more aggressive url filtering

This commit is contained in:
vulpine 2020-06-25 13:42:07 +00:00
parent a6c8f78ec7
commit 56e3aab304
1 changed files with 1 additions and 1 deletions

2
crawly
View File

@ -42,7 +42,7 @@ visit $SITE urls.txt
fi
URLLIST=`cat urls.txt|sort|uniq`
URLLIST=`cat urls.txt|grep -v '<'|grep -v ' '|sort|uniq`
rm urls.txt