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,
   9     compat_urllib_parse_urlparse,
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     str_to_int,
  15 )
  16 from ..aes import (
  17     aes_decrypt_text
  18 )
  19
  20
  21 class PornHubIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
  23     _TEST = {
  24         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  25         'md5': '882f488fa1f0026f023f33576004a2ed',
  26         'info_dict': {
  27             'id': '648719015',
  28             'ext': 'mp4',
  29             "uploader": "Babes",
  30             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
  31             "age_limit": 18
  32         }
  33     }
  34
  35     def _extract_count(self, pattern, webpage, name):
  36         return str_to_int(self._search_regex(
  37             pattern, webpage, '%s count' % name, fatal=False))
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         req = compat_urllib_request.Request(url)
  43         req.add_header('Cookie', 'age_verified=1')
  44         webpage = self._download_webpage(req, video_id)
  45
  46         error_msg = self._html_search_regex(
  47             r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
  48             webpage, 'error message', default=None)
  49         if error_msg:
  50             error_msg = re.sub(r'\s+', ' ', error_msg)
  51             raise ExtractorError(
  52                 'PornHub said: %s' % error_msg,
  53                 expected=True, video_id=video_id)
  54
  55         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
  56         video_uploader = self._html_search_regex(
  57             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
  58             webpage, 'uploader', fatal=False)
  59         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
  60         if thumbnail:
  61             thumbnail = compat_urllib_parse.unquote(thumbnail)
  62
  63         view_count = self._extract_count(
  64             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
  65         like_count = self._extract_count(
  66             r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
  67         dislike_count = self._extract_count(
  68             r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
  69         comment_count = self._extract_count(
  70             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
  71
  72         video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
  73         if webpage.find('"encrypted":true') != -1:
  74             password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
  75             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  76
  77         formats = []
  78         for video_url in video_urls:
  79             path = compat_urllib_parse_urlparse(video_url).path
  80             extension = os.path.splitext(path)[1][1:]
  81             format = path.split('/')[5].split('_')[:2]
  82             format = "-".join(format)
  83
  84             m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
  85             if m is None:
  86                 height = None
  87                 tbr = None
  88             else:
  89                 height = int(m.group('height'))
  90                 tbr = int(m.group('tbr'))
  91
  92             formats.append({
  93                 'url': video_url,
  94                 'ext': extension,
  95                 'format': format,
  96                 'format_id': format,
  97                 'tbr': tbr,
  98                 'height': height,
  99             })
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': video_id,
 104             'uploader': video_uploader,
 105             'title': video_title,
 106             'thumbnail': thumbnail,
 107             'view_count': view_count,
 108             'like_count': like_count,
 109             'dislike_count': dislike_count,
 110             'comment_count': comment_count,
 111             'formats': formats,
 112             'age_limit': 18,
 113         }
 114
 115
 116 class PornHubPlaylistIE(InfoExtractor):
 117     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
 118     _TESTS = [{
 119         'url': 'http://www.pornhub.com/playlist/6201671',
 120         'info_dict': {
 121             'id': '6201671',
 122             'title': 'P0p4',
 123         },
 124         'playlist_mincount': 35,
 125     }]
 126
 127     def _real_extract(self, url):
 128         playlist_id = self._match_id(url)
 129
 130         webpage = self._download_webpage(url, playlist_id)
 131
 132         entries = [
 133             self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
 134             for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
 135         ]
 136
 137         playlist = self._parse_json(
 138             self._search_regex(
 139                 r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
 140             playlist_id)
 141
 142         return self.playlist_result(
 143             entries, playlist_id, playlist.get('title'), playlist.get('description'))