diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-12-25 23:06:26 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-12-25 23:06:26 +0600 |
commit | 2b8f151094cdecc73343838bfce731983008664f (patch) | |
tree | f03cb90ddf2f6826dc2485d835b514a2220217e0 /youtube_dl/extractor | |
parent | 5ac71f0b27fbbca11517e5592978a2fe7bfd9f34 (diff) | |
parent | 33b53b60212ca28f589616f1acb650b323a18f11 (diff) | |
download | youtube-dl-2b8f151094cdecc73343838bfce731983008664f.tar.xz |
Merge branch 'teletask' of https://github.com/MaxReimann/youtube-dl into 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 | 67 |
2 files changed, 68 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..aa5535042 --- /dev/null +++ b/youtube_dl/extractor/teletask.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re +import datetime + +from .common import InfoExtractor + + +class TeleTaskIE(InfoExtractor): + _VALID_URL = r'http?://(?: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': { + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + 'id': 'speaker_26168', + 'ext': 'mp4', + } + }, + { + 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', + 'info_dict': { + 'title': 'Duplicate Detection', + 'upload_date': '20141218', + 'id': 'slides_26168', + 'ext': 'mp4', + } + }] + } + + 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') + url_speaker = self._html_search_regex( + r'class="speaker".*?src="([^"]+)"', webpage, 'video_url_speaker', flags=re.DOTALL) + url_slides = self._html_search_regex( + r'class="slides".*?src="([^"]+)"', webpage, 'video_url_slides', flags=re.DOTALL) + date = self._html_search_regex( + r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date') + date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d') + + entries = [{ + 'title': title, + 'upload_date': date, + 'id': "speaker_"+lecture_id, + 'url': url_speaker, + }, + { + 'title': title, + 'upload_date': date, + 'id': "slides_"+lecture_id, + 'url': url_slides}] + + return { + '_type': "playlist", + 'id': lecture_id, + 'title': title, + 'entries': entries, + } |