Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tagesschau.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TagesschauIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html'
  11
  12     _TESTS = [{
  13         'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
  14         'md5': 'bcdeac2194fb296d599ce7929dfa4009',
  15         'info_dict': {
  16             'id': '1399128',
  17             'ext': 'mp4',
  18             'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
  19             'description': 'md5:69da3c61275b426426d711bde96463ab',
  20             'thumbnail': 're:^http:.*\.jpg$',
  21         },
  22     }, {
  23         'url': 'http://www.tagesschau.de/multimedia/video/video-5964.html',
  24         'md5': '66652566900963a3f962333579eeffcf',
  25         'info_dict': {
  26             'id': '5964',
  27             'ext': 'mp4',
  28             'title': 'Nahost-Konflikt: Israel bombadiert Ziele im Gazastreifen und Westjordanland',
  29             'description': 'md5:07bfc78c48eec3145ed4805299a1900a',
  30             'thumbnail': 're:http://.*\.jpg',
  31         },
  32     }]
  33
  34     _FORMATS = {
  35         's': {'width': 256, 'height': 144, 'quality': 1},
  36         'm': {'width': 512, 'height': 288, 'quality': 2},
  37         'l': {'width': 960, 'height': 544, 'quality': 3},
  38     }
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43
  44         if video_id.startswith('-'):
  45             display_id = video_id.strip('-')
  46         else:
  47             display_id = video_id
  48
  49         webpage = self._download_webpage(url, display_id)
  50
  51         playerpage = self._download_webpage(
  52             'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id,
  53             display_id, 'Downloading player page')
  54
  55         medias = re.findall(
  56             r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
  57             playerpage)
  58
  59         formats = []
  60         for url, ext, res in medias:
  61             f = {
  62                 'format_id': res + '_' + ext,
  63                 'url': url,
  64                 'ext': ext,
  65             }
  66             f.update(self._FORMATS.get(res, {}))
  67             formats.append(f)
  68
  69         self._sort_formats(formats)
  70
  71         thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
  72
  73         return {
  74             'id': display_id,
  75             'title': self._og_search_title(webpage).strip(),
  76             'thumbnail': 'http://www.tagesschau.de' + thumbnail,
  77             'formats': formats,
  78             'description': self._og_search_description(webpage).strip(),
  79         }