[spiegel] Add support for articles

This commit is contained in:
Philipp Hagemeister 2014-09-13 06:55:38 +02:00
parent b734a87112
commit 89fb6a9797
2 changed files with 33 additions and 1 deletions

View File

@ -325,7 +325,7 @@
) )
from .space import SpaceIE from .space import SpaceIE
from .spankwire import SpankwireIE from .spankwire import SpankwireIE
from .spiegel import SpiegelIE from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE from .spike import SpikeIE
from .sportdeutschland import SportDeutschlandIE from .sportdeutschland import SportDeutschlandIE

View File

@ -4,6 +4,7 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import compat_urlparse
class SpiegelIE(InfoExtractor): class SpiegelIE(InfoExtractor):
@ -82,3 +83,34 @@ def _real_extract(self, url):
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
} }
class SpiegelArticleIE(InfoExtractor):
_VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
IE_NAME = 'Spiegel:Article'
IE_DESC = 'Articles on spiegel.de'
_TEST = {
'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
'info_dict': {
'id': '1516455',
'ext': 'mp4',
'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
'description': 're:^Patrick Kämnitz gehört.{100,}',
},
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage = self._download_webpage(url, video_id)
video_link = self._search_regex(
r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
'video page URL')
video_url = compat_urlparse.urljoin(
self.http_scheme() + '//spiegel.de/', video_link)
return {
'_type': 'url',
'url': video_url,
}