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     str_to_int,
  12 )
  13 from ..aes import (
  14     aes_decrypt_text
  15 )
  16
  17
  18 class PornHubIE(InfoExtractor):
  19     _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
  20     _TEST = {
  21         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  22         'md5': '882f488fa1f0026f023f33576004a2ed',
  23         'info_dict': {
  24             'id': '648719015',
  25             'ext': 'mp4',
  26             "uploader": "Babes",
  27             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
  28             "age_limit": 18
  29         }
  30     }
  31
  32     def _extract_count(self, pattern, webpage, name):
  33         count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
  34         if count:
  35             count = str_to_int(count)
  36         return count
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         req = compat_urllib_request.Request(url)
  42         req.add_header('Cookie', 'age_verified=1')
  43         webpage = self._download_webpage(req, video_id)
  44
  45         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
  46         video_uploader = self._html_search_regex(
  47             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
  48             webpage, 'uploader', fatal=False)
  49         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
  50         if thumbnail:
  51             thumbnail = compat_urllib_parse.unquote(thumbnail)
  52
  53         view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
  54         like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
  55         dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
  56         comment_count = self._extract_count(
  57             r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
  58
  59         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
  60         if webpage.find('"encrypted":true') != -1:
  61             password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
  62             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  63
  64         formats = []
  65         for video_url in video_urls:
  66             path = compat_urllib_parse_urlparse(video_url).path
  67             extension = os.path.splitext(path)[1][1:]
  68             format = path.split('/')[5].split('_')[:2]
  69             format = "-".join(format)
  70
  71             m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
  72             if m is None:
  73                 height = None
  74                 tbr = None
  75             else:
  76                 height = int(m.group('height'))
  77                 tbr = int(m.group('tbr'))
  78
  79             formats.append({
  80                 'url': video_url,
  81                 'ext': extension,
  82                 'format': format,
  83                 'format_id': format,
  84                 'tbr': tbr,
  85                 'height': height,
  86             })
  87         self._sort_formats(formats)
  88
  89         return {
  90             'id': video_id,
  91             'uploader': video_uploader,
  92             'title': video_title,
  93             'thumbnail': thumbnail,
  94             'view_count': view_count,
  95             'like_count': like_count,
  96             'dislike_count': dislike_count,
  97             'comment_count': comment_count,
  98             'formats': formats,
  99             'age_limit': 18,
 100         }