Raphaël G. Git Repositories - youtubedl/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         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  19         'md5': '65e20c48e6abff62ed0c3965fff13a39',
  20         'info_dict': {
  21             'id': '229795',
  22             'display_id': 'kasia-music-video',
  23             'ext': 'mp4',
  24             'description': 'hot teen Kasia grinding',
  25             'uploader': 'unknown',
  26             'title': 'Kasia music video',
  27             'age_limit': 18,
  28             'duration': 230,
  29         }
  30     }, {
  31         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38         display_id = mobj.group('display_id')
  39
  40         req = sanitized_Request(url)
  41         req.add_header('Cookie', 'age_verified=1')
  42         webpage = self._download_webpage(req, display_id)
  43
  44         flashvars = self._parse_json(
  45             self._search_regex(
  46                 r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'),
  47             video_id)
  48
  49         formats = []
  50         for key, video_url in flashvars.items():
  51             if not isinstance(video_url, compat_str) or not video_url.startswith('http'):
  52                 continue
  53             height = self._search_regex(
  54                 r'quality_(\d+)[pP]', key, 'height', default=None)
  55             if not height:
  56                 continue
  57             if flashvars.get('encrypted') is True:
  58                 video_url = aes_decrypt_text(
  59                     video_url, flashvars['video_title'], 32).decode('utf-8')
  60             formats.append({
  61                 'url': video_url,
  62                 'format_id': '%sp' % height,
  63                 'height': int(height),
  64             })
  65         self._sort_formats(formats)
  66
  67         thumbnail = flashvars.get('image_url')
  68
  69         title = self._html_search_regex(
  70             r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  71         description = self._html_search_regex(
  72             r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
  73         uploader = self._html_search_regex(
  74             r'<span class="username">\s*(.+?)\s*<',
  75             webpage, 'uploader', fatal=False)
  76         duration = int_or_none(flashvars.get('video_duration'))
  77
  78         like_count = int_or_none(self._search_regex(
  79             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  80         dislike_count = int_or_none(self._search_regex(
  81             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  82         view_count = str_to_int(self._search_regex(
  83             r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
  84             webpage, 'view count', fatal=False))
  85         comment_count = str_to_int(self._search_regex(
  86             r'<span id="allCommentsCount">(\d+)</span>',
  87             webpage, 'comment count', fatal=False))
  88
  89         return {
  90             'id': video_id,
  91             'display_id': display_id,
  92             'title': title,
  93             'description': description,
  94             'thumbnail': thumbnail,
  95             'uploader': uploader,
  96             'duration': duration,
  97             'view_count': view_count,
  98             'like_count': like_count,
  99             'dislike_count': dislike_count,
 100             'comment_count': comment_count,
 101             'age_limit': 18,
 102             'formats': formats,
 103         }