youtube_dl/extractor/websurg.py

   1 # coding: utf-8
   2
   3 import re
   4
   5 from ..utils import (
   6     compat_urllib_request,
   7     compat_urllib_parse
   8 )
   9
  10 from .common import InfoExtractor
  11
  12 class WeBSurgIE(InfoExtractor):
  13     IE_NAME = u'websurg.com'
  14     _VALID_URL = r'http://.*?\.websurg\.com/MEDIA/\?noheader=1&doi=(.*)'
  15
  16     _TEST = {
  17         u'url': u'http://www.websurg.com/MEDIA/?noheader=1&doi=vd01en4012',
  18         u'file': u'vd01en4012.mp4',
  19         u'params': {
  20             u'skip_download': True,
  21         },
  22         u'skip': u'Requires login information',
  23     }
  24
  25     _LOGIN_URL = 'http://www.websurg.com/inc/login/login_div.ajax.php?login=1'
  26
  27     def _real_initialize(self):
  28
  29         login_form = {
  30             'username': self._downloader.params['username'],
  31             'password': self._downloader.params['password'],
  32             'Submit': 1
  33         }
  34
  35         request = compat_urllib_request.Request(
  36             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
  37         request.add_header(
  38             'Content-Type', 'application/x-www-form-urlencoded;charset=utf-8')
  39         compat_urllib_request.urlopen(request).info()
  40         webpage = self._download_webpage(self._LOGIN_URL, '', 'Logging in')
  41
  42         if webpage != 'OK':
  43             self._downloader.report_error(
  44                 u'Unable to log in: bad username/password')
  45
  46     def _real_extract(self, url):
  47         video_id = re.match(self._VALID_URL, url).group(1)
  48
  49         webpage = self._download_webpage(url, video_id)
  50
  51         url_info = re.search(r'streamer="(.*?)" src="(.*?)"', webpage)
  52
  53         return {'id': video_id,
  54                 'title': self._og_search_title(webpage),
  55                 'description': self._og_search_description(webpage),
  56                 'ext' : 'mp4',
  57                 'url' : url_info.group(1) + '/' + url_info.group(2),
  58                 'thumbnail': self._og_search_thumbnail(webpage)
  59                 }