_ Git - youtube-dl/blob - youtube_dl/extractor/tube8.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     sanitized_Request,
  10     str_to_int,
  11 )
  12 from ..aes import aes_decrypt_text
  13
  14
  15 class Tube8IE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  17     _TESTS = [
  18         {
  19             'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  20             'md5': '44bf12b98313827dd52d35b8706a4ea0',
  21             'info_dict': {
  22                 'id': '229795',
  23                 'display_id': 'kasia-music-video',
  24                 'ext': 'mp4',
  25                 'description': 'hot teen Kasia grinding',
  26                 'uploader': 'unknown',
  27                 'title': 'Kasia music video',
  28                 'age_limit': 18,
  29             }
  30         },
  31         {
  32             'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  33             'only_matching': True,
  34         },
  35     ]
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         display_id = mobj.group('display_id')
  41
  42         req = sanitized_Request(url)
  43         req.add_header('Cookie', 'age_verified=1')
  44         webpage = self._download_webpage(req, display_id)
  45
  46         flashvars = self._parse_json(
  47             self._search_regex(
  48                 r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'),
  49             video_id)
  50
  51         formats = []
  52         for key, video_url in flashvars.items():
  53             if not isinstance(video_url, compat_str) or not video_url.startswith('http'):
  54                 continue
  55             height = self._search_regex(
  56                 r'quality_(\d+)[pP]', key, 'height', default=None)
  57             if not height:
  58                 continue
  59             if flashvars.get('encrypted') is True:
  60                 video_url = aes_decrypt_text(
  61                     video_url, flashvars['video_title'], 32).decode('utf-8')
  62             formats.append({
  63                 'url': video_url,
  64                 'format_id': '%sp' % height,
  65                 'height': int(height),
  66             })
  67         self._sort_formats(formats)
  68
  69         thumbnail = flashvars.get('image_url')
  70
  71         title = self._html_search_regex(
  72             r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  73         description = self._html_search_regex(
  74             r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
  75         uploader = self._html_search_regex(
  76             r'<span class="username">\s*(.+?)\s*<',
  77             webpage, 'uploader', fatal=False)
  78
  79         like_count = int_or_none(self._html_search_regex(
  80             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  81         dislike_count = int_or_none(self._html_search_regex(
  82             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  83         view_count = self._html_search_regex(
  84             r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False)
  85         if view_count:
  86             view_count = str_to_int(view_count)
  87         comment_count = self._html_search_regex(
  88             r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
  89         if comment_count:
  90             comment_count = str_to_int(comment_count)
  91
  92         return {
  93             'id': video_id,
  94             'display_id': display_id,
  95             'title': title,
  96             'description': description,
  97             'thumbnail': thumbnail,
  98             'uploader': uploader,
  99             'view_count': view_count,
 100             'like_count': like_count,
 101             'dislike_count': dislike_count,
 102             'comment_count': comment_count,
 103             'age_limit': 18,
 104             'formats': formats,
 105         }