5.8. grep, egrep, fgrep, rgrep - print lines matching a pattern

简介:

5.8.1. 删除空行

$ cat file | grep '.'
		

5.8.2. -v, --invert-match

grep -v "grep"

[root@development ~]# ps ax | grep httpd
 6284 ?        Ss     0:10 /usr/local/httpd-2.2.14/bin/httpd -k start
 8372 ?        S      0:00 perl ./wrapper.pl -chdir -name httpd -class com.caucho.server.resin.Resin restart
19136 ?        S      0:00 /usr/local/httpd-2.2.14/bin/httpd -k start
19749 pts/1    R+     0:00 grep httpd
31530 ?        Sl     0:57 /usr/local/httpd-2.2.14/bin/httpd -k start
31560 ?        Sl     1:12 /usr/local/httpd-2.2.14/bin/httpd -k start
31623 ?        Sl     1:06 /usr/local/httpd-2.2.14/bin/httpd -k start
[root@development ~]# ps ax | grep httpd | grep -v grep
 6284 ?        Ss     0:10 /usr/local/httpd-2.2.14/bin/httpd -k start
 8372 ?        S      0:00 perl ./wrapper.pl -chdir -name httpd -class com.caucho.server.resin.Resin restart
19136 ?        S      0:00 /usr/local/httpd-2.2.14/bin/httpd -k start
31530 ?        Sl     0:57 /usr/local/httpd-2.2.14/bin/httpd -k start
31560 ?        Sl     1:12 /usr/local/httpd-2.2.14/bin/httpd -k start
31623 ?        Sl     1:06 /usr/local/httpd-2.2.14/bin/httpd -k start
		

5.8.3. Output control

5.8.3.1. -o, --only-matching show only the part of a line matching PATTERN

			
$ curl -s http://www.example.com | egrep -o '<a href="(.*)">.*</a>' | sed -e 's/.*href="\([^"]*\)".*/\1/'
			
			
$ mysqlshow | egrep -o "|\w(.*)\w|"
Databases
information_schema
test
			
			
$ cat file.html | grep -o \
    -E '\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w\d]+\)|([^[:punct:]\s]|/)))'

$ cat file.html | grep -o -E 'href="([^"#]+)"'

$ cat sss.html | grep -o -E 'thunder://([^<]+)'
			
			
5.8.3.1.1. IP 地址
# grep rhost /var/log/secure | grep -oE "\b([0-9]{1,3}\.){3}[0-9]{1,3}\b"
				

5.8.3.2. 递归操作

递归查询

$ sudo grep -r 'neo' /etc/*
			

递归替换

			
for file in $( grep -rl '8800.org' *  | grep -v .svn ); do
    echo item: $file
	[ -f $file ] && sed -e 's/8800\.org/sf\.net/g' -e 's/netkiller/neo/g' $file >$file.bak; cp $file.bak $file;
done
			
			

5.8.3.3. -c, --count print only a count of matching lines per FILE

$ cat /etc/resolv.conf
nameserver localhost
nameserver 208.67.222.222
nameserver 208.67.220.220
nameserver 202.96.128.166
nameserver 202.96.134.133
$ grep -c nameserver /etc/resolv.conf
5
			
# grep -c GET /www/logs/access.log
188460

# grep -c POST /www/logs/access.log
421
			

5.8.4. Context control

5.8.4.1. -A, --after-context=NUM print NUM lines of trailing context

返回匹配当前行至下面N行

# grep -A1 game /etc/passwd
games:x:12:100:games:/usr/games:/sbin/nologin
gopher:x:13:30:gopher:/var/gopher:/sbin/nologin

# grep -A2 game /etc/passwd
games:x:12:100:games:/usr/games:/sbin/nologin
gopher:x:13:30:gopher:/var/gopher:/sbin/nologin
ftp:x:14:50:FTP User:/var/ftp:/sbin/nologin
			

5.8.4.2. -B, --before-context=NUM print NUM lines of leading context

返回匹配当前行至上面N行

# grep -B1 game /etc/passwd
operator:x:11:0:operator:/root:/sbin/nologin
games:x:12:100:games:/usr/games:/sbin/nologin

# grep -B2 game /etc/passwd
uucp:x:10:14:uucp:/var/spool/uucp:/sbin/nologin
operator:x:11:0:operator:/root:/sbin/nologin
games:x:12:100:games:/usr/games:/sbin/nologin

			

