php解析ip列表并入库-白红宇

php解析ip列表并入库

阅读量：6501 次

发布时间：2019-06-24

本文共 8122 字，大约阅读时间需要 27 分钟。

前一段时间因为要开发一个新项目，需要一个ip库，由于公司原本无这样一个库，所以急需从文件中匹配ip地址然后存库。下面是我下的一段程序，可能效率不是很高，代码也没有做过多的优化，有些地方比较繁琐，但这样以后脏数据相对来说少点，但或多或少还是存在一定的脏数据。但是这个文件有40多行，我采取的办法是按行数将这个相对来说很大的文件拆分是N多很小的文件分布式分析入库的。当然你也可以通过多进程处理。一个问题有很多解决办法，我分享一下我的想法。当然如果您有更好的办法请多多指正，笔者虚心求教，还有我下面贴出的代码您也可以去优化，然后提出您的优化建议，我们一起探讨，共同进步。

我当时采用的是浏览器运行php文件来执行的，在这里我建议应该在linux环境下采用php命令行执行，这样效率会更高，而且不存在超时的问题。

<?php

*Author:马荣财

*date:2011/8/2 14:25:28

*目的:正则匹配ip文件列表导入数据库

*@param $filename ip列表文件全路径包括目录

*分析了一下文件发现主要有一下几种格式

*A: **省如甘肃省

*B: **市**区如北京市海淀区或如浙江省宁波市北仑区

*C: ****大学如清华大学

*D: ****市如新疆，宁夏，西藏，内蒙古**市

*E: 剩下的为一类

//set_time_limit(0);

ini_set('max_execution_time', '3000');

$conn = mysql_connect('localhost','root','') or die('MYSQL 连接错误！');

mysql_query("set names utf8");

mysql_select_db('test',$conn);

$result = mysql_query('select `cid`,`pid`,`name` from `tbl_city`');

$citys = array();

while($row=mysql_fetch_array($result)) {

$citys[$row['name']] = $row;

}

function parseAndImport($filename,$citys) {

//将ip文件列表读入一个数组

$fileArr = file($filename);

//分别定义了国家、省份、城市、描述、省份id、城市id、ip段(1,2)

$country ='';

$province = '';

$city ='';

$ser = '';

$cid = '';

$pid = '';

$ip1 ='';

$ip2 = '';

//定义一个计数器

$i=0;

$sql = '';

foreach($fileArr as $key=>$lineText) {

if(preg_match("|(\d+\.\d+\.\d+\.\d+) +(\d+\.\d+\.\d+\.\d+) +(.*)|",$lineText,$lineArr)) {

//用空格切割匹配的与城市有关的信息

$dataArr= explode(' ',$lineArr[3]);

$ser = $lineArr[3];

$cityStr = $dataArr[0];

//把ip装换成整数形式

$ip1 = sprintf("%u", ip2long($lineArr[1]));

$ip1 = addslashes($ip1);

$ip2 = sprintf("%u", ip2long($lineArr[2]));

$ip2 = addslashes($ip2);

echo $ip2;exit;

//先查找A类型的数据

if(preg_match("|(.*)省$|",$cityStr,$cityArr)) {

$country = '中国';

$cityArrlen = count($cityArr);

if($cityArrlen>0) {

$province = $cityArr[1];

$city ='';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

} else {

$province ='';

$city = '';

}

delLine($filename,$lineText);

}

//查找B类型的数据

elseif(preg_match("|(.*?)市(.*)|",$cityStr,$cityArr) || preg_match("|(.*?)州(.*)|",$cityStr,$cityArr)) {

$country = '中国';

$cityArrlen = count($cityArr);

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'省');

if($len>0) {

$pcArr = explode('省',$cityArr[1]);

$province=$pcArr[0];

$city=$pcArr[1];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$province = $cityArr[1];

$areaLen = mb_strpos($cityArr[2],'区');

if($areaLen>0) {

$aArr = explode($cityArr[2],'区');

$city = $aArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$province = $cityArr[1];

$city ='';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

} else {

$province ='';

$city = '';

}

delLine($filename,$lineText);

}

//查找C类型的数据

elseif(preg_match("|(.*)大学(.*)|",$cityStr,$cityArr) || preg_match("|(.*)学院(.*)|",$cityStr,$cityArr)) {

//参阅附件，这块比较繁琐

}

//查找D类型的数据

elseif(preg_match("|^内蒙古(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '内蒙古';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

elseif(preg_match("|^西藏(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '西藏';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city='';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

elseif(preg_match("|^新疆(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '新疆';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city ='';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

elseif(preg_match("|^宁夏(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '宁夏';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

elseif(preg_match("|^香港(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '香港';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

elseif(preg_match("|^澳门(.*)|",$cityStr,$cityArr)) {

$cityArrlen = count($cityArr);

$country = '中国';

$province = '澳门';

if($cityArrlen>0) {

$len=mb_strpos($cityArr[1],'市');

if($len>0) {

$pcArr = explode('市',$cityArr[1]);

$city=$pcArr[0];

$pid =empty($citys[$city]['pid']) ? '' : $citys[$city]['pid'];

$cid =empty($citys[$city]['cid']) ? '' : $citys[$city]['cid'];

} else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

}

else {

$city = '';

$pid =empty($citys[$province]['pid']) ? '' : $citys[$province]['pid'];

$cid =empty($citys[$province]['cid']) ? '' : $citys[$province]['cid'];

}

delLine($filename,$lineText);

}

else {

$country = $cityStr;

$province='';

$city='';

$cid = '';

$pid ='';

delLine($filename,$lineText);

}

}

$i++;

echo $ip2;exit;

$sql = 'insert into `city_ip`(`ip1`,`ip2`,`country`,`ser`,`province_id`,`province_name`,`city_id`,`city_name`) values ("'.$ip1.'","'.$ip2.'","'.$country.'","'.$ser.'","'.$pid.'","'.$province.'","'.$cid.'","'.$city.'")';

if(mysql_query($sql)) {

echo $i.'<br/>';

}

}

}

function delLine($filename,$text) {

$f1=fopen($filename,'r');

$tmp=tempnam('e:\web\www\\','newip.txt');//建立临时文件

$f2=fopen($tmp,'w');

while(!feof($f1)){

$line=fgets($f1);

if ($line!=$text) fputs($f2,$line);

}

fclose($f1);

fclose($f2);

rename($tmp,$filename);

}

parseAndImport('ip1.txt',$citys);

转载于:https://blog.51cto.com/mrcelite/751380

你可能感兴趣的文章