[karrierevideos] add support for www.karrierevideos.at (closes #5354)
authorMister Hat <misterhat144@gmail.com>
Sun, 17 May 2015 00:50:58 +0000 (19:50 -0500)
committerMister Hat <misterhat144@gmail.com>
Sun, 17 May 2015 00:50:58 +0000 (19:50 -0500)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/karrierevideos.py [new file with mode: 0644]

index fb4f63ca3aef64530329b386307e962944f989ae..d131d3ec31645e30611be62180d95e488ebbdcc6 100644 (file)
@@ -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 (file)
index 0000000..59d29e8
--- /dev/null
@@ -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'
+        }