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