From 95dc46f2bc608c118ac5b54baff33e0becd5f416 Mon Sep 17 00:00:00 2001 From: Chomba Ng'ang'a Date: Tue, 24 Dec 2013 17:29:40 +0300 Subject: [PATCH] Removing extra 'doc' extension, adding 'pptx' and 'xlsx' extensions --- scrapy/linkextractor.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scrapy/linkextractor.py b/scrapy/linkextractor.py index 59e1edee7..946c82062 100644 --- a/scrapy/linkextractor.py +++ b/scrapy/linkextractor.py @@ -17,8 +17,8 @@ IGNORED_EXTENSIONS = [ 'm4a', # office suites - 'xls', 'ppt', 'doc', 'docx', 'odt', 'ods', 'odg', 'odp', + 'xls', 'xlsx', 'ppt', 'pptx', 'doc', 'docx', 'odt', 'ods', 'odg', 'odp', # other - 'css', 'pdf', 'doc', 'exe', 'bin', 'rss', 'zip', 'rar', + 'css', 'pdf', 'exe', 'bin', 'rss', 'zip', 'rar', ]