youtube_dl/extractor/nosvideo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     sanitized_Request,
  10     urlencode_postdata,
  11     xpath_text,
  12     xpath_with_ns,
  13 )
  14
  15 _x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
  16
  17
  18 class NosVideoIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
  20                  r'(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
  21     _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
  22     _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
  23     _TEST = {
  24         'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
  25         'md5': '6124ed47130d8be3eacae635b071e6b6',
  26         'info_dict': {
  27             'id': 'mu8fle7g7rpq',
  28             'ext': 'mp4',
  29             'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31         }
  32     }
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         fields = {
  38             'id': video_id,
  39             'op': 'download1',
  40             'method_free': 'Continue to Video',
  41         }
  42         req = sanitized_Request(url, urlencode_postdata(fields))
  43         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  44         webpage = self._download_webpage(req, video_id,
  45                                          'Downloading download page')
  46         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  47             raise ExtractorError('Video %s does not exist' % video_id,
  48                                  expected=True)
  49
  50         xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
  51         playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
  52         playlist = self._download_xml(playlist_url, video_id)
  53
  54         track = playlist.find(_x('.//xspf:track'))
  55         if track is None:
  56             raise ExtractorError(
  57                 'XML playlist is missing the \'track\' element',
  58                 expected=True)
  59         title = xpath_text(track, _x('./xspf:title'), 'title')
  60         url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
  61         thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
  62         if title is not None:
  63             title = title.strip()
  64
  65         formats = [{
  66             'format_id': 'sd',
  67             'url': url,
  68         }]
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'thumbnail': thumbnail,
  74             'formats': formats,
  75         }