| / retrieve doctype of document
function get_doctype($file){
$h1tags = preg_match(‘/<!DOCTYPE (\w.*)dtd”>/is’,$file,$patterns);
$res = array();
array_push($res,$patterns[0]);
array_push($res,count($patterns[0]));
return $res;
}
// retrieve page title
function get_doc_title($file){
$h1tags = preg_match(‘/<title> ?.* <\/title>/isx’,$file,$patterns);
$res = array();
array_push($res,$patterns[0]);
array_push($res,count($patterns[0]));
return $res;
}
// retrieve keywords
function get_keywords($file){
$h1tags = preg_match(‘/(<meta name=”keywords” content=”(.*)” \/>)/i’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// get rel links in header of the site
function get_link_rel($file){
$h1tags = preg_match_all(‘/(rel=)(”.*”) href=(”.*”)/im’,$file,$patterns);
$res = array();
array_push($res,$patterns);
array_push($res,count($patterns[2]));
return $res;
}
function get_external_css($file){
$h1tags = preg_match_all(‘/(href=”)(\w.*\.css)”/i’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h1 tags
function get_h1($file){
$h1tags = preg_match_all(“/(<h1.*>)(\w.*)(<\/h1>)/isxmU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h2 tags
function get_h2($file){
$h1tags = preg_match_all(“/(<h2.*>)(\w.*)(<\/h2>)/isxmU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h3 tags
function get_h3($file){
$h1tags = preg_match_all(“/(<h3.*>)(\w.*)(<\/h3>)/ismU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h4 tags
function get_h4($file){
$h1tags = preg_match_all(“/(<h4.*>)(\w.*)(<\/h4>)/ismU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h5 tags
function get_h5($file){
$h1tags = preg_match_all(“/(<h5.*>)(\w.*)(<\/h5>)/ismU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all h5 tags
function get_h6($file){
$h1tags = preg_match_all(“/(<h6.*>)(\w.*)(<\/h6>)/ismU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve p tag contents
function get_p($file){
$h1tags = preg_match_all(“/(<p.*>)(\w.*)(<\/p>)/ismU”,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve names of links
function get_a_content($file){
$h1count = preg_match_all(“/(<a.*>)(\w.*)(<.*>)/ismU”,$file,$patterns);
return $patterns[2];
}
// retrieve link destinations
function get_a_href($file){
$h1count = preg_match_all(‘/(href=”)(.*?)(”)/i’,$file,$patterns);
return $patterns[2];
}
// get count of href’s
function get_a_href_count($file){
$h1count = preg_match_all(‘/<(a.*) href=\”(.*?)\”(.*)<\/a>/’,$file,$patterns);
return count($patterns[0]);
}
//get all additional tags inside a link tag
function get_a_additionaltags($file){
$h1count = preg_match_all(‘/<(a.*) href=”(.*?)”(.*)>(.*)(<\/a>)/’,$file,$patterns);
return $patterns[3];
}
// retrieve span’s
function get_span($file){
$h1count = preg_match_all(‘/(<span .*>)(.*)(<\/span>)/’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve spans on the site
function get_script($file){
$h1count = preg_match_all(‘/(<script.*>)(.*)(<\/script>)/imxsU’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve content of ul’s
function get_ul($file){
$h1count = preg_match_all(‘/(<ul \w*>)(.*)(<\/ul>)/ismxU’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
//retrieve li contents
function get_li($file){
$h1count = preg_match_all(‘/(<li \w*>)(.*)(<\/li>)/ismxU’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve page comments
function get_comments($file){
$h1count = preg_match_all(‘/(<!–).(.*)(–>)/isU’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all used id’s on the page
function get_ids($file){
$h1count = preg_match_all(‘/(id=”(\w*)”)/is’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve all used classes ( inline ) of the document
function get_classes($file){
$h1count = preg_match_all(‘/(class=”(\w*)”)/is’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// get the meta tag contents
function get_meta_content($file){
$h1count = preg_match_all(‘/(<meta)(.*=”(.*)”).\/>/ix’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// get inline styles
function get_styles($file){
$h1count = preg_match_all(‘/(style=”)(.*?)(”)/is’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// get titles of tags
function get_tag_titles($file){
$h1count = preg_match_all(‘/(title=)”(.*)”(.*)/’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// get image alt descriptions
