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     str_to_int,
  14 )
  15 from ..aes import (
  16     aes_decrypt_text
  17 )
  18
  19
  20 class PornHubIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
  22     _TEST = {
  23         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  24         'md5': '882f488fa1f0026f023f33576004a2ed',
  25         'info_dict': {
  26             'id': '648719015',
  27             'ext': 'mp4',
  28             "uploader": "Babes",
  29             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
  30             "age_limit": 18
  31         }
  32     }
  33
  34     def _extract_count(self, pattern, webpage, name):
  35         count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
  36         if count:
  37             count = str_to_int(count)
  38         return count
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         req = compat_urllib_request.Request(url)
  44         req.add_header('Cookie', 'age_verified=1')
  45         webpage = self._download_webpage(req, video_id)
  46
  47         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
  48         video_uploader = self._html_search_regex(
  49             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
  50             webpage, 'uploader', fatal=False)
  51         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
  52         if thumbnail:
  53             thumbnail = compat_urllib_parse.unquote(thumbnail)
  54
  55         view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
  56         like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
  57         dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
  58         comment_count = self._extract_count(
  59             r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
  60
  61         video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
  62         if webpage.find('"encrypted":true') != -1:
  63             password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
  64             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  65
  66         formats = []
  67         for video_url in video_urls:
  68             path = compat_urllib_parse_urlparse(video_url).path
  69             extension = os.path.splitext(path)[1][1:]
  70             format = path.split('/')[5].split('_')[:2]
  71             format = "-".join(format)
  72
  73             m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
  74             if m is None:
  75                 height = None
  76                 tbr = None
  77             else:
  78                 height = int(m.group('height'))
  79                 tbr = int(m.group('tbr'))
  80
  81             formats.append({
  82                 'url': video_url,
  83                 'ext': extension,
  84                 'format': format,
  85                 'format_id': format,
  86                 'tbr': tbr,
  87                 'height': height,
  88             })
  89         self._sort_formats(formats)
  90
  91         return {
  92             'id': video_id,
  93             'uploader': video_uploader,
  94             'title': video_title,
  95             'thumbnail': thumbnail,
  96             'view_count': view_count,
  97             'like_count': like_count,
  98             'dislike_count': dislike_count,
  99             'comment_count': comment_count,
 100             'formats': formats,
 101             'age_limit': 18,
 102         }