php 截取一个网页的所有超链接的代码 急急
3个回答
展开全部
<?php
header("Content-type: text/html; charset=utf-8");
if(!empty($_POST['input_text'])) {
ini_set('default_socket_timeout', 60); //php file_get_contents超时控制
if(!$data = file_get_contents($_POST['input_text'])) {
echo "Time out!";
return false;
}else{
$charset_pos = stripos($data,'charset');
if($charset_pos) { //页面数据编码格式转换
if(stripos($data,'utf-8',$charset_pos)) {
$data = iconv('utf-8','utf-8',$data);
}else if(stripos($data,'gb2312',$charset_pos)) {
$data = iconv('gb2312','utf-8',$data);
}else if(stripos($data,'gbk',$charset_pos)) {
$data = iconv('gbk','utf-8',$data);
}
}
}
//获取超链接核心代码
$pattern = '/<a(.*?)href="((http(s?):\/\/)?([^\"]+))"([^>]*?)>([^<]*?)<\/a>/i';
preg_match_all($pattern, $data, $links);
$links[2]为全部链接。
$br = 5;
echo "<table><tr>";
//$links[2]为所有超链接组成的数组。
foreach($links[0] as $count => $link){
if($count!=0 && $count%$br == 0) echo "</tr><tr>";
echo "<td>".$link."</td>";
}
echo "</tr></table>";
die;
}else {
?>
<html>
<head>
<title>Get Web Page</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta http-equiv="Content-Language" content="zh-CN" />
<script type="text/javascript">
function createXMLHTTP()
{
try
{
var request = new XMLHttpRequest();
}
catch(e1)
{
var arrVersions = ["Microsoft.XMLHTTP","MSXML2.XMLHttp.4.0",
"MSXML2.XMLHttp.3.0","MSXML2.XMLHttp.5.0"];
for(var i=0;i < arrVersions.length;i++){
try{
request = new ActiveXObject(arrVersions[i]);
}catch(e2){
request = false;
}
}
}
return request;
}
function ajax_post(url, params, target_id)
{
request = new createXMLHTTP();
request.onreadystatechange = function() {
if (this.readyState == 4)
if (this.status == 200)
if (this.responseText != null)
document.getElementById(target_id).innerHTML = this.responseText;
}
request.open("POST", url, true);
request.setRequestHeader("Content-type", "application/x-www-form-urlencoded");
request.setRequestHeader("Content-length", params.length);
request.setRequestHeader("Connection", "close");
request.send(params);
}
var checked = false;
function check_(value) {
checked = value;
}
function get_key(event) {
event = event || window.event;
if(event.keyCode==13 && checked != false)
{
var url = document.getElementById('input_text').value;
if(url != '') {
get_page();
}else {
document.getElementById('input_text').onfocus();
return false;
}
}
}
function get_page() {
var url = document.getElementById('input_text').value;
if(!url) {
return false;
}else {
if(document.getElementById('output_page').innerHTML != '') {
document.getElementById('output_page').innerHTML = '';
}
}
if(url.indexOf('
url = '
}
ajax_post(
'<?php echo $_SERVER['PHP_SELF']; ?>',
'input_text='+url,
'output_page'
);
document.getElementById('click_show').style.display = 'block';
document.getElementById('back_a').href = document.location.href;
document.getElementById('origin_website').href = url;
}
</script>
<style>
.div_box{
margin-top:10px;
}
.input_box{
border:1px solid;
margin-left:10px;
margin-top:2px;
height:15px;
float:left;
size:32
font-size: 14px;
}
.button_box{
float:left;
height:23px;
padding-bottom:3px;
}
.hide_box{
display:none;
}
.a_box{
margin-left:10px;
margin-top:3px;
height:15px;
float:left;
font-size: 14px;
}
.clear_box{
height:50px;
}
</style>
</head>
<body onkeydown="get_key(event)">
<div class="div_box">
<input id="input_text" class="input_box" type="text" value="" onclick="check_(true)" onblur="check_(false)"></input>
<input type="button" class="button_box" onclick="get_page()" value="Get it!" ></input>
<div id="click_show" class="hide_box">
<a id="origin_website" class="a_box" href="#" target="_black">访问原站</a>
<a id="back_a" class="a_box" href="#">后退</a>
</div>
</div>
<div class="clear_box"></div>
<div id="output_page"></div>
</body>
</html>
<?php
}
//End_php
header("Content-type: text/html; charset=utf-8");
if(!empty($_POST['input_text'])) {
ini_set('default_socket_timeout', 60); //php file_get_contents超时控制
if(!$data = file_get_contents($_POST['input_text'])) {
echo "Time out!";
return false;
}else{
$charset_pos = stripos($data,'charset');
if($charset_pos) { //页面数据编码格式转换
