Created
April 17, 2013 09:17
-
-
Save cuheguevara/5402946 to your computer and use it in GitHub Desktop.
PHP XML Parser
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
function curl_get_html($options, $file) { | |
$ch = curl_init(); | |
foreach ($options as $key => $value) { | |
curl_setopt($ch, $key, $value); | |
} | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); | |
$server_output = curl_exec($ch); | |
curl_close($ch); | |
@unlink($file); | |
$fp = @fopen($file, 'w'); | |
fwrite($fp, $server_output); | |
fclose($fp); | |
return $file; | |
} | |
$url = array( | |
"http://address1.com/sitemap.xml", | |
"http://address2.com/site.xml", | |
"http://address3.com/sitemap.xml" | |
); | |
$inputFile = 'input.html'; | |
$outputFile = 'output.html'; | |
if (!file_exists($inputFile)){ | |
$fp = fopen($inputFile, 'w'); | |
fclose($fp); | |
}else{ | |
unlink($inputFile); | |
$fp = fopen($inputFile, 'w'); | |
fclose($fp); | |
} | |
if (!file_exists($outputFile)){ | |
$fp = fopen($outputFile, 'w'); | |
fclose($fp); | |
}else{ | |
unlink($outputFile); | |
$fp = fopen($inputFile, 'w'); | |
fclose($fp); | |
} | |
foreach ($url as $page) { | |
$options = array(CURLOPT_URL => $page,CURLOPT_POST => 0); | |
if (!file_exists($inputFile)){ | |
$fp = fopen($inputFile, 'w'); | |
fclose($fp); | |
} | |
// CURL XML to local file | |
$output = curl_get_html($options, $inputFile); | |
// load & extract local file | |
$xml = simplexml_load_file($output); | |
$fp = @fopen($outputFile, 'a'); | |
foreach ($xml as $value) { | |
//echo $value->loc . " \n"; | |
// extract node into text a line | |
fwrite($fp, $value->loc . " \n"); | |
} | |
fclose($fp); | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment