DZone Snippets is a public source code repository. Easily build up your personal collection of code snippets, categorize them with tags / keywords, and share them with the world
Export All Links From Any Page - PHP Code - Outbound/Inbound Links Checker
This code will show all internal and external links individually and also in count. This is being used in <a href="http://www.link-checker.org/" rel="dofollow" alt="link checker">link checker</a> as outbound links checking option.
<form method="post">
URL here: <input type="text" name="url" value="http://" /><br />
<input type="submit" name="submit" value="submit" />
</form>
<?php
// retrieve link destinations
function get_a_href($url){
$url = htmlentities(strip_tags($url));
$ExplodeUrlInArray = explode('/',$url);
$DomainName = $ExplodeUrlInArray[2];
$file = @file_get_contents($url);
$h1count = preg_match_all('/(href=["|\'])(.*?)(["|\'])/i',$file,$patterns);
$linksInArray = $patterns[2];
$CountOfLinks = count($linksInArray);
$InternalLinkCount = 0;
$ExternalLinkCount = 0;
for($Counter=0;$Counter<$CountOfLinks;$Counter++)
{
if($linksInArray[$Counter] == "" || $linksInArray[$Counter] == "#")
continue;
preg_match('/javascript:/', $linksInArray[$Counter],$CheckJavascriptLink);
if($CheckJavascriptLink != NULL)
continue;
$Link = $linksInArray[$Counter];
preg_match('/\?/', $linksInArray[$Counter],$CheckForArgumentsInUrl);
if($CheckForArgumentsInUrl != NULL)
{
$ExplodeLink = explode('?',$linksInArray[$Counter]);
$Link = $ExplodeLink[0];
}
preg_match('/'.$DomainName.'/',$Link,$Check);
if($Check == NULL)
{
preg_match('/http:\/\//',$Link,$ExternalLinkCheck);
if($ExternalLinkCheck == NULL)
{
$InternalDomainsInArray[$InternalLinkCount] = $Link;
$InternalLinkCount++;
}
else
{
$ExternalDomainsInArray[$ExternalLinkCount] = $Link;
$ExternalLinkCount++;
}
}
else
{
$InternalDomainsInArray[$InternalLinkCount] = $Link;
$InternalLinkCount++;
}
}
$LinksResultsInArray = array(
'ExternalLinks'=>$ExternalDomainsInArray,
'InternalLinks'=>$InternalDomainsInArray
);
return $LinksResultsInArray;
}
if(isset($_POST['submit']) && $_POST['submit'] == 'submit')
{
$url = $_POST['url'];
$linksInArray = get_a_href($url);
$CountOfExternalLink = count($linksInArray['ExternalLinks']);
$CountOfInternalLink = count($linksInArray['InternalLinks']);
echo "<h1>Linking structure</h1>";
if(!empty($linksInArray['ExternalLinks'])){
echo "<br/>External Links found: (".$CountOfExternalLink.")<ul>";
foreach($linksInArray['ExternalLinks'] as $key => $val){
$val = preg_replace("/</","<",$val);
echo "<li>" . htmlentities($val) . "</li>";
}
echo "</ul>";
}else{
echo "<br/><div class=\"error\">No External Links found</div><br/>";
}
if(!empty($linksInArray['InternalLinks'])){
echo "<br/>Internal Links found: (".$CountOfInternalLink.")<ul>";
foreach($linksInArray['InternalLinks'] as $key => $val){
$val = preg_replace("/</","<",$val);
echo "<li>" . htmlentities($val) . "</li>";
}
echo "</ul>";
}else{
echo "<br/><div class=\"error\">No Internal Links found</div><br/>";
}
}
?>





