Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tube8.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from ..utils import (
   6     int_or_none,
   7     str_to_int,
   8 )
   9 from .keezmovies import KeezMoviesIE
  10
  11
  12 class Tube8IE(KeezMoviesIE):
  13     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  14     _TESTS = [{
  15         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  16         'md5': '65e20c48e6abff62ed0c3965fff13a39',
  17         'info_dict': {
  18             'id': '229795',
  19             'display_id': 'kasia-music-video',
  20             'ext': 'mp4',
  21             'description': 'hot teen Kasia grinding',
  22             'uploader': 'unknown',
  23             'title': 'Kasia music video',
  24             'age_limit': 18,
  25             'duration': 230,
  26             'categories': ['Teen'],
  27             'tags': ['dancing'],
  28         },
  29     }, {
  30         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  31         'only_matching': True,
  32     }]
  33
  34     @staticmethod
  35     def _extract_urls(webpage):
  36         return re.findall(
  37             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
  38             webpage)
  39
  40     def _real_extract(self, url):
  41         webpage, info = self._extract_info(url)
  42
  43         if not info['title']:
  44             info['title'] = self._html_search_regex(
  45                 r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  46
  47         description = self._html_search_regex(
  48             r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
  49         uploader = self._html_search_regex(
  50             r'<span class="username">\s*(.+?)\s*<',
  51             webpage, 'uploader', fatal=False)
  52
  53         like_count = int_or_none(self._search_regex(
  54             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  55         dislike_count = int_or_none(self._search_regex(
  56             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  57         view_count = str_to_int(self._search_regex(
  58             r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
  59             webpage, 'view count', fatal=False))
  60         comment_count = str_to_int(self._search_regex(
  61             r'<span id="allCommentsCount">(\d+)</span>',
  62             webpage, 'comment count', fatal=False))
  63
  64         category = self._search_regex(
  65             r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
  66             webpage, 'category', fatal=False)
  67         categories = [category] if category else None
  68
  69         tags_str = self._search_regex(
  70             r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
  71             webpage, 'tags', fatal=False)
  72         tags = [t for t in re.findall(
  73             r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
  74
  75         info.update({
  76             'description': description,
  77             'uploader': uploader,
  78             'view_count': view_count,
  79             'like_count': like_count,
  80             'dislike_count': dislike_count,
  81             'comment_count': comment_count,
  82             'categories': categories,
  83             'tags': tags,
  84         })
  85
  86         return info