5.8.4.3. -C, --context=NUM print NUM lines of output context

-NUM same as --context=NUM
neo@neo-OptiPlex-380:~$ grep -C 1 new /etc/passwd
mail:x:8:8:mail:/var/mail:/bin/sh
news:x:9:9:news:/var/spool/news:/bin/sh
uucp:x:10:10:uucp:/var/spool/uucp:/bin/sh

neo@neo-OptiPlex-380:~$ grep -C 5 new /etc/passwd
sync:x:4:65534:sync:/bin:/bin/sync
games:x:5:60:games:/usr/games:/bin/sh
man:x:6:12:man:/var/cache/man:/bin/sh
lp:x:7:7:lp:/var/spool/lpd:/bin/sh
mail:x:8:8:mail:/var/mail:/bin/sh
news:x:9:9:news:/var/spool/news:/bin/sh
uucp:x:10:10:uucp:/var/spool/uucp:/bin/sh
proxy:x:13:13:proxy:/bin:/bin/sh
www-data:x:33:33:www-data:/var/www:/bin/sh
backup:x:34:34:backup:/var/backups:/bin/sh
list:x:38:38:Mailing List Manager:/var/list:/bin/sh

# grep -3 game /etc/passwd
mail:x:8:12:mail:/var/spool/mail:/sbin/nologin
uucp:x:10:14:uucp:/var/spool/uucp:/sbin/nologin
operator:x:11:0:operator:/root:/sbin/nologin
games:x:12:100:games:/usr/games:/sbin/nologin
gopher:x:13:30:gopher:/var/gopher:/sbin/nologin
ftp:x:14:50:FTP User:/var/ftp:/sbin/nologin
nobody:x:99:99:Nobody:/:/sbin/nologin

			

5.8.4.4. --color

# grep --color root  /etc/passwd
root:x:0:0:root:/root:/bin/bash
operator:x:11:0:operator:/root:/sbin/nologin
			

可以通过alias别名启用--color选项

alias egrep='egrep --color=auto'
alias fgrep='fgrep --color=auto'
alias grep='grep --color=auto'
			

加入.bashrc中,每次用户登录将自动生效

			
# enable color support of ls and also add handy aliases
if [ -x /usr/bin/dircolors ]; then
    test -r ~/.dircolors && eval "$(dircolors -b ~/.dircolors)" || eval "$(dircolors -b)"
    alias ls='ls --color=auto'
    #alias dir='dir --color=auto'
    #alias vdir='vdir --color=auto'

    alias grep='grep --color=auto'
    alias fgrep='fgrep --color=auto'
    alias egrep='egrep --color=auto'
fi
			
			

5.8.5. Regexp selection and interpretation

n 开头

$ grep '^n' /etc/passwd
news:x:9:9:news:/var/spool/news:/bin/sh
nobody:x:65534:65534:nobody:/nonexistent:/bin/sh
neo:x:1000:1000:neo chan,,,:/home/neo:/bin/bash
nagios:x:116:127::/var/run/nagios2:/bin/false
		

bash 结尾

$ grep 'bash$' /etc/passwd
root:x:0:0:root:/root:/bin/bash
neo:x:1000:1000:neo chan,,,:/home/neo:/bin/bash
postgres:x:114:124:PostgreSQL administrator,,,:/var/lib/postgresql:/bin/bash
cvsroot:x:1001:1001:cvsroot,,,,:/home/cvsroot:/bin/bash
svnroot:x:1002:1002:subversion,,,,:/home/svnroot:/bin/bash
		

中间包含 root

$ grep '.*root' /etc/passwd
root:x:0:0:root:/root:/bin/bash
cvsroot:x:1001:1001:cvsroot,,,,:/home/cvsroot:/bin/bash
svnroot:x:1002:1002:subversion,,,,:/home/svnroot:/bin/bash
		

5.8.5.1. .*

			
$ curl -s http://www.example.com | egrep -o '<a href=(.*)>.*</a>'
			
			

5.8.5.2. 2010:(13|14|15|16)

regular 匹配一组

egrep "2010:(13|14|15|16)"  access.2010-11-18.log > apache.log
			
ps ax |grep -E "mysqld|httpd|resin"
			

