PHP取网页所有链接实现程序代码总结

function get_all_url($code){
             preg_match_all(‘/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+)</a>/i’,$code,$arr);
            return array(‘name’=>$arr[2],’url’=>$arr[1]);
}

$url ='http://www.111cn.net';
$body=@file_get_contents($url);
preg_match_all('/href=['"]?([^'"]*)['"]?>(.*)/i',$body,$b);
$nums = array();
foreach($b[1] as $u){
  if(in_array($u,$nums)){
  continue;
  }
  $nums[]=$u;
  $title=strip_tags($u);
  echo $title."</br>";
}

<?php
/*
 * 使用curl 采集www.111cn.net下的所有链接。 
 */
include_once('function.php');

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'http://www.111cn.net/');
// 只需返回HTTP header
curl_setopt($ch, CURLOPT_HEADER, 1);
// 页面内容我们并不需要
// curl_setopt($ch, CURLOPT_NOBODY, 1);
// 返回结果，而不是输出它
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$html = curl_exec($ch);
$info = curl_getinfo($ch);
if ($html === false) {
 echo "cURL Error: " . curl_error($ch);
}

curl_close($ch);
$linkarr = _striplinks($html);
// 主机部分，补全用
$host = 'http://www.111cn.net/';
if (is_array($linkarr)) {
 foreach ($linkarr as $k => $v) {
  $linkresult[$k] = _expandlinks($v, $host);
 }
}

printf("<p>此页面的所有链接为：</p><pre>%s</pre>n", var_export($linkresult , true));

?>

<?
　　$e=clinchgeturl("http://im286.com/forumdisplay.php?fid=1");
　　
　　var_dump($e);
　　function clinchgeturl($url)
　　{
　　
　　//$url="http://127.0.0.1/1.htm";
　　//$rootpath="http://fsrootpathfsfsf/yyyyyy/";
　　//var_dump($rrr);
　　if(eregi('(.)*[.](.)*',$url)){
　　 $roopath=split("/",$url);
　　 $rootpath="http://".$roopath[2]."/";
　　 $nnn=count($roopath)-1;for($yu=3;$yu<$nnn;$yu ){$rootpath.=$roopath[$yu]."/";}
　　 // var_dump($rootpath); //http: ,'',127.0.0.1,xnml,index.php
　　 }
　　 else{$rootpath=$url;//var_dump($rootpath);
　　}
　　if(isset($url)){
　　echo "$url 有下列裢接：<br>";
　　$fcontents = file($url);
　　while(list(,$line)=each($fcontents)){
　　while(eregi('(href[[:space:]]*=[[:space:]]*"?[[:alnum:]:@/._-] [?]?[^"]*"?)',$line,$regs)){
　　//$regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*"?)([[:alnum:]:@/._-] )("?)',"\2",$regs[1]);
　　$regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*["]?)([[:alnum:]:@/._-] [?]?[^"]*)(.*)[^"/]*(["]?)',"\2",$regs[1]);
　　
　　if(!eregi('^http://',$regs[1])){
　　
　　 if(eregi('^..',$regs[1])){
　　 // $roopath=eregi_replace('(http://)?([[:alnum:]:@/._-] )[[:alnum:] ](.*)[[:alnum:] ]',"http://\2",$url);
　　
　　 $roopath=split("/",$rootpath);
　　 $rootpath="http://".$roopath[2]."/";
　　 //echo "这是根本d ："."n";
　　 $nnn=count($roopath)-1;for($yu=3;$yu<$nnn;$yu ){$rootpath.=$roopath[$yu]."/";}
　　 //var_dump($rootpath);
　　 if(eregi('^..[/[:alnum:]]',$regs[1])){
　　 //echo "这是../目录/ ："."n";
　　 //$regs[1]="../xx/xxxxxx.xx";
　　 // $rr=split("/",$regs[1]);
　　 //for($oooi=1;$oooi<count($rr);$oooi )
　　$rrr=$regs[1];
　　 // {$rrr.="/".$rr[$oooi];
　　 $rrr = eregi_replace("^[.][.][/]",'',$rrr); /

(http[s]{0,1}|ftp)://[a-zA-Z0-9\.\-]+\.([a-zA-Z]{2,4})(:\d+)?(/[a-zA-Z0-9\.\-~!@#$%^&*+?:_/=<>]*)?

