_ Git - youtube-dl/blob - 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         }
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(url, video_id)
  37         json_url = self._search_regex(
  38             r'json_url:\s*"([^"]+)"', webpage, 'json URL')
  39         config = self._download_json(json_url, video_id)
  40
  41         info = {
  42             'id': video_id,
  43             'thumbnail': config.get('poster'),
  44             'timestamp': parse_iso8601(get_meta_content('date', webpage)),
  45         }
  46
  47         title = get_meta_content('fulltitle', webpage)
  48         if title:
  49             info['title'] = title
  50         elif config.get('title'):
  51             info['title'] = config['title']
  52         else:
  53             info['title'] = self._og_search_title(webpage)
  54
  55         formats = []
  56         for t, rs in config['formats'].items():
  57             if not rs or not hasattr(rs, 'items'):
  58                 self._downloader.report_warning(
  59                     'formats: {0}: no resolutions'.format(t))
  60                 continue
  61
  62             for height_str, obj in rs.items():
  63                 format_id = '{0}_{1}'.format(t, height_str)
  64
  65                 if not obj or not obj.get('url'):
  66                     self._downloader.report_warning(
  67                         'formats: {0}: no url'.format(format_id))
  68                     continue
  69
  70                 formats.append({
  71                     'url': obj['url'],
  72                     'format_id': format_id,
  73                     'height': self._int(height_str, 'height'),
  74                 })
  75
  76         self._sort_formats(formats)
  77         info['formats'] = formats
  78
  79         return info