Scrapy, a fast high-level web crawling & scraping framework for Python.
Add dotx to exclude for documents
Mikael Schirén83fff6c9511f
diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.pyindex 906188184..492c455fd 100644--- a/scrapy/linkextractors/__init__.py+++ b/scrapy/linkextractors/__init__.py@@ -73,6 +73,7 @@ IGNORED_EXTENSIONS = ["pps","doc","docx",+ "dotx","odt","ods","odg",