gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

Add an extractor for Szombathelyi TV

Browse source
This commit is contained in:
Andras Elso 2013-10-14 13:07:47 +02:00
parent ea62a2da46
commit f9b3d7af47
2 changed files with 42 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View file

@ -112,6 +112,7 @@ from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE from .statigram import StatigramIE
from .steam import SteamIE from .steam import SteamIE
from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE from .teamcoco import TeamcocoIE
from .ted import TEDIE from .ted import TEDIE
from .tf1 import TF1IE from .tf1 import TF1IE

41
youtube_dl/extractor/sztvhu.py Normal file
View file

@ -0,0 +1,41 @@
# -*- coding: utf-8 -*-
import re
from .common import InfoExtractor
from ..utils import determine_ext
class SztvHuIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/([^/]+)/(?P<name>.+)'
_TEST = {
u'url': u'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909',
u'file': u'130909zoldnap.mp4',
u'md5': u'0047eacedc0afd1ceeac99e69173a07e',
u'info_dict': {
u"title": u"Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren",
u"description" : u'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
# file = self._search_regex(r'var fileHtml5 = "...:(.*?)";',
file = self._search_regex(r'file: "...:(.*?)",',
webpage, 'video file')
title = self._html_search_regex(r'<meta name="title" content="([^"]*)"',
webpage, 'video title').rsplit(' - ', 2)[0]
description = self._html_search_regex(r'<meta name="description" content="([^"]*)"/>',
webpage, 'video description')
thumbnail = self._og_search_thumbnail(webpage)
video_url = 'http://media.sztv.hu/vod/' + file
return {'id': name,
'url' : video_url,
'title': title,
'ext': determine_ext(video_url),
'description': description,
'thumbnail': thumbnail,
}