![[shell基础]——awk命令](https://image.shishitao.com:8440/aHR0cHM6Ly9ia3FzaW1nLmlrYWZhbi5jb20vdXBsb2FkL2NoYXRncHQtcy5wbmc%2FIQ%3D%3D.png?!?w=700&webp=1 "[shell基础]——awk命令")
关于awk
awk是一个强大的文本分析工具，相对于grep的查找、sed的编辑，awk在其对数据分析并生成报告时，显得尤为强大。
简单来说awk就是把文件逐行的读入，以空格为默认分隔符将每行切片，切开的部分再进行各种分析处理。
awk有3个不同版本: awk、nawk和gawk，未作特别说明，一般指gawk，gawk 是 AWK 的 GNU 版本。
本文用的测试文本
# cat -n passwd
1 root:x:0:0:root:/root:/bin/bash
2 bin:x:1:1:bin:/bin:/sbin/nologin
3 daemon:x:2:2:daemon:/sbin:/sbin/nologin
4 adm:x:3:4:adm:/var/adm:/sbin/nologin
5 lp:x:4:7:lp:/var/spool/lpd:/sbin/nologin
6 sync:x:5:0:sync:/sbin:/bin/sync
7 shutdown:x:6:0:shutdown:/sbin:/sbin/shutdown
8 halt:x:7:0:halt:/sbin:/sbin/halt
9 mail:x:8:12:mail:/var/spool/mail:/sbin/nologin
10 uucp:x:10:14:uucp:/var/spool/uucp:/sbin/nologin
11 operator:x:11:100:operator:/root:/sbin/nologin
# cat -n netstat.txt
1 Proto Recv-Q Send-Q Local-Address Foreign-Address State
2 tcp 0 0 0.0.0.0:3306 0.0.0.0:* LISTEN
3 tcp 0 0 0.0.0.0:80 0.0.0.0:* LISTEN
4 tcp 0 0 127.0.0.1:9000 0.0.0.0:* LISTEN
5 tcp 0 0 coolshell.cn:80 124.205.5.146:18245 TIME_WAIT
6 tcp 0 0 coolshell.cn:80 61.140.101.185:37538 FIN_WAIT2
7 tcp 0 0 coolshell.cn:80 110.194.134.189:1032 ESTABLISHED
8 tcp 0 0 coolshell.cn:80 123.169.124.111:49809 ESTABLISHED
9 tcp 0 0 coolshell.cn:80 116.234.127.77:11502 FIN_WAIT2
10 tcp 0 0 coolshell.cn:80 123.169.124.111:49829 ESTABLISHED
11 tcp 0 0 coolshell.cn:80 183.60.215.36:36970 TIME_WAIT
12 tcp 0 4166 coolshell.cn:80 61.148.242.38:30901 ESTABLISHED
13 tcp 0 1 coolshell.cn:80 124.152.181.209:26825 FIN_WAIT1
14 tcp 0 0 coolshell.cn:80 110.194.134.189:4796 ESTABLISHED
15 tcp 0 0 coolshell.cn:80 183.60.212.163:51082 TIME_WAIT
16 tcp 0 1 coolshell.cn:80 208.115.113.92:50601 LAST_ACK
17 tcp 0 0 coolshell.cn:80 123.169.124.111:49840 ESTABLISHED
18 tcp 0 0 coolshell.cn:80 117.136.20.85:50025 FIN_WAIT2
19 tcp 0 0 :::22 :::* LISTEN
域和记录的理解
(1) awk执行时浏览域标记为$1,$2...$n，这种方法称为域的标识
(2) $1代表分割第一个域、$2 代表分割第二个域、依次类推....
