractor):
 146     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 147     _TEST = {
 148         'url': 'http://xhamster.com/xembed.php?video=3328539',
 149         'info_dict': {
 150             'id': '3328539',
 151             'ext': 'mp4',
 152             'title': 'Pen Masturbation',
 153             'upload_date': '20140728',
 154             'uploader_id': 'anonymous',
 155             'duration': 5,
 156             'age_limit': 18,
 157         }
 158     }
 159
 160     @staticmethod
 161     def _extract_urls(webpage):
 162         return [url for _, url in re.findall(
 163             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 164             webpage)]
 165
 166     def _real_extract(self, url):
 167         video_id = self._match_id(url)
 168
 169         webpage = self._download_webpage(url, video_id)
 170
 171         video_url = self._search_regex(
 172             r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
 173             webpage, 'xhamster url')
 174
 175         return self.url_result(video_url, 'XHamster')