youtube_dl/extractor/heise.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     get_meta_content,
   7     parse_iso8601,
   8 )
   9
  10
  11 class HeiseIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13         https?://(?:www\.)?heise\.de/video/artikel/
  14         .+?(?P<id>[0-9]+)\.html(?:$|[?#])
  15     '''
  16     _TEST = {
  17         'url': (
  18             'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
  19         ),
  20         'md5': 'ffed432483e922e88545ad9f2f15d30e',
  21         'info_dict': {
  22             'id': '2404147',
  23             'ext': 'mp4',
  24             'title': (
  25                 "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
  26             ),
  27             'format_id': 'mp4_720',
  28             'timestamp': 1411812600,
  29             'upload_date': '20140927',
  30             'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
  31         }
  32     }
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         webpage = self._download_webpage(url, video_id)
  38         json_url = self._search_regex(
  39             r'json_url:\s*"([^"]+)"', webpage, 'json URL')
  40         config = self._download_json(json_url, video_id)
  41
  42         info = {
  43             'id': video_id,
  44             'thumbnail': config.get('poster'),
  45             'timestamp': parse_iso8601(get_meta_content('date', webpage)),
  46             'description': self._og_search_description(webpage),
  47         }
  48
  49         title = get_meta_content('fulltitle', webpage)
  50         if title:
  51             info['title'] = title
  52         elif config.get('title'):
  53             info['title'] = config['title']
  54         else:
  55             info['title'] = self._og_search_title(webpage)
  56
  57         formats = []
  58         for t, rs in config['formats'].items():
  59             if not rs or not hasattr(rs, 'items'):
  60                 self._downloader.report_warning(
  61                     'formats: {0}: no resolutions'.format(t))
  62                 continue
  63
  64             for height_str, obj in rs.items():
  65                 format_id = '{0}_{1}'.format(t, height_str)
  66
  67                 if not obj or not obj.get('url'):
  68                     self._downloader.report_warning(
  69                         'formats: {0}: no url'.format(format_id))
  70                     continue
  71
  72                 formats.append({
  73                     'url': obj['url'],
  74                     'format_id': format_id,
  75                     'height': self._int(height_str, 'height'),
  76                 })
  77
  78         self._sort_formats(formats)
  79         info['formats'] = formats
  80
  81         return info