Nginx访问日志分析脚本

#!/bin/bash # ========================================== # Nginx访问日志分析脚本 # 用途：分析Nginx访问日志，输出统计报告 # 使用方法：bash nginx_log_analyzer.sh [日志文件路径] # ========================================== LOG_FILE="${1:-/var/log/nginx/access.log}" echo "========== Nginx日志分析报告 ==========" echo "分析时间: $(date '+%Y-%m-%d %H:%M:%S')" echo "日志文件: $LOG_FILE" echo "" if [ ! -f "$LOG_FILE" ]; then echo "❌ 错误: 日志文件不存在: $LOG_FILE" exit 1 fi TOTAL_LINES=$(wc -l < "$LOG_FILE") echo "日志总行数: $TOTAL_LINES" echo "" # 1. PV/UV统计 echo "【1. PV/UV统计】" PV=$TOTAL_LINES UV=$(awk '{print $1}' "$LOG_FILE" | sort -u | wc -l) echo " 总访问量(PV): $PV" echo " 独立访客(UV): $UV" echo " 人均访问页数: $(echo "scale=1; $PV / $UV" | bc 2>/dev/null || echo 'N/A')" echo "" # 2. 状态码分布 echo "【2. HTTP状态码分布】" awk '{print $9}' "$LOG_FILE" | sort | uniq -c | sort -rn | while read count code; do case "$code" in 2*) echo " ✅ $code: $count 次" ;; 3*) echo " 🔄 $code: $count 次" ;; 4*) echo " ⚠️ $code: $count 次" ;; 5*) echo " ❌ $code: $count 次" ;; *) echo " ❓ $code: $count 次" ;; esac done echo "" # 3. Top 10访问IP echo "【3. Top 10访问IP】" awk '{print $1}' "$LOG_FILE" | sort | uniq -c | sort -rn | head -10 | awk '{printf " %2d. %-15s %d次 ", NR, $2, $1}' echo "" # 4. Top 10热门页面 echo "【4. Top 10热门页面】" awk '{print $7}' "$LOG_FILE" | sort | uniq -c | sort -rn | head -10 | awk '{printf " %2d. %-50s %d次 ", NR, $2, $1}' echo "" # 5. 请求方法分布 echo "【5. 请求方法分布】" awk '{print $6}' "$LOG_FILE" | tr -d '"' | sort | uniq -c | sort -rn | while read count method; do echo " $method: $count 次" done echo "" # 6. User-Agent统计 echo "【6. 浏览器/设备统计】" awk -F'"' '{print $6}' "$LOG_FILE" | sort | uniq -c | sort -rn | head -5 | awk '{printf " %2d. %d次 - %s ", NR, $1, substr($0, index($0,$2))}' echo "" # 7. 响应时间分析（如果日志包含$request_time） echo "【7. 响应时间分析】" if grep -qE '[0-9]+\.[0-9]+$' "$LOG_FILE" 2>/dev/null; then TIMES=$(awk '{print $NF}' "$LOG_FILE" | grep -E '^[0-9]+\.[0-9]+$' | sort -n) if [ -n "$TIMES" ]; then COUNT=$(echo "$TIMES" | wc -l) AVG=$(echo "$TIMES" | awk '{sum+=$1} END {printf "%.3f", sum/NR}') MAX=$(echo "$TIMES" | tail -1) P95=$(echo "$TIMES" | awk -v c="$COUNT" 'BEGIN{target=int(c*0.95)} NR==target{print; exit}') echo " 总请求数: $COUNT" echo " 平均响应时间: ${AVG}s" echo " P95响应时间: ${P95}s" echo " 最大响应时间: ${MAX}s" # 慢请求统计 SLOW=$(echo "$TIMES" | awk '$1 > 1' | wc -l) echo " 慢请求(>1s): $SLOW 次 ($(echo "scale=1; $SLOW * 100 / $COUNT" | bc)%)" else echo " 未检测到响应时间数据" fi else echo " 日志格式不包含响应时间字段" echo " 提示: 在nginx.conf中添加 log_format 包含 \$request_time" fi echo "" # 8. 404页面统计 echo "【8. 404错误页面Top 10】" awk '$9 == 404 {print $7}' "$LOG_FILE" | sort | uniq -c | sort -rn | head -10 | awk '{printf " %2d. %-50s %d次 ", NR, $2, $1}' echo "" # 9. 按小时统计访问量 echo "【9. 按小时访问量分布】" awk '{print $4}' "$LOG_FILE" | cut -d: -f2 | sort | uniq -c | sort -k2 -n | while read count hour; do BAR=$(printf '=%.0s' $(seq 1 $((count/100)) 2>/dev/null)) echo " ${hour}:00 | ${BAR} ${count}" done echo "" echo "========== 分析完成 =========="

[{"name": "LOG_FILE", "label": "Nginx\u65e5\u5fd7\u6587\u4ef6\u8def\u5f84", "default": "/var/log/nginx/access.log"}]