<?php
// $html        = the html on the page
// $current_url = the full url that the html came from (only needed for $repath)
// $repath      = converts ../ and / and // urls to full valid urls
function pageLinks($html, $current_url = "", $repath = false){
    preg_match_all("/<a.+?href=("|')(?!javascript:|#)(.+?)("|')/i", $html, $matches);
    $links = array();
    if(isset($matches[2])){
        $links = $matches[2];
    }
    if($repath && count($links) > 0 && strlen($current_url) > 0){
        $pathi      = pathinfo($current_url);
        $dir        = $pathi["dirname"];
        $base       = parse_url($current_url);
        $split_path = explode("/", $dir);
        $url        = "";
        foreach($links as $k => $link){
            if(preg_match("/^../", $link)){
                $total = substr_count($link, "../");
                for($i = 0; $i < $total; $i++){
                    array_pop($split_path);
                }
                $url = implode("/", $split_path) . "/" . str_replace("../", "", $link);
            }elseif(preg_match("/^///", $link)){
                $url = $base["scheme"] . ":" . $link;
            }elseif(preg_match("/^/|^.//", $link)){
                $url = $base["scheme"] . "://" . $base["host"] . $link;
            }elseif(preg_match("/^[a-zA-Z0-9]/", $link)){
                if(preg_match("/^http/", $link)){
                    $url = $link;
                }else{
                    $url       = $dir . "/" . $link;
                }
            }
            $links[$k] = $url;
        }
    }
    return $links;
}
header("content-type: text/plain");
$url = "http://www.111cn.net";
$html = file_get_contents($url);
// Gets links from the page:
print_r(pageLinks($html));

// Gets links from the page and formats them to a full valid url:
print_r(pageLinks($html, $url, true));

-- phpMyAdmin SQL Dump
-- version 2.11.2-rc1
-- http://www.111cn.net
--
-- 主机: localhost
-- 生成日期: 2010 年 11 月 09 日 05:34
-- 服务器版本: 5.0.41
-- PHP 版本: 5.2.4

SET SQL_MODE="NO_AUTO_VALUE_ON_ZERO";

--
-- 数据库: `demo`
--

-- --------------------------------------------------------

--
-- 表的结构 `customer`
--

CREATE TABLE IF NOT EXISTS `customer` (
  `id` int(11) NOT NULL auto_increment,
  `username` varchar(100) NOT NULL,
  `solutation` varchar(40) NOT NULL,
  `phone` varchar(50) NOT NULL,
  `company` varchar(100) NOT NULL,
  `mobile` varchar(50) NOT NULL,
  `source` varchar(50) NOT NULL,
  `sdate` date NOT NULL,
  `job` varchar(50) NOT NULL,
  `web` varchar(100) NOT NULL,
  `email` varchar(100) NOT NULL,
  `createtime` datetime NOT NULL,
  `modifiedtime` datetime default NULL,
  `note` varchar(500) NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=MyISAM  DEFAULT CHARSET=utf8 AUTO_INCREMENT=2 ;

--
-- 导出表中的数据 `customer`
--

INSERT INTO `customer` (`id`, `username`, `solutation`, `phone`, `company`, `mobile`, `source`, `sdate`, `job`, `web`, `email`, `createtime`, `modifiedtime`, `note`) VALUES
(1, '李小三', '先生', '(513) 378-6268', '常丰集团', '13800138000', '合作伙伴', '2011-11-30', '部门经理', 'www.helloweba.com', 'lrfbeyond@163.com', '2010-11-04 21:11:59', '2010-11-08 09:30:35', '备注信息n');

<?php
include_once("connect.php");
$query=mysql_query("select * from customer where id=1");
$rs=mysql_fetch_array($query);
$username=$rs['username'];
$userid=$rs['userid'];
$solutation=$rs['solutation'];
$phone=$rs['phone'];
$company=$rs['company'];
$mobile=$rs['mobile'];
$source=$rs['source'];
$sdate=$rs['sdate'];
$job=$rs['job'];
$web=$rs['web'];
$email=$rs['email'];
$createtime=$rs['createtime'];
$modifiedtime=$rs['modifiedtime'];
$note=$rs['note'];
?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>可编辑的表格：jQuery+PHP实现实时编辑表格字段内容-Helloweba演示平台</title>
<link rel="stylesheet" type="text/css" href="css/main.css" />
<link rel="stylesheet" type="text/css" href="css/jquery-ui.css" />
<style type="text/css">
table{width:96%; margin:20px auto; border-collapse:collapse;}
table td{line-height:26px; padding:2px; padding-left:8px; border:1px solid #b6d6e6;}
.table_title{height:26px; line-height:26px; background:url(css/btn_bg.gif) repeat-x bottom; font-weight:bold; text-indent:.3em; outline:0;}
.table_label{background:#e8f5fe; text-align:right; }
.btn{height:24px; background:url(css/btn_bg.gif) repeat-x; padding:0 4px; font-size:12px; border:1px solid #ccc; cursor:pointer; margin-left:3px}
.input{border:1px solid #369; background:#ffc; padding:2px}
.msg{padding-left:30px; margin-top:20px}
textarea{font-size:12px}
</style>
<script type="text/javascript" src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js"></script>
<script type="text/javascript" src="js/jquery.jeditable.js"></script>
<script type='text/javascript' src='http://ajax.googleapis.com/ajax/libs/jqueryui/1.7.2/jquery-ui.min.js'></script>
<script type="text/javascript">
$(function(){
$('.edit').editable('save.php');
$('.edit_select').editable('save.php', {
loadurl : 'json.php',
type : "select",
style : 'display: inline'
});

