| Server IP : 79.136.114.73 / Your IP : 3.128.173.223 Web Server : Apache/2.4.7 (Ubuntu) PHP/5.5.9-1ubuntu4.29 OpenSSL/1.0.1f System : Linux b8009 3.13.0-170-generic #220-Ubuntu SMP Thu May 9 12:40:49 UTC 2019 x86_64 User : www-data ( 33) PHP Version : 5.5.9-1ubuntu4.29 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority, MySQL : ON | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /proc/self/root/home/b8009/php-5.6.22/ext/tidy/examples/ |
Upload File : |
<?php
/*
* urlgrab5.php
*
* A simple command-line utility to extract all of the URLS contained
* within <A HREF> tags from a document.
*
* NOTE: Only works with tidy for PHP 5, please see urlgrab.php for tidy for PHP 4.3.x
*
* By: John Coggeshall <john@php.net>
*
* Usage: php urlgrab5.php <file>
*
*/
function dump_nodes(tidyNode $node, &$urls = NULL) {
$urls = (is_array($urls)) ? $urls : array();
if(isset($node->id)) {
if($node->id == TIDY_TAG_A) {
$urls[] = $node->attribute['href'];
}
}
if($node->hasChildren()) {
foreach($node->child as $c) {
dump_nodes($c, $urls);
}
}
return $urls;
}
$a = tidy_parse_file($_SERVER['argv'][1]);
$a->cleanRepair();
print_r(dump_nodes($a->html()));
?>