if(stripos($data,'utf-8',$charset_pos)) {
$data = iconv('utf-8','utf-8',$data);
}else if(stripos($data,'gb2312',$charset_pos)) {
$data = iconv('gb2312','utf-8',$data);
}else if(stripos($data,'gbk',$charset_pos)) {
$data = iconv('gbk','utf-8',$data);
}
}
}
//获取超链接核心代码
$pattern = '/<a(.*?)href="((http(s?):\/\/)?([^\"]+))"([^>]*?)>([^<]*?)<\/a>/i';
preg_match_all($pattern, $data, $links);
$links[2]为全部链接。
$br = 5;
echo "<table><tr>";
//$links[2]为所有超链接组成的数组。
foreach($links[0] as $count => $link){
if($count!=0 && $count%$br == 0) echo "</tr><tr>";
echo "<td>".$link."</td>";
}
echo "</tr></table>";
die;
}else {
?>
<html>
<head>
<title>Get Web Page</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta http-equiv="Content-Language" content="zh-CN" />
<script type="text/javascript">
function createXMLHTTP()
{
try
{
var request = new XMLHttpRequest();
}
catch(e1)
{
var arrVersions = ["Microsoft.XMLHTTP","MSXML2.XMLHttp.4.0",
"MSXML2.XMLHttp.3.0","MSXML2.XMLHttp.5.0"];
for(var i=0;i < arrVersions.length;i++){
try{
request = new ActiveXObject(arrVersions[i]);
}catch(e2){
request = false;
}
}
}
return request;
}
function ajax_post(url, params, target_id)
{
request = new createXMLHTTP();
request.onreadystatechange = function() {
if (this.readyState == 4)
if (this.status == 200)
if (this.responseText != null)
document.getElementById(target_id).innerHTML = this.responseText;
}
request.open("POST", url, true);
request.setRequestHeader("Content-type", "application/x-www-form-urlencoded");
request.setRequestHeader("Content-length", params.length);
request.setRequestHeader("Connection", "close");
request.send(params);
}
var checked = false;
function check_(value) {
checked = value;
}
function get_key(event) {
event = event || window.event;
if(event.keyCode==13 && checked != false)
{
var url = document.getElementById('input_text').value;
if(url != '') {
get_page();
}else {
document.getElementById('input_text').onfocus();
return false;
}
}
}
function get_page() {
var url = document.getElementById('input_text').value;
if(!url) {
return false;
}else {
if(document.getElementById('output_page').innerHTML != '') {
document.getElementById('output_page').innerHTML = '';
}
}
if(url.indexOf('
url = '
}
ajax_post(
'<?php echo $_SERVER['PHP_SELF']; ?>',
'input_text='+url,
'output_page'
);
document.getElementById('click_show').style.display = 'block';
document.getElementById('back_a').href = document.location.href;
document.getElementById('origin_website').href = url;
}
</script>
<style>
.div_box{
margin-top:10px;
}
.input_box{
border:1px solid;
margin-left:10px;
margin-top:2px;
height:15px;
float:left;
size:32
font-size: 14px;
}
.button_box{
float:left;
height:23px;
padding-bottom:3px;
}
.hide_box{
display:none;
}
.a_box{
margin-left:10px;
margin-top:3px;
height:15px;
float:left;
font-size: 14px;
}
.clear_box{
height:50px;
}
</style>
</head>
<body onkeydown="get_key(event)">
<div class="div_box">
<input id="input_text" class="input_box" type="text" value="" onclick="check_(true)" onblur="check_(false)"></input>
<input type="button" class="button_box" onclick="get_page()" value="Get it!" ></input>
<div id="click_show" class="hide_box">
<a id="origin_website" class="a_box" href="#" target="_black">访问原站</a>
<a id="back_a" class="a_box" href="#">后退</a>
</div>
</div>
<div class="clear_box"></div>
<div id="output_page"></div>
</body>
</html>
<?php
}
//End_php
已赞过
已踩过<
评论
收起
你对这个回答的评价是？
展开全部
function get_links($content) {
$pattern = '/<a(.*?)href="(.*?)"(.*?)>(.*?)<\/a>/i';
preg_match_all($pattern, $content, $m);
return $m;
}
$pattern = '/<a(.*?)href="(.*?)"(.*?)>(.*?)<\/a>/i';
preg_match_all($pattern, $content, $m);
return $m;
}
本回答被网友采纳
已赞过
已踩过<
评论
收起
你对这个回答的评价是？
展开全部
远程截取 就用curl_exec 或者 fopen
这个方法可取：
function get_links($content) { $pattern = '/<a(.*?)href="(.*?)"(.*?)>(.*?)<\/a>/i'; preg_match_all($pattern, $content, $m); return $m; }
这个方法可取：
function get_links($content) { $pattern = '/<a(.*?)href="(.*?)"(.*?)>(.*?)<\/a>/i'; preg_match_all($pattern, $content, $m); return $m; }
已赞过
已踩过<
评论
收起
你对这个回答的评价是？
更多回答（1）
推荐律师服务：
若未解决您的问题，请您详细描述您的问题，通过百度律临进行免费专业咨询
