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

   1 from __future__ import unicode_literals
   2
   3 import os
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10     compat_urllib_parse,
  11 )
  12 from ..aes import (
  13     aes_decrypt_text
  14 )
  15
  16
  17 class SpankwireIE(InfoExtractor):
  18     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
  19     _TEST = {
  20         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  21         'file': '103545.mp4',
  22         'md5': '1b3f55e345500552dbc252a3e9c1af43',
  23         'info_dict': {
  24             "uploader": "oreusz",
  25             "title": "Buckcherry`s X Rated Music Video Crazy Bitch",
  26             "description": "Crazy Bitch X rated 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('videoid')
  34         url = 'http://www.' + mobj.group('url')
  35
  36         req = compat_urllib_request.Request(url)
  37         req.add_header('Cookie', 'age_verified=1')
  38         webpage = self._download_webpage(req, video_id)
  39
  40         video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
  41         video_uploader = self._html_search_regex(
  42             r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
  43         thumbnail = self._html_search_regex(
  44             r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
  45         description = self._html_search_regex(
  46             r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
  47
  48         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
  49         if webpage.find('flashvars\.encrypted = "true"') != -1:
  50             password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ')
  51             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  52
  53         formats = []
  54         for video_url in video_urls:
  55             path = compat_urllib_parse_urlparse(video_url).path
  56             extension = os.path.splitext(path)[1][1:]
  57             format = path.split('/')[4].split('_')[:2]
  58             resolution, bitrate_str = format
  59             format = "-".join(format)
  60             height = int(resolution.rstrip('P'))
  61             tbr = int(bitrate_str.rstrip('K'))
  62
  63             formats.append({
  64                 'url': video_url,
  65                 'ext': extension,
  66                 'resolution': resolution,
  67                 'format': format,
  68                 'tbr': tbr,
  69                 'height': height,
  70                 'format_id': format,
  71             })
  72         self._sort_formats(formats)
  73
  74         age_limit = self._rta_search(webpage)
  75
  76         return {
  77             'id': video_id,
  78             'uploader': video_uploader,
  79             'title': video_title,
  80             'thumbnail': thumbnail,
  81             'description': description,
  82             'formats': formats,
  83             'age_limit': age_limit,
  84         }