|
@ -1,3 +1,5 @@ |
|
|
|
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
import re |
|
|
import re |
|
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
from .common import InfoExtractor |
|
@ -6,20 +8,20 @@ from .common import InfoExtractor |
|
|
class SpiegelIE(InfoExtractor): |
|
|
class SpiegelIE(InfoExtractor): |
|
|
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' |
|
|
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' |
|
|
_TESTS = [{ |
|
|
_TESTS = [{ |
|
|
u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', |
|
|
|
|
|
u'file': u'1259285.mp4', |
|
|
|
|
|
u'md5': u'2c2754212136f35fb4b19767d242f66e', |
|
|
|
|
|
u'info_dict': { |
|
|
|
|
|
u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv" |
|
|
|
|
|
} |
|
|
|
|
|
|
|
|
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', |
|
|
|
|
|
'file': '1259285.mp4', |
|
|
|
|
|
'md5': '2c2754212136f35fb4b19767d242f66e', |
|
|
|
|
|
'info_dict': { |
|
|
|
|
|
'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', |
|
|
|
|
|
}, |
|
|
}, |
|
|
}, |
|
|
{ |
|
|
{ |
|
|
u'url': u'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', |
|
|
|
|
|
u'file': u'1309159.mp4', |
|
|
|
|
|
u'md5': u'f2cdf638d7aa47654e251e1aee360af1', |
|
|
|
|
|
u'info_dict': { |
|
|
|
|
|
u'title': u'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers' |
|
|
|
|
|
} |
|
|
|
|
|
|
|
|
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', |
|
|
|
|
|
'file': '1309159.mp4', |
|
|
|
|
|
'md5': 'f2cdf638d7aa47654e251e1aee360af1', |
|
|
|
|
|
'info_dict': { |
|
|
|
|
|
'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers', |
|
|
|
|
|
}, |
|
|
}] |
|
|
}] |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
def _real_extract(self, url): |
|
@ -29,17 +31,17 @@ class SpiegelIE(InfoExtractor): |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
|
|
|
|
|
|
video_title = self._html_search_regex( |
|
|
video_title = self._html_search_regex( |
|
|
r'<div class="module-title">(.*?)</div>', webpage, u'title') |
|
|
|
|
|
|
|
|
r'<div class="module-title">(.*?)</div>', webpage, 'title') |
|
|
|
|
|
|
|
|
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' |
|
|
|
|
|
|
|
|
xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml' |
|
|
idoc = self._download_xml( |
|
|
idoc = self._download_xml( |
|
|
xml_url, video_id, |
|
|
xml_url, video_id, |
|
|
note=u'Downloading XML', errnote=u'Failed to download XML') |
|
|
|
|
|
|
|
|
note='Downloading XML', errnote='Failed to download XML') |
|
|
|
|
|
|
|
|
formats = [ |
|
|
formats = [ |
|
|
{ |
|
|
{ |
|
|
'format_id': n.tag.rpartition('type')[2], |
|
|
'format_id': n.tag.rpartition('type')[2], |
|
|
'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text, |
|
|
|
|
|
|
|
|
'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text, |
|
|
'width': int(n.find('./width').text), |
|
|
'width': int(n.find('./width').text), |
|
|
'height': int(n.find('./height').text), |
|
|
'height': int(n.find('./height').text), |
|
|
'abr': int(n.find('./audiobitrate').text), |
|
|
'abr': int(n.find('./audiobitrate').text), |
|
@ -55,10 +57,9 @@ class SpiegelIE(InfoExtractor): |
|
|
|
|
|
|
|
|
self._sort_formats(formats) |
|
|
self._sort_formats(formats) |
|
|
|
|
|
|
|
|
info = { |
|
|
|
|
|
|
|
|
return { |
|
|
'id': video_id, |
|
|
'id': video_id, |
|
|
'title': video_title, |
|
|
'title': video_title, |
|
|
'duration': duration, |
|
|
'duration': duration, |
|
|
'formats': formats, |
|
|
'formats': formats, |
|
|
} |
|
|
} |
|
|
return info |
|
|
|