yt_dlp/extractor/golem.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4     compat_urlparse,
   5 )
   6 from ..utils import (
   7     determine_ext,
   8 )
   9
  10
  11 class GolemIE(InfoExtractor):
  12     _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
  13     _TEST = {
  14         'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
  15         'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
  16         'info_dict': {
  17             'id': '14095',
  18             'format_id': 'high',
  19             'ext': 'mp4',
  20             'title': 'iPhone 6 und 6 Plus - Test',
  21             'duration': 300.44,
  22             'filesize': 65309548,
  23         }
  24     }
  25
  26     _PREFIX = 'http://video.golem.de'
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         config = self._download_xml(
  32             'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
  33
  34         info = {
  35             'id': video_id,
  36             'title': config.findtext('./title', 'golem'),
  37             'duration': self._float(config.findtext('./playtime'), 'duration'),
  38         }
  39
  40         formats = []
  41         for e in config:
  42             url = e.findtext('./url')
  43             if not url:
  44                 continue
  45
  46             formats.append({
  47                 'format_id': compat_str(e.tag),
  48                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  49                 'height': self._int(e.get('height'), 'height'),
  50                 'width': self._int(e.get('width'), 'width'),
  51                 'filesize': self._int(e.findtext('filesize'), 'filesize'),
  52                 'ext': determine_ext(e.findtext('./filename')),
  53             })
  54         info['formats'] = formats
  55
  56         thumbnails = []
  57         for e in config.findall('.//teaser'):
  58             url = e.findtext('./url')
  59             if not url:
  60                 continue
  61             thumbnails.append({
  62                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  63                 'width': self._int(e.get('width'), 'thumbnail width'),
  64                 'height': self._int(e.get('height'), 'thumbnail height'),
  65             })
  66         info['thumbnails'] = thumbnails
  67
  68         return info