[teletask] Simplify

This commit is contained in:
Sergey M․ 2014-12-25 23:26:57 +06:00
parent 2b8f151094
commit 885e4384a1

View file

@ -1,13 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import datetime
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unified_strdate
class TeleTaskIE(InfoExtractor): class TeleTaskIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/' _VALID_URL = r'https?://(?: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': { 'info_dict': {
@ -16,52 +16,38 @@ class TeleTaskIE(InfoExtractor):
'playlist': [{ 'playlist': [{
'md5': '290ef69fb2792e481169c3958dbfbd57', 'md5': '290ef69fb2792e481169c3958dbfbd57',
'info_dict': { 'info_dict': {
'id': '26168-speaker',
'ext': 'mp4',
'title': 'Duplicate Detection', 'title': 'Duplicate Detection',
'upload_date': '20141218', 'upload_date': '20141218',
'id': 'speaker_26168',
'ext': 'mp4',
} }
}, }, {
{
'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
'info_dict': { 'info_dict': {
'id': '26168-slides',
'ext': 'mp4',
'title': 'Duplicate Detection', 'title': 'Duplicate Detection',
'upload_date': '20141218', 'upload_date': '20141218',
'id': 'slides_26168',
'ext': 'mp4',
} }
}] }]
} }
def _real_extract(self, url): def _real_extract(self, url):
lecture_id = self._match_id(url) lecture_id = self._match_id(url)
webpage = self._download_webpage(url, lecture_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_speaker = self._html_search_regex( upload_date = unified_strdate(self._html_search_regex(
r'class="speaker".*?src="([^"]+)"', webpage, 'video_url_speaker', flags=re.DOTALL) r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False))
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 = [{ entries = [{
'id': '%s-%s' % (lecture_id, format_id),
'url': video_url,
'title': title, 'title': title,
'upload_date': date, 'upload_date': upload_date,
'id': "speaker_"+lecture_id, } for format_id, video_url in re.findall(
'url': url_speaker, r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)]
},
{
'title': title,
'upload_date': date,
'id': "slides_"+lecture_id,
'url': url_slides}]
return { return self.playlist_result(entries, lecture_id, title)
'_type': "playlist",
'id': lecture_id,
'title': title,
'entries': entries,
}