Estrarre urls da una pagina

[salentonet]

Estrarre urls da una pagina

Ho trovato questo script slla rete, che promette di estarre tutti gli url da un indirizzo internet, ma non funziona
Chi di voi è in grado di correggerlo?

<?php

if (getenv('REQUEST_METHOD') == 'POST') {
$url = $_POST;
} else {
$url = $_GET;
}
?>

<form action="<?= $PHP_SELF ?>" method="POST">
URL:<input type="text" name="url" value="<?= $url ?>"/>

<input type="submit">
</form>

<?php
if ($url) {
$remote = fopen($url, 'r');
$html = fread($remote, 1048576);
fclose($remote);

$urls = '(http|file|ftp)';
$ltrs = 'w';
$gunk = '/#~:.?+=&%@!-';
$punc = '.:?-';
$any = "$ltrs$gunk$punc";
preg_match_all("{
                  b
                  $urls   :
                  [$any] +?


                  (?=
                    [$punc] *
                    [^$any]
                  |
                    $
                  )
              }x", $html, $matches);
printf("Output of URLs %d URLs

n", sizeof($matches[0]));
foreach ($matches[0] as $u) {
$link = $PHP_SELF . '?url=' . urlencode($u);
echo "[url='$link']$u
n";
}
}
?>

grazie

[cached]

prova questo costruttore :

class LinkExtractor {
	/* private Array variable: $linkReg [ contains pregs to parse links ]*/
	var $linkReg = Array(
	"/&#40;?i&#41;<a&#40;&#91;^\a&#93;+?&#41;href='&#40;&#91;^\a&#93;+?&#41;'/i",
	"/&#40;?i&#41;<a&#40;&#91;^\a&#93;+?&#41;href=\"&#40;&#91;^\a&#93;+?&#41;\"/i",
	"/&#40;?i&#41;<a&#40;&#91;^\a&#93;+?&#41;href=&#40;&#91;^\a&#93;+?&#41;&#91; |>&#93;/i"
	&#41;;

	/**
	* Public constructor.
	* Create a global Array with no value, used for parsing
	* and an internal array with valid pregs for links parsing.
	*/
	function LinkExtractor&#40;&#41; &#123;
		global $__linkExtractor_linkRecipient;
		$__linkExtractor_linkRecipient = Array&#40;&#41;;
	&#125;

	/**
	* Private method, popolate internal Array with preg matches
	* .
	* @Param	String		String to push into internal array
	* @Return	nothing
	*/
        function __manageLinkRecipient&#40; $replacement &#41; &#123;
		global $__linkExtractor_linkRecipient;
		array_push&#40; $__linkExtractor_linkRecipient, htmlspecialchars&#40; $replacement&#91;2&#93; &#41; &#41;;
	&#125;

	/**
	* Private method, call preg_replace_callback function with string.
	* .
	* @Param	String		String to parse
	* @Return	nothing
	*/
	function __callBackCaller&#40; $st &#41; &#123;
		preg_replace_callback&#40; $this->linkReg, Array&#40; &$this, '__manageLinkRecipient' &#41;, $st &#41;;
	&#125;

	/**
	* Public method, read remote page or file and parse them
	* .
	* @Param	String		valid url address to parse
	* @Return	Boolean		true if readed , false in other cases
	*/
	function parseUrl&#40; $url &#41; &#123;
		if&#40; @$fp = fopen&#40; $url, "r" &#41; &#41; &#123;
			$st = '';
			while&#40; $text = fread&#40; $fp, 8192 &#41; &#41; &#123;
				$st .= $text;
			&#125;
			fclose&#40; $fp &#41;;
			$this->__callBackCaller&#40; $st &#41;;
			return true;
		&#125;
		return false;
	&#125;
	
	/**
	* Public method, parse links in a file
	* .
	* @Param	String		string to parse
	* @Return	nothing
	*/
	function parseFile&#40; $st &#41; &#123;
		return $this->parseUrl&#40; $st &#41;;
	&#125;

	/**
	* Public method, parse links in a string
	* .
	* @Param	String		string to parse
	* @Return	nothing
	*/
	function parseString&#40; $st &#41; &#123;
		$this->__callBackCaller&#40; $st &#41;;
	&#125;
	
	/**
	* Public method, return an array with all found links
	* .
	* @Param	no	no params need
	* @Return	Array	Array with all links &#40; if there're &#41;
	*/
	function getLinks&#40;&#41; &#123;
		global $__linkExtractor_linkRecipient;
		return $__linkExtractor_linkRecipient;
	&#125;
&#125;
function linkExtractor&#40; $what, $url = false &#41; &#123;
	
	
	$myLinks = &new LinkExtractor&#40;&#41;;
	if&#40; $url == false &#41; &#123;
		$myLinks->parseString&#40; $what &#41;;
	&#125;
	elseif&#40; $url == true &#41; &#123;
	        if&#40; $myLinks->parseUrl&#40; $what &#41; == false &#41; &#123;
	        	return false;
		&#125;
	&#125;
	return $myLinks->getLinks&#40;&#41;;
&#125;

// EXAMPLE
$url = "http&#58;//www.php.net/"; // site to parse

$arrayLinks = &linkExtractor&#40; $url, true &#41;;

if&#40; $arrayLinks != false &#41; &#123;
	for&#40; $a = 0, $b = count&#40; $arrayLinks &#41;; $a < $b; $a++ &#41; &#123;
		echo $arrayLinks&#91;$a&#93;."
";
	&#125;
&#125;

```[/img]