2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import compat_urlparse
10 class SpiegelIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
13 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
14 'md5': '2c2754212136f35fb4b19767d242f66e',
18 'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
19 'description': 'md5:8029d8310232196eb235d27575a8b9f4',
23 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
24 'md5': 'f2cdf638d7aa47654e251e1aee360af1',
28 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
29 'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
33 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
34 'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
38 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
39 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
44 def _real_extract(self, url):
45 m = re.match(self._VALID_URL, url)
46 video_id = m.group('videoID')
48 webpage = self._download_webpage(url, video_id)
50 title = self._html_search_regex(
51 r'<div class="module-title">(.*?)</div>', webpage, 'title')
52 description = self._html_search_meta('description', webpage, 'description')
54 base_url = self._search_regex(
55 r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
57 xml_url = base_url + video_id + '.xml'
58 idoc = self._download_xml(xml_url, video_id)
62 'format_id': n.tag.rpartition('type')[2],
63 'url': base_url + n.find('./filename').text,
64 'width': int(n.find('./width').text),
65 'height': int(n.find('./height').text),
66 'abr': int(n.find('./audiobitrate').text),
67 'vbr': int(n.find('./videobitrate').text),
68 'vcodec': n.find('./codec').text,
72 # Blacklist type 6, it's extremely LQ and not available on the same server
73 if n.tag.startswith('type') and n.tag != 'type6'
75 duration = float(idoc[0].findall('./duration')[0].text)
77 self._sort_formats(formats)
82 'description': description,
88 class SpiegelArticleIE(InfoExtractor):
89 _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
90 IE_NAME = 'Spiegel:Article'
91 IE_DESC = 'Articles on spiegel.de'
93 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
97 'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
98 'description': 're:^Patrick Kämnitz gehört.{100,}',
102 def _real_extract(self, url):
103 m = re.match(self._VALID_URL, url)
104 video_id = m.group('id')
106 webpage = self._download_webpage(url, video_id)
107 video_link = self._search_regex(
108 r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
110 video_url = compat_urlparse.urljoin(
111 self.http_scheme() + '//spiegel.de/', video_link)