From 33b53b60212ca28f589616f1acb650b323a18f11 Mon Sep 17 00:00:00 2001 From: MaxReimann Date: Sun, 21 Dec 2014 12:26:47 +0100 Subject: [PATCH] [teletask] Add new extractor --- youtube_dl/extractor/teletask.py | 62 ++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/teletask.py b/youtube_dl/extractor/teletask.py index 6920b871e..aa5535042 100644 --- a/youtube_dl/extractor/teletask.py +++ b/youtube_dl/extractor/teletask.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals - -import re +import re import datetime from .common import InfoExtractor @@ -10,34 +9,59 @@ 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': '290ef69fb2792e481169c3958dbfbd57', + 'url': 'http://www.tele-task.de/archive/video/html5/26168/', 'info_dict': { - 'id': '26168', - 'ext': 'mp4', 'title': 'Duplicate Detection', - 'upload_date': '20141218', - } + }, + '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): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - + lecture_id = self._match_id(url) + webpage = self._download_webpage(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) - + 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'Date:([^"]+)', 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 { - 'id': video_id, + '_type': "playlist", + 'id': lecture_id, 'title': title, - 'url': url, - 'upload_date': date, - } \ No newline at end of file + 'entries': entries, + }