Filter and Analyze Web Server Access Logs

#!/bin/bash

# Configuration variables
LOG_FILE="/var/log/nginx/access.log" # Path to your web server access log
SEARCH_TERM="404"                   # Example: Filter for '404' errors

# Check if the log file exists
if [ ! -f "$LOG_FILE" ]; then
    echo "Error: Log file '$LOG_FILE' not found or is not readable." >&2
    exit 1
fi

echo "--- Filtering '$LOG_FILE' for lines containing '$SEARCH_TERM' (first 10 matches) ---"
grep "$SEARCH_TERM" "$LOG_FILE" | head -n 10

echo "
--- Top 5 IP addresses accessing the server ---"
# Extracts the first field (IP), sorts, counts unique occurrences, sorts numerically (descending), and takes top 5
awk '{print $1}' "$LOG_FILE" | sort | uniq -c | sort -nr | head -n 5

echo "
--- Top 5 Most Accessed URLs (excluding common static assets) ---"
# Extracts the 7th field (request path) and filters out common static asset extensions
awk '($7 !~ /\.(jpg|jpeg|png|gif|bmp|svg|css|js|ico|woff|woff2|ttf|otf|eot)/) {print $7}' "$LOG_FILE" \
| sort | uniq -c | sort -nr | head -n 5

echo "
--- Total requests by HTTP status code ---"
# Extracts the 9th field (status code) and counts occurrences
awk '{print $9}' "$LOG_FILE" | sort | uniq -c | sort -nr