note 56701 added to function.get-meta-tags
| From: | mariano at cricava dot com | Date: | Tue, 13 Sep 2005 00:18:16 +0000 |
| Subject: | note 56701 added to function.get-meta-tags | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-95081@lists.php.net to get a copy of this message | ||
Based on Michael Knapp's code, and adding some regex, here's a function that will get all
meta tags and the title based on a URL. If there's an error, it will return false. Using the
function getUrlContents(), also included, it takes care of META REFRESH re-directions, following up
to the specified number of redirections. Please note that the regular expressions included were
split into strings because php.net was complaining about the line being to long ;)
<?php
function getUrlData($url)
{
$result = false;
$contents = getUrlContents($url);
if (isset($contents) && is_string($contents))
{
$title = null;
$metaTags = null;
preg_match('/<title>([^>]*)<\/title>/si', $contents, $match );
if (isset($match) && is_array($match) && count($match) > 0)
{
$title = strip_tags($match[1]);
}
preg_match_all('/<[\s]*meta[\s]*name="?' .
'([^>"]*)"?[\s]*' .
'content="?([^>"]*)"?[\s]*[\/]?[\s]*>/si', $contents, $match);
if (isset($match) && is_array($match) && count($match) == 3)
{
$originals = $match[0];
$names = $match[1];
$values = $match[2];
if (count($originals) == count($names) && count($names) == count($values))
{
$metaTags = array();
for ($i=0, $limiti=count($names); $i < $limiti; $i++)
{
$metaTags[$names[$i]] = array (
'html' => htmlentities($originals[$i]),
'value' => $values[$i]
);
}
}
}
$result = array (
'title' => $title,
'metaTags' => $metaTags
);
}
return $result;
}
function getUrlContents($url, $maximumRedirections = null, $currentRedirection = 0)
{
$result = false;
$contents = @file_get_contents($url);
// Check if we need to go somewhere else
if (isset($contents) && is_string($contents))
{
preg_match_all('/<[\s]*meta[\s]*http-equiv="?REFRESH"?' .
'[\s]*content="?[0-9]*;[\s]*URL[\s]*=[\s]*([^>"]*)"?' .
'[\s]*[\/]?[\s]*>/si', $contents, $match);
if (isset($match) && is_array($match) && count($match) == 2 &&
count($match[1]) == 1)
{
if (!isset($maximumRedirections) || $currentRedirection < $maximumRedirections)
{
return getUrlContents($match[1][0], $maximumRedirections, ++$currentRedirection);
}
$result = false;
}
else
{
$result = $contents;
}
}
return $contents;
}
?>
Here's an example of its usage. Check that the included URL has a META REFRESH redirection:
<?php
$result = getUrlData('http://www.marianoiglesias.com.ar/');
echo '<pre>'; print_r($result); echo '</pre>';
?>
For the above code the output would be:
<?php
Array
(
[title] => Mariano Iglesias: El Eternauta
[metaTags] => Array
(
[description] => Array
(
[html] => <meta name="description" content="Java, PHP, and
some other technological mumble jumble. Also, some real-life stuff as well." />
[value] => Java, PHP, and some other technological mumble jumble. Also, some
real-life stuff as well.
)
[DC.title] => Array
(
[html] => <meta name="DC.title" content="Mariano Iglesias -
Weblog" />
[value] => Mariano Iglesias - Weblog
)
[ICBM] => Array
(
[html] => <meta name="ICBM" content="-34.6017,
-58.3956" />
[value] => -34.6017, -58.3956
)
[geo.position] => Array
(
[html] => <meta name="geo.position"
content="-34.6017;-58.3956" />
[value] => -34.6017;-58.3956
)
[geo.region] => Array
(
[html] => <meta name="geo.region" content="AR-BA">
[value] => AR-BA
)
[geo.placename] => Array
(
[html] => <meta name="geo.placename" content="Buenos
Aires">
[value] => Buenos Aires
)
)
)
?>
----
Manual Page -- http://www.php.net/manual/en/function.get-meta-tags.php
Edit -- http://master.php.net/manage/user-notes.php?action=edit+56701
Delete: added to the manual -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes&reason=added+to+the+manual
Delete: bad code -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes&reason=bad+code
Delete: spam -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes&reason=spam
Delete: useless -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes&reason=useless
Delete: non-english -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes&reason=non-english
Delete: other reasons -- http://master.php.net/manage/user-notes.php?action=delete+56701&report=yes
Reject -- http://master.php.net/manage/user-notes.php?action=reject+56701&report=yes
Search -- http://master.php.net/manage/user-notes.php