From 9cba3c63a0b6af40a484bf9ebf92b23fe46b5c9e Mon Sep 17 00:00:00 2001 From: Romain Bignon Date: Sat, 27 Oct 2012 10:46:02 +0200 Subject: [PATCH] add url patterns and fix encoding issues --- modules/minutes20/browser.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/modules/minutes20/browser.py b/modules/minutes20/browser.py index 8edf59d7..0c977318 100644 --- a/modules/minutes20/browser.py +++ b/modules/minutes20/browser.py @@ -26,8 +26,9 @@ from .tools import id2url class Newspaper20minutesBrowser(BaseBrowser): "Newspaper20minutesBrowser class" + ENCODING = None PAGES = { - 'http://www.20minutes.fr/article/?.*': ArticlePage, + 'http://www.20minutes.fr/(?!preums|ledirect).+/?.*': ArticlePage, 'http://www.20minutes.fr/ledirect/?.*': SimplePage, 'http://www.20minutes.fr/preums/?.*': SimplePage }