diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index 906188184..6b8be909e 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -67,12 +67,22 @@ IGNORED_EXTENSIONS = [ "webm", # office suites "xls", + "xlsm", "xlsx", + "xltm", + "xltx", + "potm", + "potx", "ppt", + "pptm", "pptx", "pps", "doc", + "docb", + "docm", "docx", + "dotm", + "dotx", "odt", "ods", "odg",