From 0e288d4a711f061a01a951d2e1d9892f737211e0 Mon Sep 17 00:00:00 2001 From: djunzu Date: Tue, 1 Mar 2016 21:02:13 -0300 Subject: [PATCH] Add pps extension to IGNORED_EXTENSIONS modified: scrapy/linkextractors/__init__.py --- scrapy/linkextractors/__init__.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index 64efa0c55..efb11e43c 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -30,7 +30,8 @@ IGNORED_EXTENSIONS = [ 'm4a', # office suites - 'xls', 'xlsx', 'ppt', 'pptx', 'doc', 'docx', 'odt', 'ods', 'odg', 'odp', + 'xls', 'xlsx', 'ppt', 'pptx', 'pps', 'doc', 'docx', 'odt', 'ods', 'odg', + 'odp', # other 'css', 'pdf', 'exe', 'bin', 'rss', 'zip', 'rar',