PHP/HTML/tidy parse file

Beautifying HTML Using Tidy

   <source lang="html4strict">

<?php

     $options = array("indent" => true,       
                      "indent-spaces" => 4,   
                      "wrap" => 4096);        
     $tidy = tidy_parse_file("http://www.php.net/", $options);
     tidy_clean_repair($tidy);
     echo $tidy;

?>

 </source>
   
  

Extracting URLs Using Tidy

   <source lang="html4strict">

<?php

     function dump_urls(tidy_node $node, &$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 $child) {
                       dump_urls($child, $urls);
                 }
           }
                      return $urls;
     }
     $tidy = tidy_parse_file("http://www.php.net/");
     $urls = dump_urls($tidy->body());
     print_r($urls);

?>

 </source>
   
  

Reducing Bandwidth Usage Using Tidy

   <source lang="html4strict">

<?php

   $options = array("clean" => true,
             "drop-proprietary-attributes" => true,
             "drop-font-tags" => true,
             "drop-empty-paras" => true,
             "hide-comments" => true,
             "join-classes" => true,
             "join-styles" => true);
   $tidy = tidy_parse_file("http://www.php.net/", $options);
   tidy_clean_repair($tidy);
   echo $tidy;

?>

 </source>
   
  

Retrieving an Entrance Node in Tidy

   <source lang="html4strict">

<?php

   $tidy = tidy_parse_file("http://www.php.net/");
   $root = $tidy->root();

?>

 </source>