yt-dlp/youtube_dl/extractor/telebruxelles.py

61 lines
2.3 KiB
Python
Raw Normal View History

2014-11-22 07:34:29 -05:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class TeleBruxellesIE(InfoExtractor):
2014-11-23 03:44:42 -05:00
_VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
2014-11-22 07:34:29 -05:00
_TESTS = [{
2014-11-23 03:44:42 -05:00
'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
'md5': '59439e568c9ee42fb77588b2096b214f',
2014-11-22 07:34:29 -05:00
'info_dict': {
'id': '11942',
2014-11-23 03:44:42 -05:00
'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
2014-11-22 07:34:29 -05:00
'ext': 'flv',
2014-11-23 03:44:42 -05:00
'title': 'Parlement : Francken et Galant répondent aux interpellations de lopposition',
'description': 're:Les auditions des ministres se poursuivent*'
},
'params': {
'skip_download': 'requires rtmpdump'
},
2014-11-22 07:34:29 -05:00
}, {
2014-11-23 03:44:42 -05:00
'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
'md5': '181d3fbdcf20b909309e5aef5c6c6047',
2014-11-22 07:34:29 -05:00
'info_dict': {
'id': '10091',
2014-11-23 03:44:42 -05:00
'display_id': 'basket-brussels-bat-mons-80-74',
2014-11-22 07:34:29 -05:00
'ext': 'flv',
'title': 'Basket : le Brussels bat Mons 80-74',
2014-11-23 03:44:42 -05:00
'description': 're:^Ils l\u2019on fait ! En basket, le B*',
},
'params': {
'skip_download': 'requires rtmpdump'
},
}]
2014-11-22 07:34:29 -05:00
def _real_extract(self, url):
2014-11-23 03:44:42 -05:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2014-11-22 07:34:29 -05:00
2014-11-23 03:44:42 -05:00
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)
2014-11-22 07:34:29 -05:00
2014-11-23 03:44:42 -05:00
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,
'ext': 'flv',
'rtmp_live': True # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
}