github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[Spiegel] move into own file

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-23 22:22:08 +02:00
parent 97d2db017c
commit 49f5f315fd
2 changed files with 38 additions and 31 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/InfoExtractors.py
View file

@ -47,6 +47,7 @@ from .extractor.photobucket import PhotobucketIE
from .extractor.pornotube import PornotubeIE from .extractor.pornotube import PornotubeIE
from .extractor.rbmaradio import RBMARadioIE from .extractor.rbmaradio import RBMARadioIE
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
from .extractor.spiegel import SpiegelIE
from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.stanfordoc import StanfordOpenClassroomIE
from .extractor.steam import SteamIE from .extractor.steam import SteamIE
from .extractor.ted import TEDIE from .extractor.ted import TEDIE
@ -90,37 +91,6 @@ from .extractor.zdf import ZDFIE
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
note=u'Downloading XML', errnote=u'Failed to download XML')
idoc = xml.etree.ElementTree.fromstring(xml_code)
last_type = idoc[-1]
filename = last_type.findall('./filename')[0].text
duration = float(last_type.findall('./duration')[0].text)
video_url = 'http://video2.spiegel.de/flash/' + filename
video_ext = filename.rpartition('.')[2]
info = {
'id': video_id,
'url': video_url,
'ext': video_ext,
'title': video_title,
'duration': duration,
}
return [info]
class LiveLeakIE(InfoExtractor): class LiveLeakIE(InfoExtractor):

37
youtube_dl/extractor/spiegel.py Normal file
View file

@ -0,0 +1,37 @@
import re
import xml.etree.ElementTree
from .common import InfoExtractor
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
note=u'Downloading XML', errnote=u'Failed to download XML')
idoc = xml.etree.ElementTree.fromstring(xml_code)
last_type = idoc[-1]
filename = last_type.findall('./filename')[0].text
duration = float(last_type.findall('./duration')[0].text)
video_url = 'http://video2.spiegel.de/flash/' + filename
video_ext = filename.rpartition('.')[2]
info = {
'id': video_id,
'url': video_url,
'ext': video_ext,
'title': video_title,
'duration': duration,
}
return [info]