diff options
author | Tjark Saul <tjark.saul@wachplan.net> | 2015-04-17 09:21:54 +0200 |
---|---|---|
committer | Tjark Saul <tjark.saul@wachplan.net> | 2015-04-17 09:21:54 +0200 |
commit | f11554092b419baa919875432fe6ebc1f22f5307 (patch) | |
tree | de99112d44737084b50be462d4252483dca9fec2 | |
parent | 8da1bb04186d4147f89923abc09a9db0fa2a4fec (diff) |
[Lecture2Go] Add new extractor
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/lecture2go.py | 33 |
2 files changed, 34 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index bbf3be41d..3d6e981b2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -249,6 +249,7 @@ from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .lecture2go import Lecture2GoIE from .letv import ( LetvIE, LetvTvIE, diff --git a/youtube_dl/extractor/lecture2go.py b/youtube_dl/extractor/lecture2go.py new file mode 100644 index 000000000..9cf28e31c --- /dev/null +++ b/youtube_dl/extractor/lecture2go.py @@ -0,0 +1,33 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class Lecture2GoIE(InfoExtractor): + _VALID_URL = r'https?://lecture2go.uni-hamburg.de/veranstaltungen/-/v/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473', + 'md5': 'a9e76f83b3ef58019c4b7dbc35f406c1', + 'info_dict': { + 'id': '17473', + 'ext': 'mp4', + 'url': 'https://fms1.rrz.uni-hamburg.de/abo/64.050_FrankHeitmann_2015-04-13_14-35.mp4', + 'title': '2 - Endliche Automaten und reguläre Sprachen' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<em class="title">(.*?)</em>', webpage, 'title') + video_url = self._search_regex(r'b.isFirefox..a.useHTML5\).b.setOption.a,"src","(.*.mp4)"\).else', webpage, 'video_url') + creator = self._html_search_regex(r'<div id="description">(.*)</div>', webpage, 'creator') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'creator': creator + } |