youtube_dl/extractor/tube8.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10     int_or_none,
  11     str_to_int,
  12 )
  13 from ..aes import aes_decrypt_text
  14
  15
  16 class Tube8IE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
  18     _TEST = {
  19         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  20         'md5': '44bf12b98313827dd52d35b8706a4ea0',
  21         'info_dict': {
  22             'id': '229795',
  23             'ext': 'mp4',
  24             'description': 'hot teen Kasia grinding',
  25             'uploader': 'unknown',
  26             'title': 'Kasia music video',
  27             'age_limit': 18,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34
  35         req = compat_urllib_request.Request(url)
  36         req.add_header('Cookie', 'age_verified=1')
  37         webpage = self._download_webpage(req, video_id)
  38
  39         flashvars = json.loads(self._html_search_regex(
  40             r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
  41
  42         video_url = flashvars['video_url']
  43         if flashvars.get('encrypted') is True:
  44             video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
  45         path = compat_urllib_parse_urlparse(video_url).path
  46         format_id = '-'.join(path.split('/')[4].split('_')[:2])
  47
  48         thumbnail = flashvars.get('image_url')
  49
  50         title = self._html_search_regex(
  51             r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
  52         description = self._html_search_regex(
  53             r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
  54         uploader = self._html_search_regex(
  55             r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
  56             webpage, 'uploader', fatal=False)
  57
  58         like_count = int_or_none(self._html_search_regex(
  59             r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
  60         dislike_count = int_or_none(self._html_search_regex(
  61             r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
  62         view_count = self._html_search_regex(
  63             r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
  64         if view_count:
  65             view_count = str_to_int(view_count)
  66         comment_count = self._html_search_regex(
  67             r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
  68         if comment_count:
  69             comment_count = str_to_int(comment_count)
  70
  71         return {
  72             'id': video_id,
  73             'url': video_url,
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'uploader': uploader,
  78             'format_id': format_id,
  79             'view_count': view_count,
  80             'like_count': like_count,
  81             'dislike_count': dislike_count,
  82             'comment_count': comment_count,
  83             'age_limit': 18,
  84         }