aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/karrierevideos.py52
2 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index fb4f63ca3..d131d3ec3 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -244,6 +244,7 @@ from .kaltura import KalturaIE
from .kanalplay import KanalPlayIE
from .kankan import KankanIE
from .karaoketv import KaraoketvIE
+from .karrierevideos import KarriereVideosIE
from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
diff --git a/youtube_dl/extractor/karrierevideos.py b/youtube_dl/extractor/karrierevideos.py
new file mode 100644
index 000000000..59d29e845
--- /dev/null
+++ b/youtube_dl/extractor/karrierevideos.py
@@ -0,0 +1,52 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class KarriereVideosIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?karrierevideos\.at/berufsvideos/([a-z-]+)/(?P<id>[a-z-]+)'
+ _TEST = {
+ 'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
+ 'info_dict': {
+ 'id': 'altenpflegerin',
+ 'ext': 'mp4',
+ 'title': 'AltenpflegerIn',
+ 'thumbnail': 're:^http://.*\.png\?v=[0-9]+',
+ 'description': 'md5:dbadd1259fde2159a9b28667cb664ae2'
+ },
+ 'params': {
+ 'skip_download': 'requires rtmpdump'
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ description = self._html_search_regex(
+ r'<div class="leadtext">\n{0,}?\s{0,}<p>(.*?)</p>',
+ webpage, 'description')
+
+ playlist = self._html_search_regex(r'/config/video/(.*?)\.xml', webpage, 'playlist')
+ playlist = self._download_xml(
+ 'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % playlist,
+ video_id)
+
+ namespace = {
+ 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
+ }
+
+ item = playlist.find('tracklist/item')
+ streamer = item.find('jwplayer:streamer', namespace).text
+
+ return {
+ 'id': video_id,
+ 'title': self._html_search_meta('title', webpage),
+ 'description': description,
+ 'thumbnail': 'http://www.karrierevideos.at' + self._html_search_meta('thumbnail', webpage),
+ 'protocol': 'rtmp',
+ 'url': streamer.replace('rtmpt', 'http'),
+ 'play_path': 'mp4:' + item.find('jwplayer:file', namespace).text,
+ 'tc_url': streamer,
+ 'ext': 'mp4'
+ }