Description
This code will attempt to figure out the url's <title> tag
so that links on your site will always have the most current
and correct title.
The code grabs the first chunk of data from a URL,
looks for <title>, and displays an <a href>
tag using the URL's current title.
It is a neat way to always have your links use the most current page
title of the pages you link to, although it can really slow the loading
of *your* pages down if you link to slow/unavailable sites.
Useage & Examples
include('url_title_v0.1.php');
print url('hurring.com') ."\n";
// prints <a href='http://hurring.com'>Hurring.com</a>
print url('google.com') ."\n";
// prints <a href='http://google.com'>Google</a>
print url('hurring.com', 'Append me') ."\n";
// prints <a href='http://hurring.com'>Hurring.com: Append me</a>
print url('/code/php/') ."\n";
// prints <a href='http://hurring.com/code/php/'>Hurring.com: Code: PHP</a>
print url('/code/php/', "Append me") ."\n";
// prints <a href='http://hurring.com/code/php/'>Hurring.com: Code: PHP: Append me</a>
print url('groups.yahoo.com/groups/alhkjter/') ."\n";
// prints <a href='http://groups.yahoo.com/groups/alhkjter/'>groups.yahoo.com/groups/alhkjter/</a>
print url('groups.yahoo.com/groups/alhkjter/', 'Pirates') ."\n";
// prints <a href='http://groups.yahoo.com/groups/alhkjter/'>Pirates</a>
print url('garbage') ."\n";
// prints (Broken Link: garbage)
print url('garbage', 'Pirates') ."\n";
// prints (Broken Link: garbage: Pirates)
View source 'url_title.php'
<?
/**
* URL title looker-upper.
*
* This code will grab a chunk of data from a URL, look at the <title>
* and display an <a href> tag using the URL's current title.
*
* It is a neat way to always have your links use the most current page
* title of the pages you link to, although it can really slow the loading
* of *your* pages down if you link to slow/unavailable sites.
*
* @authour Scott Hurring (scott at hurring dot com)
* @version 0.2 (Dec 23, 2005) Merry christmas!
* http://hurring.com/code/php/url_title/
* @license GPL
*/
// Your site's domain, used if you give a url that's located
// on the current server: like "/code/index.php"
$url_site_domain = 'hurring.com';
/*
function url()
$link the URL whose title you want to fetch
$text optional text to append to the page title
*/
function url($link, $text='')
{
// Ensure $link is a valid URL
$url = url_resolve($link);
$fp = @fopen($url, 'r');
if (!$fp) {
$title = (!$text ? $link : $text);
return "(Broken Link: $link". ($text ? ": {$text}" : "") .")";
}
// Grab <title>*</title> from the first "chunk" of data
$title = url_grab_title($fp);
// No <title> tag in first chunk...
if (!$title) {
$title = (!$text ? $link : $text);
return "<a href='$url'>$title</a>";
}
// User gave me some text to append to the link title
if ($text) {
$title .= ': '. $text;
}
return "<a href='$url'>$title</a>";
}
/*
Attempt to turn a partial URL (e.g. "server.com" or "/code/")
into a valid URL (e.g. "http://server.com/" or "http://server.com/code/")
*/
function url_resolve($url)
{
global $url_site_domain;
if (!preg_match('/^(http|ftp):/', $url)) {
// assume it's not "server.tld" and instead "/dir/file.ext"
if (!preg_match('/\.(com|net|org|co|uk|edu|info|biz)/', $url)) {
$url = $url_site_domain .'/'. $url;
}
}
return 'http://'. preg_replace('/\/\//', '/', $url);
}
// Fetch a "chunk" of data and look for <title> in it
function url_grab_title($fp)
{
// How many bytes to grab in one chunk.
// Most sites seem to have <title> within 512
$chunk_size = 512;
$chunk = fread($fp, $chunk_size);
$chunk = preg_replace("/(\n|\r)/", '', $chunk);
// Look for <title>(.*?)</title> in the text
if (preg_match('/<title>(.*?)<\/title>/i', $chunk, $matches)) {
return $matches[1];
}
return null;
}
// Run this to test the code
function url_test()
{
print url('hurring.com') ."\n";
// <a href='http://hurring.com'>Hurring.com</a>
print url('google.com') ."\n";
// <a href='http://google.com'>Google</a>
print url('hurring.com', 'Append me') ."\n";
// <a href='http://hurring.com'>Hurring.com: Append me</a>
print url('/code/php/') ."\n";
// <a href='http://hurring.com/code/php/'>Hurring.com: Code: PHP</a>
print url('/code/php/', "Append me") ."\n";
// <a href='http://hurring.com/code/php/'>Hurring.com: Code: PHP: Append me</a>
print url('groups.yahoo.com/groups/alhkjter/') ."\n";
// <a href='http://groups.yahoo.com/groups/alhkjter/'>groups.yahoo.com/groups/alhkjter/</a>
print url('groups.yahoo.com/groups/alhkjter/', 'Pirates') ."\n";
// <a href='http://groups.yahoo.com/groups/alhkjter/'>Pirates</a>
print url('garbage') ."\n";
// (Broken Link: garbage)
print url('garbage', 'Pirates') ."\n";
// (Broken Link: garbage: Pirates)
}
?>
