Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornhub.py

   1 from __future__ import unicode_literals
   2
   3 import os
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_unquote,
   9     compat_urllib_parse_unquote_plus,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15     sanitized_Request,
  16     str_to_int,
  17 )
  18 from ..aes import (
  19     aes_decrypt_text
  20 )
  21
  22
  23 class PornHubIE(InfoExtractor):
  24     _VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
  25     _TESTS = [{
  26         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  27         'md5': '1e19b41231a02eba417839222ac9d58e',
  28         'info_dict': {
  29             'id': '648719015',
  30             'ext': 'mp4',
  31             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
  32             'uploader': 'Babes',
  33             'duration': 361,
  34             'view_count': int,
  35             'like_count': int,
  36             'dislike_count': int,
  37             'comment_count': int,
  38             'age_limit': 18,
  39         }
  40     }, {
  41         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
  45         'only_matching': True,
  46     }]
  47
  48     @classmethod
  49     def _extract_url(cls, webpage):
  50         mobj = re.search(
  51             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
  52         if mobj:
  53             return mobj.group('url')
  54
  55     def _extract_count(self, pattern, webpage, name):
  56         return str_to_int(self._search_regex(
  57             pattern, webpage, '%s count' % name, fatal=False))
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61
  62         req = sanitized_Request(
  63             'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
  64         req.add_header('Cookie', 'age_verified=1')
  65         webpage = self._download_webpage(req, video_id)
  66
  67         error_msg = self._html_search_regex(
  68             r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
  69             webpage, 'error message', default=None)
  70         if error_msg:
  71             error_msg = re.sub(r'\s+', ' ', error_msg)
  72             raise ExtractorError(
  73                 'PornHub said: %s' % error_msg,
  74                 expected=True, video_id=video_id)
  75
  76         flashvars = self._parse_json(
  77             self._search_regex(
  78                 r'var\s+flashv1ars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
  79             video_id)
  80         if flashvars:
  81             video_title = flashvars.get('video_title')
  82             thumbnail = flashvars.get('image_url')
  83             duration = int_or_none(flashvars.get('video_duration'))
  84         else:
  85             video_title, thumbnail, duration = [None] * 3
  86
  87         if not video_title:
  88             video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
  89
  90         video_uploader = self._html_search_regex(
  91             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
  92             webpage, 'uploader', fatal=False)
  93
  94         view_count = self._extract_count(
  95             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
  96         like_count = self._extract_count(
  97             r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
  98         dislike_count = self._extract_count(
  99             r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
 100         comment_count = self._extract_count(
 101             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 102
 103         video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))
 104         if webpage.find('"encrypted":true') != -1:
 105             password = compat_urllib_parse_unquote_plus(
 106                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
 107             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 108
 109         formats = []
 110         for video_url in video_urls:
 111             path = compat_urllib_parse_urlparse(video_url).path
 112             extension = os.path.splitext(path)[1][1:]
 113             format = path.split('/')[5].split('_')[:2]
 114             format = '-'.join(format)
 115
 116             m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)
 117             if m is None:
 118                 height = None
 119                 tbr = None
 120             else:
 121                 height = int(m.group('height'))
 122                 tbr = int(m.group('tbr'))
 123
 124             formats.append({
 125                 'url': video_url,
 126                 'ext': extension,
 127                 'format': format,
 128                 'format_id': format,
 129                 'tbr': tbr,
 130                 'height': height,
 131             })
 132         self._sort_formats(formats)
 133
 134         return {
 135             'id': video_id,
 136             'uploader': video_uploader,
 137             'title': video_title,
 138             'thumbnail': thumbnail,
 139             'duration': duration,
 140             'view_count': view_count,
 141             'like_count': like_count,
 142             'dislike_count': dislike_count,
 143             'comment_count': comment_count,
 144             'formats': formats,
 145             'age_limit': 18,
 146         }
 147
 148
 149 class PornHubPlaylistBaseIE(InfoExtractor):
 150     def _extract_entries(self, webpage):
 151         return [
 152             self.url_result('http://www.pornhub.com/%s' % video_url, PornHubIE.ie_key())
 153             for video_url in set(re.findall(
 154                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
 155         ]
 156
 157     def _real_extract(self, url):
 158         playlist_id = self._match_id(url)
 159
 160         webpage = self._download_webpage(url, playlist_id)
 161
 162         entries = self._extract_entries(webpage)
 163
 164         playlist = self._parse_json(
 165             self._search_regex(
 166                 r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
 167             playlist_id)
 168
 169         return self.playlist_result(
 170             entries, playlist_id, playlist.get('title'), playlist.get('description'))
 171
 172
 173 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 174     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
 175     _TESTS = [{
 176         'url': 'http://www.pornhub.com/playlist/6201671',
 177         'info_dict': {
 178             'id': '6201671',
 179             'title': 'P0p4',
 180         },
 181         'playlist_mincount': 35,
 182     }]
 183
 184
 185 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
 186     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
 187     _TESTS = [{
 188         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 189         'info_dict': {
 190             'id': 'rushandlia',
 191         },
 192         'playlist_mincount': 13,
 193     }]
 194
 195     def _real_extract(self, url):
 196         user_id = self._match_id(url)
 197
 198         webpage = self._download_webpage(url, user_id)
 199
 200         return self.playlist_result(self._extract_entries(webpage), user_id)