2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_urlparse
10 class SpiegelIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.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/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
34 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51',
38 'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
39 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
45 webpage = self._download_webpage(url, video_id)
47 title = re.sub(r'\s+', ' ', self._html_search_regex(
48 r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',
50 description = self._html_search_meta('description', webpage, 'description')
52 base_url = self._search_regex(
53 r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
55 xml_url = base_url + video_id + '.xml'
56 idoc = self._download_xml(xml_url, video_id)
60 'format_id': n.tag.rpartition('type')[2],
61 'url': base_url + n.find('./filename').text,
62 'width': int(n.find('./width').text),
63 'height': int(n.find('./height').text),
64 'abr': int(n.find('./audiobitrate').text),
65 'vbr': int(n.find('./videobitrate').text),
66 'vcodec': n.find('./codec').text,
70 # Blacklist type 6, it's extremely LQ and not available on the same server
71 if n.tag.startswith('type') and n.tag != 'type6'
73 duration = float(idoc[0].findall('./duration')[0].text)
75 self._sort_formats(formats)
80 'description': description,
86 class SpiegelArticleIE(InfoExtractor):
87 _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
88 IE_NAME = 'Spiegel:Article'
89 IE_DESC = 'Articles on spiegel.de'
91 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
95 'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
96 'description': 're:^Patrick Kämnitz gehört.{100,}',
99 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
106 def _real_extract(self, url):
107 video_id = self._match_id(url)
108 webpage = self._download_webpage(url, video_id)
110 # Single video on top of the page
111 video_link = self._search_regex(
112 r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
113 'video page URL', default=None)
115 video_url = compat_urlparse.urljoin(
116 self.http_scheme() + '//spiegel.de/', video_link)
117 return self.url_result(video_url)
119 # Multiple embedded videos
121 r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
124 self.url_result(compat_urlparse.urljoin(
125 self.http_scheme() + '//spiegel.de/', embed_path))
126 for embed_path in embeds
128 return self.playlist_result(entries)