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

[telebruxelles] Simplify (#4270)

Browse Source
This commit is contained in:
Philipp Hagemeister
2014-11-23 09:44:42 +01:00
parent 119b3caa46
commit dd60be2bf9
1 changed files with 40 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
youtube_dl/extractor/telebruxelles.py
View File

@@ -1,49 +1,57 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class TeleBruxellesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<title>[^\?]+)'
_VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
_TESTS = [{
'url': r'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
'md5': '59439e568c9ee42fb77588b2096b214f',
'info_dict': {
'id': '11942',
'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
'ext': 'flv',
'title': 're:Parlement : Francken et Galant répondent aux interpellations*',
'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
'description': 're:Les auditions des ministres se poursuivent*'
}
},
'params': {
'skip_download': 'requires rtmpdump'
},
}, {
'url': r'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
'md5': '181d3fbdcf20b909309e5aef5c6c6047',
'info_dict': {
'id': '10091',
'display_id': 'basket-brussels-bat-mons-80-74',
'ext': 'flv',
'title': 'Basket : le Brussels bat Mons 80-74',
'description': 're:Ils l\u2019on fait ! En basket, le B*'
}
'description': 're:^Ils l\u2019on fait ! En basket, le B*',
},
'params': {
'skip_download': 'requires rtmpdump'
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, title)
article_id = self._html_search_regex(
r"<article id=\"post-(\d+)\"", webpage, 'article ID')
title = self._html_search_regex(
r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
description = self._og_search_description(webpage)
article_id = self._html_search_regex(r"<article id=\"post-(\d+)\"", webpage, '0')
title = self._html_search_regex(r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(r"property=\"og:description\" content=\"(.*?)\"", webpage, 'description', fatal=False)
rtmp_url = self._html_search_regex(r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"", webpage, 'url')
rtmp_url = self._html_search_regex(
r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"",
webpage, 'RTMP url')
rtmp_url = rtmp_url.replace("\" + \"", "")
return {
'id': article_id,
'display_id': display_id,
'title': title,
'description': description,
'url': rtmp_url,