2014-11-22 21:34:29 +09:00
|
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2016-04-11 03:06:05 +09:00
|
|
|
|
import re
|
|
|
|
|
|
2014-11-22 21:34:29 +09:00
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TeleBruxellesIE(InfoExtractor):
|
2016-12-07 03:01:09 +09:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
|
2014-11-22 21:34:29 +09:00
|
|
|
|
_TESTS = [{
|
2016-12-07 03:01:09 +09:00
|
|
|
|
'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
|
|
|
|
|
'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
|
2014-11-22 21:34:29 +09:00
|
|
|
|
'info_dict': {
|
2016-12-07 03:01:09 +09:00
|
|
|
|
'id': '158856',
|
|
|
|
|
'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
|
|
|
|
|
'description': 'md5:3cf8df235d44ebc5426373050840e466',
|
2014-11-23 17:44:42 +09:00
|
|
|
|
},
|
2014-11-22 21:34:29 +09:00
|
|
|
|
}, {
|
2016-12-07 03:01:09 +09:00
|
|
|
|
'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
|
|
|
|
|
'md5': 'dfe07ecc9c153ceba8582ac912687675',
|
2014-11-22 21:34:29 +09:00
|
|
|
|
'info_dict': {
|
2016-12-07 03:01:09 +09:00
|
|
|
|
'id': '158433',
|
|
|
|
|
'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
|
|
|
|
|
'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
|
2014-11-23 17:44:42 +09:00
|
|
|
|
},
|
2016-12-07 03:01:09 +09:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
|
|
|
|
|
'only_matching': True,
|
2014-11-23 17:44:42 +09:00
|
|
|
|
}]
|
2014-11-22 21:34:29 +09:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-11-23 17:44:42 +09:00
|
|
|
|
display_id = self._match_id(url)
|
|
|
|
|
webpage = self._download_webpage(url, display_id)
|
2014-11-22 21:34:29 +09:00
|
|
|
|
|
2014-11-23 17:44:42 +09:00
|
|
|
|
article_id = self._html_search_regex(
|
2016-04-11 03:06:05 +09:00
|
|
|
|
r"<article id=\"post-(\d+)\"", webpage, 'article ID', default=None)
|
2014-11-23 17:44:42 +09:00
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
|
2016-04-11 03:06:05 +09:00
|
|
|
|
description = self._og_search_description(webpage, default=None)
|
2014-11-22 21:34:29 +09:00
|
|
|
|
|
2014-11-23 17:44:42 +09:00
|
|
|
|
rtmp_url = self._html_search_regex(
|
2016-04-11 03:06:05 +09:00
|
|
|
|
r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
|
2014-11-23 17:44:42 +09:00
|
|
|
|
webpage, 'RTMP url')
|
2016-04-11 03:06:05 +09:00
|
|
|
|
rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
|
2016-12-07 03:01:09 +09:00
|
|
|
|
formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
|
|
|
|
|
self._sort_formats(formats)
|
2014-11-23 17:44:42 +09:00
|
|
|
|
|
|
|
|
|
return {
|
2016-04-11 03:06:05 +09:00
|
|
|
|
'id': article_id or display_id,
|
2014-11-23 17:44:42 +09:00
|
|
|
|
'display_id': display_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'description': description,
|
2016-12-07 03:01:09 +09:00
|
|
|
|
'formats': formats,
|
2014-11-23 17:44:42 +09:00
|
|
|
|
}
|