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

   1 import os
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse_urlparse,
   7     compat_urllib_request,
   8     compat_urllib_parse,
   9 )
  10 from ..aes import (
  11     aes_decrypt_text
  12 )
  13
  14 class SpankwireIE(InfoExtractor):
  15     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
  16     _TEST = {
  17         u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  18         u'file': u'103545.mp4',
  19         u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
  20         u'info_dict': {
  21             u"uploader": u"oreusz",
  22             u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
  23             u"description": u"Crazy Bitch X rated music video.",
  24             u"age_limit": 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('videoid')
  31         url = 'http://www.' + mobj.group('url')
  32
  33         req = compat_urllib_request.Request(url)
  34         req.add_header('Cookie', 'age_verified=1')
  35         webpage = self._download_webpage(req, video_id)
  36
  37         video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
  38         video_uploader = self._html_search_regex(
  39             r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
  40         thumbnail = self._html_search_regex(
  41             r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
  42         description = self._html_search_regex(
  43             r'<div\s+id="descriptionContent">([^<]+)<', webpage, u'description', fatal=False)
  44
  45         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
  46         if webpage.find('flashvars\.encrypted = "true"') != -1:
  47             password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
  48             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
  49
  50         formats = []
  51         for video_url in video_urls:
  52             path = compat_urllib_parse_urlparse(video_url).path
  53             extension = os.path.splitext(path)[1][1:]
  54             format = path.split('/')[4].split('_')[:2]
  55             format = "-".join(format)
  56             formats.append({
  57                 'url': video_url,
  58                 'ext': extension,
  59                 'format': format,
  60                 'format_id': format,
  61             })
  62         formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
  63
  64         age_limit = self._rta_search(webpage)
  65
  66         return {
  67             'id': video_id,
  68             'uploader': video_uploader,
  69             'title': video_title,
  70             'thumbnail': thumbnail,
  71             'description': description,
  72             'formats': formats,
  73             'age_limit': age_limit,
  74         }