diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-12-25 23:27:23 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-12-25 23:27:23 +0600 |
commit | 3e2b085ef900dc74f8a50a04b8d3dab43e7e53e1 (patch) | |
tree | 24ee9df32cbdd0a2dd83331a243bede1df84f8bb /youtube_dl/extractor | |
parent | 5ac71f0b27fbbca11517e5592978a2fe7bfd9f34 (diff) | |
parent | 885e4384a1ad8b12037810824d15e9436134a148 (diff) | |
download | youtube-dl-3e2b085ef900dc74f8a50a04b8d3dab43e7e53e1.tar.xz |
Merge branch 'MaxReimann-teletask'
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/teletask.py | 53 |
2 files changed, 54 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 92aca503c..fd0ebffe3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -406,6 +406,7 @@ from .ted import TEDIE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telemb import TeleMBIE +from .teletask import TeleTaskIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE diff --git a/youtube_dl/extractor/teletask.py b/youtube_dl/extractor/teletask.py new file mode 100644 index 000000000..e54145105 --- /dev/null +++ b/youtube_dl/extractor/teletask.py @@ -0,0 +1,53 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class TeleTaskIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.tele-task.de/archive/video/html5/26168/', + 'info_dict': { + 'title': 'Duplicate Detection', + }, + 'playlist': [{ + 'md5': '290ef69fb2792e481169c3958dbfbd57', + 'info_dict': { + 'id': '26168-speaker', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }, { + 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', + 'info_dict': { + 'id': '26168-slides', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + } + }] + } + + def _real_extract(self, url): + lecture_id = self._match_id(url) + + webpage = self._download_webpage(url, lecture_id) + + title = self._html_search_regex( + r'itemprop="name">([^<]+)</a>', webpage, 'title') + upload_date = unified_strdate(self._html_search_regex( + r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False)) + + entries = [{ + 'id': '%s-%s' % (lecture_id, format_id), + 'url': video_url, + 'title': title, + 'upload_date': upload_date, + } for format_id, video_url in re.findall( + r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)] + + return self.playlist_result(entries, lecture_id, title) |