aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-05-24 19:19:48 +0600
committerSergey M․ <dstftw@gmail.com>2015-05-24 19:19:48 +0600
commit05a976cd99ef2a0eb0b301cd4f98e1aec927968c (patch)
treefd785f786699ac771855a5121bc38f58a1868e32 /youtube_dl/extractor
parent34fb7e46ad3fa1a04635fa4876401aac881bb39b (diff)
parentba9d16291b8ace3bd412bcfc0c128c047545e509 (diff)
Merge branch 'karrierevideos' of https://github.com/misterhat/youtube-dl into misterhat-karrierevideos
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/karrierevideos.py50
2 files changed, 51 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 8bb3926a0..79bcd9106 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..a05e8ab76
--- /dev/null
+++ b/youtube_dl/extractor/karrierevideos.py
@@ -0,0 +1,50 @@
+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=' + playlist,
+ video_id)
+
+ namespace = 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
+
+ item = playlist.find('tracklist/item')
+ streamer = item.find('{%s}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('{%s}file' % namespace).text,
+ 'tc_url': streamer,
+ 'ext': 'mp4'
+ }