[mdr] Fix extraction (Closes #8702)

pull/8/head
Sergey M․ 9 years ago
parent 4b3cd7316c
commit 2812c24c16

@ -14,7 +14,7 @@ from ..utils import (
class MDRIE(InfoExtractor): class MDRIE(InfoExtractor):
IE_DESC = 'MDR.DE and KiKA' IE_DESC = 'MDR.DE and KiKA'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html' _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
_TESTS = [{ _TESTS = [{
# MDR regularly deletes its videos # MDR regularly deletes its videos
@ -60,6 +60,9 @@ class MDRIE(InfoExtractor):
}, { }, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html', 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -68,8 +71,8 @@ class MDRIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
data_url = self._search_regex( data_url = self._search_regex(
r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1', r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>\\?/.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
webpage, 'data url', group='url') webpage, 'data url', default=None, group='url').replace('\/', '/')
doc = self._download_xml( doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id) compat_urlparse.urljoin(url, data_url), video_id)

Loading…
Cancel
Save