yt-dlc/youtube_dl/extractor/spiegel.py

65 lines
2.3 KiB
Python
Raw Normal View History

2013-06-23 22:22:08 +02:00
import re
from .common import InfoExtractor
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
2013-11-16 01:33:12 +01:00
_TESTS = [{
2013-06-27 20:46:46 +02:00
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"
}
2013-11-16 01:33:12 +01:00
},
{
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'
}
}]
2013-06-23 22:22:08 +02:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
2013-11-16 01:33:12 +01:00
video_title = self._html_search_regex(
r'<div class="module-title">(.*?)</div>', webpage, u'title')
2013-06-23 22:22:08 +02:00
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
idoc = self._download_xml(
2013-11-16 01:33:12 +01:00
xml_url, video_id,
note=u'Downloading XML', errnote=u'Failed to download XML')
2013-06-23 22:22:08 +02:00
2013-11-16 01:33:12 +01:00
formats = [
{
'format_id': n.tag.rpartition('type')[2],
'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text,
'width': int(n.find('./width').text),
'height': int(n.find('./height').text),
'abr': int(n.find('./audiobitrate').text),
'vbr': int(n.find('./videobitrate').text),
'vcodec': n.find('./codec').text,
'acodec': 'MP4A',
}
for n in list(idoc)
# Blacklist type 6, it's extremely LQ and not available on the same server
if n.tag.startswith('type') and n.tag != 'type6'
]
duration = float(idoc[0].findall('./duration')[0].text)
2013-12-24 12:40:23 +01:00
self._sort_formats(formats)
2013-06-23 22:22:08 +02:00
info = {
'id': video_id,
'title': video_title,
'duration': duration,
2013-11-16 01:33:12 +01:00
'formats': formats,
2013-06-23 22:22:08 +02:00
}
2013-11-16 01:33:12 +01:00
return info