yt_dlp/extractor/nosvideo.py

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