almal almal - 22 days ago 14
Ajax Question

PHP parse Meta Tags of an aspx page failure

In my project I have a PHP function that parses an HTML page and retrieves meta tags correctly. When I run my function for an aspx page this fails and doesn't create return data even though the aspx page in question has correctly set the meta tags.

The function is:

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;
}


How is it possible to read meta tags from aspx pages?

Thanks in advance

AM

Answer

There might be a easier way to do this using get_meta_tags

e.g.

<?php

// Load
$tags = get_meta_tags('http://www.example.com/');

// Debug
echo "<pre>";
print_r($tags);
echo "</pre>";

?>
Comments