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', ]