Raphaël G. Git Repositories - youtubedl/blob - 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         'file': '229795.mp4',
  21         'md5': 'e9e0b0c86734e5e3766e653509475db0',
  22         'info_dict': {
  23             'description': 'hot teen Kasia grinding',
  24             'uploader': 'unknown',
  25             'title': 'Kasia music video',
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33
  34         req = compat_urllib_request.Request(url)
  35         req.add_header('Cookie', 'age_verified=1')
  36         webpage = self._download_webpage(req, video_id)
  37
  38         flashvars = json.loads(self._html_search_regex(
  39             r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
  40
  41         video_url = flashvars['video_url']
  42         if flashvars.get('encrypted') is True:
  43             video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
  44         path = compat_urllib_parse_urlparse(video_url).path
  45         format_id = '-'.join(path.split('/')[4].split('_')[:2])
  46
  47         thumbnail = flashvars.get('image_url')
  48
  49         title = self._html_search_regex(
  50             r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
  51         description = self._html_search_regex(
  52             r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
  53         uploader = self._html_search_regex(
  54             r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
  55             webpage, 'uploader', fatal=False)
  56
  57         like_count = int_or_none(self._html_search_regex(
  58             r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
  59         dislike_count = int_or_none(self._html_search_regex(
  60             r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
  61         view_count = self._html_search_regex(
  62             r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
  63         if view_count:
  64             view_count = str_to_int(view_count)
  65         comment_count = self._html_search_regex(
  66             r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
  67         if comment_count:
  68             comment_count = str_to_int(comment_count)
  69
  70         return {
  71             'id': video_id,
  72             'url': video_url,
  73             'title': title,
  74             'description': description,
  75             'thumbnail': thumbnail,
  76             'uploader': uploader,
  77             'format_id': format_id,
  78             'view_count': view_count,
  79             'like_count': like_count,
  80             'dislike_count': dislike_count,
  81             'comment_count': comment_count,
  82             'age_limit': 18,
  83         }