(3) 域标识符$后面可以跟变量、或者变量表达式
(4) 一些特殊的域和记录：
| $0 | 当前记录（这个变量中存放着整个文本的内容） |
| $1~$n | 当前记录的第n个字段，字段间由FS分隔 |
| FS | 输入字段分隔符 默认是空格或Tab |
| NF | 当前记录中的“域”个数，就是有多少列 |
| $NF | 表示最后一个“域”的内容 |
| NR | 感觉上就是匹配上的行的行号，且是文本当中本身的行号。NR==1可以输出表头 |
| FNR | 当前记录数，与NR不同的是，这个值会是各个文件自己的行号 |
| RS | 输入的记录分隔符， 默认为换行符 |
| OFS | 输出字段分隔符， 默认也是空格 |
| ORS | 输出的记录分隔符，默认为换行符 |
| FILENAME | 当前输入文件的名字 |
(5) awk的默认分隔域是空格
(6) 用 -F 选项指定分隔域
(7) BEGIN { } END 的理解
BEGIN{ 这里面放的是执行前的语句 }
END {这里面放的是处理完所有的行后要执行的语句 }
{这里面放的是处理每一行时要执行的语句}
基本匹配($N=="string")、输出表头、格式化输出
# awk '$3==0 && $6=="LISTEN"' netstat.txt
tcp 0 0 0.0.0.0:3306 0.0.0.0:* LISTEN
tcp 0 0 0.0.0.0:80 0.0.0.0:* LISTEN
tcp 0 0 127.0.0.1:9000 0.0.0.0:* LISTEN
tcp 0 0 :::22 :::* LISTEN # awk '$3==0 && $6=="LISTEN" || NR==1' netstat.txt
Proto Recv-Q Send-Q Local-Address Foreign-Address State
tcp 0 0 0.0.0.0:3306 0.0.0.0:* LISTEN
tcp 0 0 0.0.0.0:80 0.0.0.0:* LISTEN
tcp 0 0 127.0.0.1:9000 0.0.0.0:* LISTEN
tcp 0 0 :::22 :::* LISTEN # awk '$3==0 && $6=="LISTEN" || NR==1 {printf "%-20s %-20s %s\n",$4,$5,$6}' netstat.txt
Local-Address Foreign-Address State
0.0.0.0: 0.0.0.0:* LISTEN
0.0.0.0: 0.0.0.0:* LISTEN
127.0.0.1: 0.0.0.0:* LISTEN
::: :::* LISTEN
字符匹配
- *$N~/ /
- *$N!~/ /
- !/ /
可以模糊匹配
可以使用正则表达式
# awk '$6~/FIN/ || NR==1 {print NR,$4,$5,$6}' netstat.txt
1 Local-Address Foreign-Address State
6 coolshell.cn:80 61.140.101.185:37538 FIN_WAIT2
9 coolshell.cn:80 116.234.127.77:11502 FIN_WAIT2
13 coolshell.cn:80 124.152.181.209:26825 FIN_WAIT1
18 coolshell.cn:80 117.136.20.85:50025 FIN_WAIT2
# awk '$6~/FIN/ || NR==1 {print $4,$5,$6}' OFS=";\t" netstat.txt
Local-Address; Foreign-Address; State
coolshell.cn:80; 61.140.101.185:37538; FIN_WAIT2
coolshell.cn:80; 116.234.127.77:11502; FIN_WAIT2
coolshell.cn:80; 124.152.181.209:26825; FIN_WAIT1
coolshell.cn:80; 117.136.20.85:50025; FIN_WAIT2
# awk '$6~/FIN|WAIT/ || NR==1 {print $4,$5,$6}' netstat.txt
Local-Address Foreign-Address State
coolshell.cn:80 124.205.5.146:18245 TIME_WAIT
coolshell.cn:80 61.140.101.185:37538 FIN_WAIT2
coolshell.cn:80 116.234.127.77:11502 FIN_WAIT2
coolshell.cn:80 183.60.215.36:36970 TIME_WAIT
coolshell.cn:80 124.152.181.209:26825 FIN_WAIT1
coolshell.cn:80 183.60.212.163:51082 TIME_WAIT
coolshell.cn:80 117.136.20.85:50025 FIN_WAIT2
# awk '$6!~/FIN|WAIT/ || NR==1 {print $4,$5,$6}' netstat.txt
Local-Address Foreign-Address State
0.0.0.0:3306 0.0.0.0:* LISTEN
0.0.0.0:80 0.0.0.0:* LISTEN
127.0.0.1:9000 0.0.0.0:* LISTEN
coolshell.cn:80 110.194.134.189:1032 ESTABLISHED
coolshell.cn:80 123.169.124.111:49809 ESTABLISHED
coolshell.cn:80 123.169.124.111:49829 ESTABLISHED
coolshell.cn:80 61.148.242.38:30901 ESTABLISHED
