Added a new extractor for the german news site in south tyrol www.sdf.bz.it

This commit is contained in:
Markus Golser 2018-10-06 08:53:35 +02:00
parent d98cb62e55
commit 66a73678fc
2 changed files with 43 additions and 0 deletions

View File

@ -974,6 +974,7 @@ from .sbs import SBSIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .scrippsnetworks import ScrippsNetworksWatchIE
from .sdf import SdfIE
from .seeker import SeekerIE
from .senateisvp import SenateISVPIE
from .sendtonews import SendtoNewsIE

View File

@ -0,0 +1,42 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class SdfIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sdf\.bz\.it/Mediathek/\(video\)/(?P<id>[0-9]+)'
_TESTS = [
{
'url': 'http://www.sdf.bz.it/Mediathek/(video)/62982',
'md5': 'c08bfa83e5a011dae3dab7d935ae1f7d',
'info_dict': {
'id': '62982',
'ext': 'mp4',
'title': 'Südtiroler Sporthilfe',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'http://www.sdf.bz.it/Mediathek/(video)/62981',
'md5': '9523207e57a0db6b322eccb70825142a',
'info_dict': {
'id': '62981',
'ext': 'mp4',
'title': 'Seelische Gesundheit',
'thumbnail': r're:^https?://.*\.jpg$',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
url = self._html_search_regex(r'(?s)file:\s\"(http.*?\.mp4)', webpage, 'url', fatal=True)
thumbnail = self._html_search_regex(r'(?s)image:\s\"(http.*?\.jpg)', webpage, 'thumbnail', fatal=True)
title = self._html_search_regex(r'(?s)\"og:title\"\scontent\=\"(.+?)\"\/>', webpage, 'title', default=video_id, fatal=False)
return (info_dict)
info_dict = {
'id': video_id,
'title': title,
'url': url,
'format': 'mp4',
'thumbnail': thumbnail,
}