From ee45625290c678c53b7ee86d2adba40847b79573 Mon Sep 17 00:00:00 2001 From: MaxReimann Date: Sun, 21 Dec 2014 11:01:28 +0100 Subject: [PATCH] Add extractor for teletask --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/teletask.py | 59 ++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) create mode 100644 youtube_dl/extractor/teletask.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 76f13bf52..073ac1fab 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -405,6 +405,7 @@ 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..1c42ac6f4 --- /dev/null +++ b/youtube_dl/extractor/teletask.py @@ -0,0 +1,59 @@ +# 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[0-9]+)/' + _TEST = { + 'url': 'http://www.tele-task.de/archive/video/html5/26168/', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': '26168', + 'ext': 'mp4', + 'title': 'Duplicate Detection', + 'thumbnail': 're:^https?://.*\.jpg$', + 'date': '20141218', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + lecture_url = self._html_search_regex( + r'href="([^"]+)" itemprop="name">', webpage, 'title') + lecture_id = re.search("([0-9]+)/",lecture_url).group(1) + overview_page = self._download_webpage("http://www.tele-task.de" + lecture_url, + lecture_id) + + title = self._html_search_regex( + r'itemprop="name">([^"]+)', webpage, 'title') + url = self._html_search_regex( + r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL) + description = self._html_search_regex( + r'Description of the series:

([^"]+)', overview_page, + 'description',flags=re.DOTALL) + + date = self._html_search_regex( + r'Date:([^"]+)', webpage, 'date') + date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d') + + + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'url': url, + 'upload_date': date, + } \ No newline at end of file