Title spider html and php source code

Title spider

« see it in action | download title-spider.rar
<!DOCTYPE html>
<html>
<head>
	<title>Get the titles of html documents</title>
</head>
<body bgcolor="white">
	<img style="margin-top:2px;" src="titlespider.png">
	<br><br>
	<p style="color:black;">

		Insert a list of urls and this tool will try to gather the title with each. Insert the urls one per line. Red urls didn't work, orange urls didn't have a title.

	</p>
	<form name="gettitleservice" action="index.php" method="POST">
		<textarea cols="190" rows="20" name="urllist"></textarea><br>
		<input type="submit">
	</form>
	<br><br>
<?php

$timeBeforeNextPost = 100; // Here you set howmany seconds users have to wait between use.
$maxurls = 100; // Here you set howmany urls the user may post at a time.

$gettime = time();

// The time the last post took place is stored in a file. 

// If it doesn't exist this file is created.

if (!file_exists('this file holds the time of the last post.txt')) {
	$handle = fopen('this file holds the time of the last post.txt', 'x+');
	fwrite($handle, $gettime);
	fclose($handle);
	$lastposttime = $gettime;

// If the time file does exist read it's value into a variable.

} else {
	$lastposttime = file_get_contents("this file holds the time of the last post.txt");
}

// Check if anything at all was posted.

if($_SERVER['REQUEST_METHOD'] == "POST"){

// Get the url list.
 
	$urllistb = $_REQUEST["urllist"];

// Check if enough time has expired since the last user used the tool.

	if (($gettime-$lastposttime) < $timeBeforeNextPost){
		echo 'It was less than ' . $timeBeforeNextPost . ' seconds ago when the tool was last used. I have to limit usage a bit sorry. You will have to wait exactly: ' . ($timeBeforeNextPost-($gettime-$lastposttime)) . ' seconds.<br><br><a href="javascript:history.back(1);">go back</a>';
		exit;
	}

// Turn the url list into an array. Real men use arrays.

	$urlArray = explode(PHP_EOL, $urllistb);

// Check if the user is perhaps over exited.

	if(count($urlArray) > $maxurls) {
		die("sorry, ". $maxurls . " urls is the maximum.");
	}

// Loop though the Array of links.

	foreach ($urlArray as $theurl){

// Replace https with http.

		$theurl=str_replace("https://", "http://", $theurl);

// The url finding process may take ages therefore we send the unfinished page to the browser.

		flush();

// Load the html.

		$thepage=@file_get_contents($theurl);

// Did we get anything at all?
		
		if($thepage !== FALSE) {

// Life is hard enough the way it is, lets just do the lowercases everything.

			;$thepage = strtolower($thepage);

// Finding the title in the html and extract it.

			preg_match('/<title>(.+)<\/title>/',$thepage,$matches);

// Did we get anything at all?

			if($matches[1]){

// Strip out the html and write things back to the page.

				echo strip_tags(ucfirst($matches[1])) . "<br>" . $theurl . "<br><br>";

// If we didn't find a <title> in the document we print the url in orange.

			}else{
				echo "<span style='color:orange;'>" . $theurl . "</span><br><br>";
			}

// If we didn't find any page at all we print the url in red.

		}else{
			echo "<span style='color:red;'>" . $theurl . "</span><br><br>";
		}
	}
}
?>