coolshell.cn:80 110.194.134.189:4796 ESTABLISHED
coolshell.cn:80 208.115.113.92:50601 LAST_ACK
coolshell.cn:80 123.169.124.111:49840 ESTABLISHED
:::22 :::* LISTEN
# awk '!/ESTABLISHED/ || NR==1 {print $4,$5,$6}' netstat.txt
Local-Address Foreign-Address State
0.0.0.0:3306 0.0.0.0:* LISTEN
0.0.0.0:80 0.0.0.0:* LISTEN
127.0.0.1:9000 0.0.0.0:* LISTEN
coolshell.cn:80 124.205.5.146:18245 TIME_WAIT
coolshell.cn:80 61.140.101.185:37538 FIN_WAIT2
coolshell.cn:80 116.234.127.77:11502 FIN_WAIT2
coolshell.cn:80 183.60.215.36:36970 TIME_WAIT
coolshell.cn:80 124.152.181.209:26825 FIN_WAIT1
coolshell.cn:80 183.60.212.163:51082 TIME_WAIT
coolshell.cn:80 208.115.113.92:50601 LAST_ACK
coolshell.cn:80 117.136.20.85:50025 FIN_WAIT2
:::22 :::* LISTEN
# cat passwd |awk -F: '{if($1~/root/) print $0}' --->#匹配$1域中包含root的并打印匹配行的完整信息
root:x:::root:/root:/bin/bash
# cat passwd |awk '$0~/root/' --->#匹配整个文本中包含root的
root:x:::root:/root:/bin/bash
operator:x:::operator:/root:/sbin/nologin
# cat passwd |awk -F: '$1~/^root/' --->#匹配$1域中以root开头的
root:x:::root:/root:/bin/bash
# cat /etc/passwd |awk -F: '$7~/bash$/' --->#匹配$7域中以bash结尾的
root:x:::root:/root:/bin/bash
huanhuan:x::::/home/huanhuan:/bin/bash
hsy:x::::/home/hsy:/bin/bash
user01:x::::/home/user01:/bin/bash
hh:x::::/home/hh:/bin/bash
打印报告头/信息尾
BEGIN{print "......"} END{print "......"}
# cat passwd |awk -F: 'BEGIN{print "======用户列表====="} {print "用户名:"$1} END{print "======ending======"}'
======用户列表=====
用户名:root
用户名:bin
用户名:daemon
用户名:adm
用户名:lp
用户名:sync
用户名:shutdown
用户名:halt
用户名:mail
用户名:uucp
用户名:operator
======ending======
条件匹配
'{ if(......) print $n }' （注：if语句中可以使用 && || 实现多条件匹配）
# cat passwd |awk -F: '{if($3<10) print $0}'
root:x:0:0:root:/root:/bin/bash
bin:x:1:1:bin:/bin:/sbin/nologin
daemon:x:2:2:daemon:/sbin:/sbin/nologin
adm:x:3:4:adm:/var/adm:/sbin/nologin
lp:x:4:7:lp:/var/spool/lpd:/sbin/nologin
sync:x:5:0:sync:/sbin:/bin/sync
shutdown:x:6:0:shutdown:/sbin:/sbin/shutdown
halt:x:7:0:halt:/sbin:/sbin/halt
mail:x:8:12:mail:/var/spool/mail:/sbin/nologin
# cat passwd |awk -F: '{if($3>=10) print $0}'
uucp:x:10:14:uucp:/var/spool/uucp:/sbin/nologin
operator:x:11:100:operator:/root:/sbin/nologin
# cat passwd |awk -F: '{if($1=="root" && $5=="root") print $0}'
root:x:::root:/root:/bin/bash
# cat passwd |awk -F: '{if($1=="root" || $1=="mail") print $0}'
root:x:::root:/root:/bin/bash
mail:x:::mail:/var/spool/mail:/sbin/nologin
# cat passwd |awk -F: '{if($4>=10 && $4<=30) print $0}'
mail:x:::mail:/var/spool/mail:/sbin/nologin
uucp:x:::uucp:/var/spool/uucp:/sbin/nologin
折分文件
# ls
netstat.txt # awk 'NR!=1 {print > $6}' netstat.txt # ls
