Forked from whaleinvasion/analyze_nginx_access_logs.sh
Last active
September 7, 2021 09:51
-
-
Save marcbrunet/703310bea5e1ffdba57cac3608c4d106 to your computer and use it in GitHub Desktop.
Bash Script to Parse Nginx Access Logs: https://sysadmins.co.za/bash-script-to-parse-and-analyze-nginx-access-logs/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# variables | |
LOGFILE="/var/log/nginx/access.log" | |
LOGFILE_GZ="/var/log/nginx/access.log.*" | |
RESPONSE_CODE="200" | |
# functions | |
filters(){ | |
grep -w $RESPONSE_CODE \ | |
| grep -v "\/rss\/" \ | |
| grep -v robots.txt \ | |
| grep -v "\.css" \ | |
| grep -v "\.jss*" \ | |
| grep -v "\.png" \ | |
| grep -v "\.ico" | |
} | |
filters_404(){ | |
grep -w "404" | |
} | |
request_ips(){ | |
awk '{print $1}' | |
} | |
request_method(){ | |
awk '{print $6}' \ | |
| cut -d'"' -f2 | |
} | |
request_pages(){ | |
awk '{print $7}' | |
} | |
wordcount(){ | |
sort \ | |
| uniq -c | |
} | |
sort_desc(){ | |
sort -rn | |
} | |
return_kv(){ | |
awk '{print $1, $2}' | |
} | |
request_pages(){ | |
awk '{print $7}' | |
} | |
return_top_ten(){ | |
head -10 | |
} | |
## actions | |
get_request_ips(){ | |
echo "" | |
echo "Top 10 Request IP's:" | |
echo "====================" | |
cat $LOGFILE \ | |
| filters \ | |
| request_ips \ | |
| wordcount \ | |
| sort_desc \ | |
| return_kv \ | |
| return_top_ten | |
echo "" | |
} | |
get_request_methods(){ | |
echo "Top Request Methods:" | |
echo "====================" | |
cat $LOGFILE \ | |
| filters \ | |
| request_method \ | |
| wordcount \ | |
| return_kv | |
echo "" | |
} | |
get_request_pages_404(){ | |
echo "Top 10: 404 Page Responses:" | |
echo "===========================" | |
zgrep '-' $LOGFILE $LOGFILE_GZ\ | |
| filters_404 \ | |
| request_pages \ | |
| wordcount \ | |
| sort_desc \ | |
| return_kv \ | |
| return_top_ten | |
echo "" | |
} | |
get_request_pages(){ | |
echo "Top 10 Request Pages:" | |
echo "=====================" | |
cat $LOGFILE \ | |
| filters \ | |
| request_pages \ | |
| wordcount \ | |
| sort_desc \ | |
| return_kv \ | |
| return_top_ten | |
echo "" | |
} | |
get_request_pages_all(){ | |
echo "Top 10 Request Pages from All Logs:" | |
echo "===================================" | |
zgrep '-' --no-filename $LOGFILE $LOGFILE_GZ \ | |
| filters \ | |
| request_pages \ | |
| wordcount \ | |
| sort_desc \ | |
| return_kv \ | |
| return_top_ten | |
echo "" | |
} | |
# executing | |
get_request_ips | |
get_request_methods | |
get_request_pages | |
get_request_pages_all | |
get_request_pages_404 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
the function
request_pages()
is specified twice in this script. Please check lines 32-34 and 49-51.Regards,
Tronde