[teletask] Add new extractor

This commit is contained in:
MaxReimann 2014-12-21 12:26:47 +01:00
parent 3f7421b71b
commit 33b53b6021

View file

@ -1,6 +1,5 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import datetime import datetime
@ -11,33 +10,58 @@ class TeleTaskIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/' _VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/'
_TEST = { _TEST = {
'url': 'http://www.tele-task.de/archive/video/html5/26168/', 'url': 'http://www.tele-task.de/archive/video/html5/26168/',
'info_dict': {
'title': 'Duplicate Detection',
},
'playlist': [{
'md5': '290ef69fb2792e481169c3958dbfbd57', 'md5': '290ef69fb2792e481169c3958dbfbd57',
'info_dict': { 'info_dict': {
'id': '26168',
'ext': 'mp4',
'title': 'Duplicate Detection', 'title': 'Duplicate Detection',
'upload_date': '20141218', '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): def _real_extract(self, url):
video_id = self._match_id(url) lecture_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, lecture_id)
title = self._html_search_regex( title = self._html_search_regex(
r'itemprop="name">([^"]+)</a>', webpage, 'title') r'itemprop="name">([^"]+)</a>', webpage, 'title')
url = self._html_search_regex( url_speaker = self._html_search_regex(
r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL) 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( date = self._html_search_regex(
r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date') r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date')
date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d') 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 { return {
'id': video_id, '_type': "playlist",
'id': lecture_id,
'title': title, 'title': title,
'url': url, 'entries': entries,
'upload_date': date,
} }