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