shell版url链接爬虫--测试版

#!/bin/bash
# egrep -o "https?://[a-zA-Z0-9\.+\/*]*"
i=3
while (($i >= 0 ))
do
read  -p  "输入一个url和探测深度: " url deep
num=`echo $url | egrep -o "https?://[a-zA-Z0-9\.+\/*]*"`
 re=`echo $?`

#判断区
if (($re==1))
then

echo -e "请输入正确url\n"
else
break   #跳出

fi

echo "还有$i次机会"
c=$((i-=1))

done
#第一层：
reurl=`curl $url |  egrep -o "https?://[a-zA-Z0-9\.+\/*]*" > /root/rebug.txt `

top=1   #设置起始点
#嵌套层
deep=${deep:-1}
#循环层
while (($deep > 0 ))
do
con=`cat /root/rebug.txt`
len=`cat /root/rebug.txt |wc -l`
#top=0   #设置起始点
echo -e "第$deep层遍历\n"
	#for i in $reurl
	while (($len > $top ))
		do

			*************************#核心代码
			echo $i,深度$deep
		curl $i |  egrep -o "https?://[a-zA-Z0-9\.+\/*]*"  >> /root/rebug.txt

			echo "-------"
			top=$((top+=1))
	done
	
  deep=$((deep-=1))
done