删除重复文件的脚本代码

#!/bin/bash

#文件名：remove duplicates.sh

#用途： 查找并删除重复文件，每一个文件只保留一个样本

ls -lS | awk 'BEGIN { getline; getline; name1=$8; size=$5}

{ name2=$8;

if (size == $5)

{

"md5sum " name1 | getline; csum1=$1;

"md5sum " name2 | getline; csum2=$1;

if (csum1 == csum2)

{ print name1; print name2}

}

size=$5; name1=name2;

}' | sort -u >duplicate_files

cat duplicate_files | xars -I { } md5sum { } | sort | uniq -w 32 | awk ' { print "^"$2"$" } ' | sort -u > duplicate_sample

echo Removing..

comm dupliacte_files duplicate_sample -2 -3 | tee /dev/stderr | xargs rm

echo Removed duplicate files successfully.

#上面的黑体I不是L，而是大写的i