$(".edit_email").editable('save.php', {
type : 'email',
select : true
});
$(".edit_mobile").editable('save.php', {
type : 'mobile',
select : true
});
$(".edit_web").editable('save.php', {
type : 'url',
select : true
});
});
</script>
</head>

<body>
<div id="main">
<h2 class="top_title"><a href="">可编辑的表格：jQuery+PHP实现实时编辑表格字段内容</a></h2>
<div class="msg"><strong>提示</strong>：点击表格中字段对应的内容即可进行在线编辑。</div>
<table width="100%" border="0" cellspacing="0" cellpadding="0">
<thead>
<tr class="table_title">
<td colspan="4"><span class="open"></span>客户信息</td>
</tr>
</thead>
<tbody>
<tr>
<td width="20%" class="table_label">姓名</td>
<td width="30%" class="edit" id="username"><?php echo $username; ?></td>
<td width="20%" class="table_label">办公电话</td>
<td width="30%" class="edit" id="phone"><?php echo $phone; ?></td>
</tr>
<tr>
<td class="table_label">称谓</td>
<td class="edit" id="solutation"><?php echo $solutation; ?></td>
<td class="table_label">手机</td>
<td class="edit" id="mobile"><?php echo $mobile; ?></td>
</tr>
<tr>
<td class="table_label">公司名称</td>
<td class="edit" id="company"><?php echo $company; ?></td>
<td class="table_label">电子邮箱</td>
<td class="edit" id="email"><?php echo $email; ?></td>
</tr>
<tr>
<td class="table_label">潜在客户来源</td>
<td class="edit_select" id="source"><?php echo $source; ?></td>
<td class="table_label">网站</td>
<td class="edit" id="web"><?php echo $web; ?></td>
</tr>
<tr>
<td class="table_label">职位</td>
<td class="edit" id="job"><?php echo $job; ?></td>
<td class="table_label">修改时间</td>
<td id="modifiedtime"><?php echo $modifiedtime; ?></td>
</tr>
</tbody>
</table>
</div>

</body>
</html>

<?php
include_once("connect.php");

$field=$_POST['id'];

$val=$_POST['value'];
$val = htmlspecialchars($val, ENT_QUOTES);
if($field=="note"){
 if(strlen($val)>100){
  echo "您输入的字符大于100字了";
  exit;
 }
}
$time=date("Y-m-d H:i:s");
if(empty($val)){
    echo "不能为空";
}else{
 $query=mysql_query("update customer set $field='$val',modifiedtime='$time' where id=1");
 if($query){
    echo $val;
 }else{
    echo "数据出错"; 
 }
}
?>

strip_tags($source, ”); 去掉所以的html标签。

strip_tags($source, ‘<div><img><em>’); 保留字符串中的div、img、em标签。

// 百度首页内容

$string = file_get_contents('http://www.111cn.net/');

// 去掉 style 及包含内容
$string = replace_html_tag($string, 'style', true);
$string = replace_html_tag($string, 'script', true);

// 去掉 a 标签，并保存其中内容
$string = replace_html_tag($string, 'a');

// 去掉 span 标签，并保存其中内容
$string = replace_html_tag($string, 'span');

echo $string;
?>

max_execution_time = 30     ; Maximum execution time of each script, in seconds
max_input_time = 60    ; Maximum amount of time each script may spend parsing request data
;max_input_nesting_level = 64 ; Maximum input variable nesting level
memory_limit = 128M      ; Maximum amount of memory a script may consume (128MB)

; Maximum size of POST data that PHP will accept.
post_max_size = 105M

; Maximum allowed size for uploaded files.
upload_max_filesize = 100M

set_time_limit(0);