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 ..compat import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     str_to_int,
  14 )
  15 from ..aes import aes_decrypt_text
  16
  17
  18 class Tube8IE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  20     _TESTS = [
  21         {
  22             'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  23             'md5': '44bf12b98313827dd52d35b8706a4ea0',
  24             'info_dict': {
  25                 'id': '229795',
  26                 'display_id': 'kasia-music-video',
  27                 'ext': 'mp4',
  28                 'description': 'hot teen Kasia grinding',
  29                 'uploader': 'unknown',
  30                 'title': 'Kasia music video',
  31                 'age_limit': 18,
  32             }
  33         },
  34         {
  35             'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  36             'only_matching': True,
  37         },
  38     ]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         display_id = mobj.group('display_id')
  44
  45         req = compat_urllib_request.Request(url)
  46         req.add_header('Cookie', 'age_verified=1')
  47         webpage = self._download_webpage(req, display_id)
  48
  49         flashvars = json.loads(self._html_search_regex(
  50             r'flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
  51
  52         video_url = flashvars['video_url']
  53         if flashvars.get('encrypted') is True:
  54             video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
  55         path = compat_urllib_parse_urlparse(video_url).path
  56         format_id = '-'.join(path.split('/')[4].split('_')[:2])
  57
  58         thumbnail = flashvars.get('image_url')
  59
  60         title = self._html_search_regex(
  61             r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  62         description = self._html_search_regex(
  63             r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
  64         uploader = self._html_search_regex(
  65             r'<span class="username">\s*(.+?)\s*<',
  66             webpage, 'uploader', fatal=False)
  67
  68         like_count = int_or_none(self._html_search_regex(
  69             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  70         dislike_count = int_or_none(self._html_search_regex(
  71             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  72         view_count = self._html_search_regex(
  73             r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False)
  74         if view_count:
  75             view_count = str_to_int(view_count)
  76         comment_count = self._html_search_regex(
  77             r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
  78         if comment_count:
  79             comment_count = str_to_int(comment_count)
  80
  81         return {
  82             'id': video_id,
  83             'display_id': display_id,
  84             'url': video_url,
  85             'title': title,
  86             'description': description,
  87             'thumbnail': thumbnail,
  88             'uploader': uploader,
  89             'format_id': format_id,
  90             'view_count': view_count,
  91             'like_count': like_count,
  92             'dislike_count': dislike_count,
  93             'comment_count': comment_count,
  94             'age_limit': 18,
  95         }