Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Added more common MS Office file extensions

Mikael Schirénda6e75d00a8a
diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py
index 492c455fd..6b8be909e 100644
--- a/scrapy/linkextractors/__init__.py
+++ b/scrapy/linkextractors/__init__.py
@@ -67,12 +67,21 @@ IGNORED_EXTENSIONS = [
"webm",
# office suites
"xls",
+ "xlsm",
"xlsx",
+ "xltm",
+ "xltx",
+ "potm",
+ "potx",
"ppt",
+ "pptm",
"pptx",
"pps",
"doc",
+ "docb",
+ "docm",
"docx",
+ "dotm",
"dotx",
"odt",
"ods",