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

   1 import os
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse_urlparse,
   7     compat_urllib_request,
   8     compat_urllib_parse,
   9     unescapeHTML,
  10 )
  11 from ..aes import (
  12     aes_decrypt_text
  13 )
  14
  15 class PornHubIE(InfoExtractor):
  16     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
  17     _TEST = {
  18         u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
  19         u'file': u'648719015.mp4',
  20         u'md5': u'882f488fa1f0026f023f33576004a2ed',
  21         u'info_dict': {
  22             u"uploader": u"BABES-COM",
  23             u"title": u"Seductive Indian beauty strips down and fingers her pink pussy",
  24             u"age_limit": 18
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('videoid')
  31         url = 'http://www.' + mobj.group('url')
  32
  33         req = compat_urllib_request.Request(url)
  34         req.add_header('Cookie', 'age_verified=1')
  35         webpage = self._download_webpage(req, video_id)
  36
  37         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, u'title')
  38         video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
  39         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
  40         if thumbnail:
  41             thumbnail = compat_urllib_parse.unquote(thumbnail)
  42
  43         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
  44         if webpage.find('"encrypted":true') != -1:
  45             password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ')
  46             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  47
  48         formats = []
  49         for video_url in video_urls:
  50             path = compat_urllib_parse_urlparse(video_url).path
  51             extension = os.path.splitext(path)[1][1:]
  52             format = path.split('/')[5].split('_')[:2]
  53             format = "-".join(format)
  54             formats.append({
  55                 'url': video_url,
  56                 'ext': extension,
  57                 'format': format,
  58                 'format_id': format,
  59             })
  60         formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
  61
  62         return {
  63             'id': video_id,
  64             'uploader': video_uploader,
  65             'title': video_title,
  66             'thumbnail': thumbnail,
  67             'formats': formats,
  68             'age_limit': 18,
  69         }