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',
34 def _real_extract(self, url):
35 m = re.match(self._VALID_URL, url)
36 video_id = m.group('videoID')
38 webpage = self._download_webpage(url, video_id)
40 title = self._html_search_regex(
41 r'<div class="module-title">(.*?)</div>', webpage, 'title')
42 description = self._html_search_meta('description', webpage, 'description')
44 base_url = self._search_regex(
45 r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
47 xml_url = base_url + video_id + '.xml'
48 idoc = self._download_xml(xml_url, video_id)
52 'format_id': n.tag.rpartition('type')[2],
53 'url': base_url + n.find('./filename').text,
54 'width': int(n.find('./width').text),
55 'height': int(n.find('./height').text),
56 'abr': int(n.find('./audiobitrate').text),
57 'vbr': int(n.find('./videobitrate').text),
58 'vcodec': n.find('./codec').text,
62 # Blacklist type 6, it's extremely LQ and not available on the same server
63 if n.tag.startswith('type') and n.tag != 'type6'
65 duration = float(idoc[0].findall('./duration')[0].text)
67 self._sort_formats(formats)
72 'description': description,
78 class SpiegelArticleIE(InfoExtractor):
79 _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
80 IE_NAME = 'Spiegel:Article'
81 IE_DESC = 'Articles on spiegel.de'
83 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
87 'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
88 'description': 're:^Patrick Kämnitz gehört.{100,}',
92 def _real_extract(self, url):
93 m = re.match(self._VALID_URL, url)
94 video_id = m.group('id')
96 webpage = self._download_webpage(url, video_id)
97 video_link = self._search_regex(
98 r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
100 video_url = compat_urlparse.urljoin(
101 self.http_scheme() + '//spiegel.de/', video_link)