本文章给大家介绍在php
正则表达式解析字符串里的所有URL地址实现代码，有需要了解学习的朋友可进入参考。
分享一个同事写的url正则表达式，缺点不支持中文url：
| 代码如下 |
复制代码 |
(http[s]{0,1}|ftp)://[a-zA-Z0-9.-]+.([a-zA-Z]{2,4})(:d+)?(/[a-zA-Z0-9.-~!@#$%^&*+?:_/=]*)? |
下面介绍一个可以支持中文正则url
| 代码如下 |
复制代码 |
var regexp = new RegExp("(http[s]{0,1}|ftp)://[a-zA-Z0-9.-]+.([a-zA-Z]{2,4})(:d+)?(/[a-zA-Z0-9.-~!@#$%^&*+?:_/=]*)?", "gi");
var urls = textbox.value.match(regexp) || [];//textbox为文本框
console.log(urls); |
实例
立即学习“PHP免费学习笔记（深入）”；
Melodio
Melodio是全球首款个性化AI流媒体音乐平台，能够根据用户场景或心情生成定制化音乐。
下载
| 代码如下 |
复制代码 |
|
// $html = the html on the page
// http://pic2.phprm.com/2013/05/22/$current_url.jpg = 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("/ $links = array();
if(isset($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; $i array_pop($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.phprm.com";
$html = file_get_contents($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));
|
