_ Git - youtube-dl/blob - youtube_dl/extractor/golem.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     compat_urlparse,
   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.findall('./*[url]'):
  44             url = e.findtext('./url')
  45             if not url:
  46                 self._downloader.report_warning(
  47                     "{0}: url: empty, skipping".format(e.tag))
  48                 continue
  49
  50             formats.append({
  51                 'format_id': e.tag,
  52                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  53                 'height': self._int(e.get('height'), 'height'),
  54                 'width': self._int(e.get('width'), 'width'),
  55                 'filesize': self._int(e.findtext('filesize'), 'filesize'),
  56                 'ext': determine_ext(e.findtext('./filename')),
  57             })
  58         self._sort_formats(formats)
  59         info['formats'] = formats
  60
  61         thumbnails = []
  62         for e in config.findall('.//teaser[url]'):
  63             url = e.findtext('./url')
  64             if not url:
  65                 continue
  66             thumbnails.append({
  67                 'url': compat_urlparse.urljoin(self._PREFIX, url),
  68                 'width': self._int(e.get('width'), 'thumbnail width'),
  69                 'height': self._int(e.get('height'), 'thumbnail height'),
  70             })
  71         info['thumbnails'] = thumbnails
  72
  73         return info