[20min.ch] Added support for videoportal

pull/8110/merge
pingtux 2016-01-02 16:19:05 +01:00 committed by Sergey M․
parent e54c44eeab
commit 66295fa4a6
1 changed files with 21 additions and 5 deletions

View File

@ -1,12 +1,14 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
class Min20IE(InfoExtractor): class Min20IE(InfoExtractor):
_VALID_URL = r'http://www\.20min\.ch/.+?-(?P<id>[0-9]+)$' _VALID_URL = r'http://www\.20min\.ch/(videotv/\?vid=(?P<video_id>[0-9]+)|.+?-(?P<page_id>[0-9]+)$)'
_TEST = { _TESTS = [{
'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469', 'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
'md5': 'cd4cbb99b94130cff423e967cd275e5e', 'md5': 'cd4cbb99b94130cff423e967cd275e5e',
'info_dict': { 'info_dict': {
@ -16,15 +18,29 @@ class Min20IE(InfoExtractor):
'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.', 'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg' 'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
} }
}, {
'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
'md5': 'b52d6bc6ea6398e6a38f12cfd418149c',
'info_dict': {
'id': '469148',
'ext': 'flv',
'title': '85 000 Franken für 15 perfekte Minuten',
'description': 'Was die Besucher vom Silvesterzauber erwarten können. (Video: Alice Grosjean/Murat Temel)',
'thumbnail': 'http://thumbnails.20min-tv.ch/server063/469148/frame-72-469148.jpg'
} }
}]
# location of the flv videos, can't be extracted from the web page # location of the flv videos, can't be extracted from the web page
_BASE_URL = "http://flv-rr.20min-tv.ch/videos/" _BASE_URL = "http://flv-rr.20min-tv.ch/videos/"
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('page_id')
if video_id is None:
# URL from the videoportal
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1><span>(.+?)</span></h1>', webpage, 'title') title = self._html_search_regex(r'<h1>.*<span>(.+?)</span></h1>', webpage, 'title')
flash_id = self._search_regex(r"so\.addVariable\(\"file1\",\"([0-9]+)\"\)", webpage, 'flash_id') flash_id = self._search_regex(r"so\.addVariable\(\"file1\",\"([0-9]+)\"\)", webpage, 'flash_id')
description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'description') description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'description')