2 from __future__ import unicode_literals
6 from .common import InfoExtractor
9 class SpiegelIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
12 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
13 'md5': '2c2754212136f35fb4b19767d242f66e',
17 'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
18 'description': 'md5:8029d8310232196eb235d27575a8b9f4',
22 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
23 'md5': 'f2cdf638d7aa47654e251e1aee360af1',
27 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
28 'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
32 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
33 'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
37 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
38 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
43 def _real_extract(self, url):
44 m = re.match(self._VALID_URL, url)
45 video_id = m.group('videoID')
47 webpage = self._download_webpage(url, video_id)
49 title = self._html_search_regex(
50 r'<div class="module-title">(.*?)</div>', webpage, 'title')
51 description = self._html_search_meta('description', webpage, 'description')
53 base_url = self._search_regex(
54 r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
56 xml_url = base_url + video_id + '.xml'
57 idoc = self._download_xml(xml_url, video_id)
61 'format_id': n.tag.rpartition('type')[2],
62 'url': base_url + n.find('./filename').text,
63 'width': int(n.find('./width').text),
64 'height': int(n.find('./height').text),
65 'abr': int(n.find('./audiobitrate').text),
66 'vbr': int(n.find('./videobitrate').text),
67 'vcodec': n.find('./codec').text,
71 # Blacklist type 6, it's extremely LQ and not available on the same server
72 if n.tag.startswith('type') and n.tag != 'type6'
74 duration = float(idoc[0].findall('./duration')[0].text)
76 self._sort_formats(formats)
81 'description': description,