5.8.5.3. []与{}

源文件

# cat /etc/fstab

#
# /etc/fstab
# Created by anaconda on Sat Sep 10 00:25:46 2011
#
# Accessible filesystems, by reference, are maintained under '/dev/disk'
# See man pages fstab(5), findfs(8), mount(8) and/or blkid(8) for more info
#
UUID=091f295e-ea6d-4f57-9314-e2333f7ebff7 /                       ext4    defaults        1 1
UUID=b3661a0b-2c50-4e18-8030-be2d043cbfc4 /www                    ext4    defaults        1 2
UUID=4d3468de-a2ac-451c-b693-3bdca8832096 swap                    swap    defaults        0 0
tmpfs                   /dev/shm                tmpfs   defaults        0 0
devpts                  /dev/pts                devpts  gid=5,mode=620  0 0
sysfs                   /sys                    sysfs   defaults        0 0
proc                    /proc                   proc    defaults        0 0

			

匹配每行包含4个连续字符的字符串的行。

# grep '[A-Z]\{4\}' /etc/fstab
UUID=091f295e-ea6d-4f57-9314-e2333f7ebff7 /                       ext4    defaults        1 1
UUID=b3661a0b-2c50-4e18-8030-be2d043cbfc4 /www                    ext4    defaults        1 2
UUID=4d3468de-a2ac-451c-b693-3bdca8832096 swap                    swap    defaults        0 0
			

5.8.5.4. -P, --perl-regexp Perl正则表达式

Interpret PATTERN as a Perl regular expression. This is highly experimental and grep -P may warn of unimplemented features.

[neo@netkiller nginx]$ grep -Po '\w+\.js' www.netkiller.cn.access.log
index.js
min.js
min.js
mCustomScrollbar.js
min.js
ajax_gd.js
ajax.js
validation.js
AC_RunActiveContent.js
WdatePicker.js
cookie.js
msg_modal.js
all.js
common.js
commonjs.js
swfobject.js
dateutil.js
form.js
live800.js
lang.js
cycle2.js
min.js
carousel.js
tabify.js
image.js
min.js
ctrl.js
packed.js
min.js
common.js
			

5.8.6. fgrep

^M 处理

fgrep -rl `echo -ne '\r'` .

find . -type f -exec grep $'\r' {} +
		

5.8.7. egrep

egrep = grep -E 在egrep中不许看使用转意字符,例如

# grep '\(oo\).*\1' /etc/passwd
root:x:0:0:root:/root:/bin/bash

# grep -E '(oo).*\1' /etc/passwd
root:x:0:0:root:/root:/bin/bash

# egrep '(oo).*\1' /etc/passwd
root:x:0:0:root:/root:/bin/bash
			
$ snmpwalk -v2c -c public 172.16.1.254 | egrep -i 'if(in|out)'

for pid in $(ps -axf |grep 'php-cgi' | egrep egrep "0:00.(6|7|8|9)"'{print $1}'); do kill -9 $pid; done

for pid in $(ps -axf |grep 'php-cgi' | egrep "0:(0|1|2|3|4|5)0.(6|7|8|9)" |awk '{print $1}'); do kill -9 $pid; done
		





原文出处:Netkiller 系列 手札
本文作者:陈景峯
转载请与作者联系,同时请务必标明文章原始出处和作者信息及本声明。

目录
相关文章
|
Shell Linux
Linux中常用的文本处理命令(echo、sort、uniq、tr、cut、split、eval)(上)
1、echo命令——输出 echo 命令主要用来显示字符串信息。
370 0
|
17天前
|
Linux 数据库
find、locate和grep命令对比
在Linux系统中,`find`、`locate`和`grep`命令各有特点。`find`通过递归遍历文件系统,适合复杂条件搜索;`locate`通过预建数据库快速查找文件,但依赖数据库更新;`grep`用于文件内文本搜索,可结合`find`提高效率。选择合适的命令需根据具体需求和场景。
rep-wc-管道符 grep [-n ] 关键字 文件路径,grep -n “code“ test.txt,grep -n “code“ test.txt 显示行号的写法,wc test.txt全
rep-wc-管道符 grep [-n ] 关键字 文件路径,grep -n “code“ test.txt,grep -n “code“ test.txt 显示行号的写法,wc test.txt全
|
6月前
|
Perl
在 `awk` 命令中,`BEGIN { commands }`
在 `awk` 命令中,`BEGIN { commands }`
37 2
|
Linux iOS开发 MacOS
报错 sed: 1: extra characters at the end of d command
报错 sed: 1: extra characters at the end of d command
539 0
|
PHP 索引
preg_grep用法
preg_grep用法
164 0
preg_grep用法