ESTABLISHED FIN_WAIT2 LISTEN TIME_WAIT
FIN_WAIT1 LAST_ACK netstat.txt # cat TIME_WAIT
tcp coolshell.cn: 124.205.5.146: TIME_WAIT
tcp coolshell.cn: 183.60.215.36: TIME_WAIT
tcp coolshell.cn: 183.60.212.163: TIME_WAIT
# awk 'NR!=1 {print $4,$5 > $6}' netstat.txt
# ls
ESTABLISHED FIN_WAIT2 LISTEN TIME_WAIT
FIN_WAIT1 LAST_ACK netstat.txt
# cat TIME_WAIT
coolshell.cn: 124.205.5.146:
coolshell.cn: 183.60.215.36:
coolshell.cn: 183.60.212.163:
# awk 'NR!=1 {if($6~/TIME|ESTABLISHED/) print $5 > "est.ip" ; else if($6~/LISTEN/) print $5 > "listen.ip" }' netstat.txt
# cat listen.ip
0.0.0.0:*
0.0.0.0:*
0.0.0.0:*
:::*
# cat est.ip
124.205.5.146:18245
110.194.134.189:1032
123.169.124.111:49809
123.169.124.111:49829
183.60.215.36:36970
61.148.242.38:30901
110.194.134.189:4796
183.60.212.163:51082
123.169.124.111:49840
统计
# awk 'NR!=1{a[$NF]++} END {for(i in a) print i "," a[i];}' netstat.txt
TIME_WAIT,
FIN_WAIT1,
ESTABLISHED,
FIN_WAIT2,
LAST_ACK,
LISTEN,
# awk ' /^tcp/ {a[$NF]++} END{ for(i in a) print i,a[i] } ' netstat.txt
TIME_WAIT
FIN_WAIT1
ESTABLISHED
FIN_WAIT2
LAST_ACK
LISTEN
# ps aux|awk ' NR!=1 {a[$1]+=$6} END{ for(i in a) print i,a[i]"KB" } ' ——> 统计每个用户的进程占用了多少内存
gdm 40388KB
rpc 912KB
dbus 1620KB
6140KB
nobody 604KB
postfix 6948KB
rpcuser 1340KB
root 86040KB
awk使用if/for/while语句
#编写一个脚本，统计/etc/passwd 有多少系统用户，每个系统用户是否拥有登录系统的权限？
#!/bin/bash
awk -F: '{ if($3>=1&&$3<=499)
{
print"系统用户:"$1;
if($NF~/nologin/)
{print"登录权限为:NO";}
else
{print"登录权限为:YES";}
}
}' /etc/passwd |paste -d "," - -
运行awk的另一种方法，以及BEGIN、END的运用
# vim cal.awk
#!/bin/awk -f BEGIN{
math=
english=
computer= printf "NAME NO. MATH ENGLISH COMPUTER TOTAL\n"
printf "---------------------------------------------\n"
} {
math+=$
english+=$
computer+=$
printf "%-6s %-6s %4d %8d %8d %8d\n", $, $, $,$,$, $+$+$
} END{
printf "---------------------------------------------\n"
printf " TOTAL:%10d %8d %8d \n", math, english, computer
printf "AVERAGE:%10.2f %8.2f %8.2f\n", math/NR, english/NR, computer/NR
}
# cat score.txt
Marry
Jack
Tom
Mike
Bob
# awk -f cal.awk score.txt
NAME NO. MATH ENGLISH COMPUTER TOTAL
---------------------------------------------
Marry
Jack
Tom
Mike
Bob
---------------------------------------------
TOTAL:
AVERAGE: 63.80 78.60 70.00
awk内置的字符串函数
(1) gsub替换
gsub(/r/,s)：把r替换成s
# cat passwd |awk 'gsub(/root/,"Jellylyj") {print $1}'
Jellylyj:x:0:0:Jellylyj:/Jellylyj:/bin/bash
operator:x:11:100:operator:/Jellylyj:/sbin/nologin gsub(/r/,s,t)：在t中把r替换成s
# cat passwd |awk -F: 'gsub(/root/,"Jelly",$1) {print$0}'
(2) length(s)返回s的长度
# cat passwd |awk -F: '{print$1}'|awk '{if(length($1)==4) print $1}'
root
sync
halt
mail
uucp
awk练习题：点此打开