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

   1 from __future__ import unicode_literals
   2
   3 from ..utils import (
   4     int_or_none,
   5     str_to_int,
   6 )
   7 from .keezmovies import KeezMoviesIE
   8
   9
  10 class Tube8IE(KeezMoviesIE):
  11     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  12     _TESTS = [{
  13         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  14         'md5': '65e20c48e6abff62ed0c3965fff13a39',
  15         'info_dict': {
  16             'id': '229795',
  17             'display_id': 'kasia-music-video',
  18             'ext': 'mp4',
  19             'description': 'hot teen Kasia grinding',
  20             'uploader': 'unknown',
  21             'title': 'Kasia music video',
  22             'age_limit': 18,
  23             'duration': 230,
  24         }
  25     }, {
  26         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         webpage, info = self._extract_info(url)
  32
  33         if not info['title']:
  34             info['title'] = self._html_search_regex(
  35                 r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  36
  37         description = self._html_search_regex(
  38             r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
  39         uploader = self._html_search_regex(
  40             r'<span class="username">\s*(.+?)\s*<',
  41             webpage, 'uploader', fatal=False)
  42
  43         like_count = int_or_none(self._search_regex(
  44             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  45         dislike_count = int_or_none(self._search_regex(
  46             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  47         view_count = str_to_int(self._search_regex(
  48             r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
  49             webpage, 'view count', fatal=False))
  50         comment_count = str_to_int(self._search_regex(
  51             r'<span id="allCommentsCount">(\d+)</span>',
  52             webpage, 'comment count', fatal=False))
  53
  54         info.update({
  55             'description': description,
  56             'uploader': uploader,
  57             'view_count': view_count,
  58             'like_count': like_count,
  59             'dislike_count': dislike_count,
  60             'comment_count': comment_count,
  61         })
  62
  63         return info