mirrors/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[sztvhu] Simplify

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-10-15 01:33:20 +02:00
parent 3ddf1a6d01
commit 7cf67fbe29
1 changed files with 24 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/sztvhu.py
View File

@ -5,12 +5,13 @@ 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>.+)'
_VALID_URL = r'(?:http://)?(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
_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'file': u'20130909.mp4',
u'md5': u'a6df607b11fb07d0e9f2ad94613375cb',
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...',
@ -19,20 +20,22 @@ class SztvHuIE(InfoExtractor):
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')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_file = self._search_regex(
r'file: "...:(.*?)",', webpage, 'video file')
title = self._html_search_regex(
r'<meta name="title" content="([^"]*) - [^-]*"',
webpage, 'video title')
description = self._html_search_regex(
r'<meta name="description" content="([^"]*)"/>',
webpage, 'video description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
video_url = 'http://media.sztv.hu/vod/' + file
video_url = 'http://media.sztv.hu/vod/' + video_file
return {'id': name,
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': determine_ext(video_url),