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

Added more common MS Office file extensions

This commit is contained in:
Mikael Schirén 2023-09-29 09:44:04 +02:00 committed by GitHub
parent 83fff6c951
commit da6e75d00a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
scrapy/linkextractors/__init__.py
View File

@ -67,12 +67,21 @@ IGNORED_EXTENSIONS = [
"webm", "webm",
# office suites # office suites
"xls", "xls",
"xlsm",
"xlsx", "xlsx",
"xltm",
"xltx",
"potm",
"potx",
"ppt", "ppt",
"pptm",
"pptx", "pptx",
"pps", "pps",
"doc", "doc",
"docb",
"docm",
"docx", "docx",
"dotm",
"dotx", "dotx",
"odt", "odt",
"ods", "ods",