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 ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10     compat_urllib_parse,
  11 )
  12 from ..aes import (
  13     aes_decrypt_text
  14 )
  15
  16
  17 class PornHubIE(InfoExtractor):
  18     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
  19     _TEST = {
  20         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  21         'file': '648719015.mp4',
  22         'md5': '882f488fa1f0026f023f33576004a2ed',
  23         'info_dict': {
  24             "uploader": "BABES-COM",
  25             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
  26             "age_limit": 18
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('videoid')
  33         url = 'http://www.' + mobj.group('url')
  34
  35         req = compat_urllib_request.Request(url)
  36         req.add_header('Cookie', 'age_verified=1')
  37         webpage = self._download_webpage(req, video_id)
  38
  39         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
  40         video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False)
  41         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
  42         if thumbnail:
  43             thumbnail = compat_urllib_parse.unquote(thumbnail)
  44
  45         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
  46         if webpage.find('"encrypted":true') != -1:
  47             password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password').replace('+', ' ')
  48             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  49
  50         formats = []
  51         for video_url in video_urls:
  52             path = compat_urllib_parse_urlparse(video_url).path
  53             extension = os.path.splitext(path)[1][1:]
  54             format = path.split('/')[5].split('_')[:2]
  55             format = "-".join(format)
  56
  57             m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
  58             if m is None:
  59                 height = None
  60                 tbr = None
  61             else:
  62                 height = int(m.group('height'))
  63                 tbr = int(m.group('tbr'))
  64
  65             formats.append({
  66                 'url': video_url,
  67                 'ext': extension,
  68                 'format': format,
  69                 'format_id': format,
  70                 'tbr': tbr,
  71                 'height': height,
  72             })
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'uploader': video_uploader,
  78             'title': video_title,
  79             'thumbnail': thumbnail,
  80             'formats': formats,
  81             'age_limit': 18,
  82         }