RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6074 from mikkeschiren/master 

Add more common MS Office file extensions to exclude for documents
This commit is contained in:
Andrey Rakhmatullin 2023-09-29 16:28:19 +04:00 committed by GitHub
parent 4abc54f0ec da6e75d00a
commit 0e64dec5dd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
scrapy/linkextractors/__init__.py
View File

@ -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",