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