Imported from /home/lorry/working-area/delta_php2/php-5.4.13.tar.bz2.HEADphp-5.4.13master

1 files changed, 39 insertions, 0 deletions

diff --git a/ext/tidy/examples/urlgrab5.php b/ext/tidy/examples/urlgrab5.php
new file mode 100644
index 0000000..875baf0
--- /dev/null
+++ b/ext/tidy/examples/urlgrab5.php
@@ -0,0 +1,39 @@
+<?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()));
+?>