#!/bin/bash

curl http://tieba.baidu.com/linux -o tmp.html
echo 'Get html done .'
cat tmp.html | grep 'class=t' | awk -F 'kz=' '{print $2}' | awk -F '\"' '{print $1}' > kz.txt
cat tmp.html | grep 'class=t' | awk -F '_blank >' '{print $2}' | awk -F '<' '{print $1}' > title.txt

#!/bin/bash

#Get the page source and put it into file tmp.html
curl [url]http://tieba.baidu.com/linux[/url] -o tmp.html

#Get the kz from file tmp.html and put it into file kz.txt
cat tmp.html | grep 'class=t' | awk -F 'kz=' '{print $2}' | awk -F '\"' '{print $1}' > kz.txt
#Get the title from file tmp.html and put it into file title.txt
cat tmp.html | grep 'class=t' | awk -F '_blank >' '{print $2}' | awk -F '<' '{print $1}' > title.txt

#Read the kz from  file kz.txt and put it into the array kz
#Read the title from  file title.txt and put it into the array title
#One page has 50 titles
kz=()
title=()
for index in {1..50}; do
        kz[$index]=`cat kz.txt | head -n $index | tail -n 1`
        title[$index]=`cat title.txt | head -n $index | tail -n 1`
done

1798        443.643518        192.168.1.6        220.181.38.80        HTTP        GET /f?ct=369098752&word=linux&cm=12&tn=baiduManagerSubmit&lm=3171&z=428601111&sc=0&rs5=472290167&rs6=3707595763&bu=/f%3Fkw%3Dlinux HTTP/1.1

原帖由 walkerxk 于 2008-7-6 00:59 发表
有时候很多参数是没用的，你试试直接在浏览器里面输入这个url看看。

#!/bin/bash

#Get the page source and put it into file tmp.html
curl http://tieba.baidu.com/linux -o tmp.html

#Get the kz from file tmp.html and put it into file kz.txt
cat tmp.html | grep 'class=t' | awk -F 'kz=' '{print $2}' | awk -F '\"' '{print $1}' > kz.txt
#Get the title from file tmp.html and put it into file title.txt
cat tmp.html | grep 'class=t' | awk -F '_blank >' '{print $2}' | awk -F '<' '{print $1}' > title.txt

#Read the kz from  file kz.txt and put it into the array kz
#Read the title from  file title.txt and put it into the array title
#One page has 50 titles
kz_list=()
title_list=()
for index in {1..50}; do
        kz_list[$index]=`cat kz.txt | head -n $index | tail -n 1`
        title_list[$index]=`cat title.txt | head -n $index | tail -n 1`
done

row=`wc -l black_title.txt | awk '{print $1}'`
if [ $row -eq 0 ]; then
        echo 'Nothing in the black_title .'
fi

for black_title in `cat black_title.txt`; do
        for title in ${title_list[*]}; do
                echo $title | grep $black_title >> /dev/null
                if [ $? -eq 0 ]; then
                        echo "Black_title $title found ."
                fi
        done
done

aaaa
bbbb
linux