youtube_dl/extractor/golem.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_str,
   7     compat_urlparse,
   8 )
   9 from ..utils import (
  10     determine_ext,
  11 )
  12
  13
  14 class GolemIE(InfoExtractor):
  15     _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
  16     _TEST = {
  17         'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
  18         'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
  19         'info_dict': {
  20             'id': '14095',
  21             'format_id': 'high',
  22             'ext': 'mp4',
  23             'title': 'iPhone 6 und 6 Plus - Test',
  24             'duration': 300.44,
  25             'filesize': 65309548,
  26         }
  27     }
  28
  29     _PREFIX = 'http://video.golem.de'
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         config = self._download_xml(
  35             'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
  36
  37         info = {
  38             'id': video_id,
  39             'title': config.findtext('./title', 'golem'),
  40             'duration': self._float(config.findtext('./playtime'), 'duration'),
  41         }
  42
  43         formats = []
  44         for e in config:
  45             url = e.findtext('./url')
  46             if not url:
  47                 continue
  48
  49             formats.append({
  50                 'format_id': compat_str(e.tag),
  51                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  52                 'height': self._int(e.get('height'), 'height'),
  53                 'width': self._int(e.get('width'), 'width'),
  54                 'filesize': self._int(e.findtext('filesize'), 'filesize'),
  55                 'ext': determine_ext(e.findtext('./filename')),
  56             })
  57         self._sort_formats(formats)
  58         info['formats'] = formats
  59
  60         thumbnails = []
  61         for e in config.findall('.//teaser'):
  62             url = e.findtext('./url')
  63             if not url:
  64                 continue
  65             thumbnails.append({
  66                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  67                 'width': self._int(e.get('width'), 'thumbnail width'),
  68                 'height': self._int(e.get('height'), 'thumbnail height'),
  69             })
  70         info['thumbnails'] = thumbnails
  71
  72         return info