function get_image_alt($file){
$h1count = preg_match_all(‘/(alt=.)([a-zA-Z0-9\s]{1,})/’,$file,$patterns);
$res = array();
array_push($res,$patterns[2]);
array_push($res,count($patterns[2]));
return $res;
}
// retrieve images on the site
function get_images($file){
$h1count = preg_match_all(‘/(<img)\s (src=”([a-zA-Z0-9\.;:\/\?&=_|\r|\n]{1,})”)/isxmU’,$file,$patterns);
$res = array();
array_push($res,$patterns[3]);
array_push($res,count($patterns[3]));
return $res;
}
// retrieve email address of the mailto tag if any
function get_mailto($file){
$h1count = preg_match_all(‘/(<a\shref=”)(mailto:)([a-zA-Z@0-9\.]{1,})”/ims’,$file,$patterns);
$res = array();
array_push($res,$patterns[3]);
array_push($res,count($patterns[3]));
return $res;
}
// retrieve any email
function get_emails($file){
$h1count = preg_match_all(‘/[a-zA-Z0-9_-]{1,}@[a-zA-Z0-9-_]{1,}\.[a-zA-Z]{1,4}/’,$file,$patterns);
$res = array();
array_push($res,$patterns[0]);
array_push($res,count($patterns[0]));
return $res;
}
// count used keywords
function countkeyword($word,$file){
$x = preg_match_all(“/(.*)($word)(.*)/”,$file,$patterns);
return count($patterns);
}
// retrieve internal site links
function get_internal_links($array){
$result = array();
$count = count($array);
for($i=0;$i<$count;$i++){
if(!empty($array[$i])){
if(strpos($array[$i],“www”,0) === false){
if(strpos($array[$i],“http”,0) === false){
array_push($result,$array[$i]);
}
}
}
}
return $result;
}
// retrieve external links
function get_external_links($array){
$result = array();
$count = count($array);
for($i=0;$i<$count;$i++){
if(!empty($array[$i])){
if(strpos($array[$i],“www”,0) !== false){
if(strpos($array[$i],“http”,0) !== false){
array_push($result,$array[$i]);
}
}
}
}
return $result;
}
// retrieve the main url of the site
function get_main_url($url){
$parts = parse_url($url);
$url = $parts["scheme"] .“://”.$parts["host"];
return $url;
}
// retrieve just the name without www and com/eu/de etc
function get_domain_name_only($url){
$match = preg_match(“/(.*:\/\/)\w{0,}(.*)\.(.*)/”,$url,$patterns);
$patterns[2] = str_replace(“.”,“”,$patterns[2]);
return $patterns[2];
}
?>
Usage Example
|
|
<!DOCTYPE html PUBLIC “-//W3C//DTD XHTML 1.0 Transitional//EN” “http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd”>
<html xmlns=”http://www.w3.org/1999/xhtml”>
<head>
<meta http-equiv=”Content-Type” content=”text/html; charset=utf-8″ />
<title>Untitled Document</title>
<style type=”text/css”>
<!–
body {
font: 11px Arial, Helvetica, sans-serif;
}
.info {
color: #99CC00;
font-weight: bold;
}
.notice {
color: #FF66CC;
}
.error {
color: #990000;
font-weight: bold;
}
–>
</style>
</head>
<body><form action=”" method=”post” enctype=”application/x-www-form-urlencoded” name=”form1″>
<input name=”url” type=”text” /><input name=”submit” type=”submit” value=”submit” /></form>
<?php if(isset($_POST['submit']) && $_POST['submit'] == “submit”){
$resultArray = array();
$url = htmlentities(strip_tags($_POST['url']));
include(“tagretrieval.php”);
if(strpos($url,“http”,0) === false){
$url = “http://$url”;
}
echo “<img src=\”http://www.artviper.net/screenshots/screener.php?url=$url&h=180&w=240&sdx=1024&sdy=768\” alt=\”$url\” style=\”margin:20px\” />”;
$file = file_get_contents($url);
$doctype = get_doctype($file);
$keywords = get_keywords($file);
$css = get_external_css($file);
$h1 = get_h1($file);
$h2 = get_h2($file);
$h3 = get_h3($file);
$p = get_p($file);
$title = get_doc_title($file);
$links = get_a_href($file);
$href_add = get_a_additionaltags($file);
$images = get_images($file);
$styles = get_styles($file);
$ids = get_ids($file);
$classes = get_classes($file);
echo“<h1>Document properties</h1>”;
// get doctype
if(!empty($doctype[0])){
$doctype = preg_replace(“/</”,‘<’,$doctype[0]);
echo “<br/>Valid doctype: $doctype”;
}else{
$doctype = “<br/>No doctype specified<br/>”;
echo $doctype;
}
// get doc title
if(!empty($title[0])){
$title[0] = preg_replace(“/</”,“<”,$title[0]);
echo “<br/>Title found: $title[0]<”;
}else{
echo“<br/><div class=\”error\”>Page does not have a title</div><br/>”;
}
// get external references CSS files
// get h1 tags
if($css[1] != 0){
echo “<br/>external CSS found: $css[1]<ul>”;
foreach($css[0] as $key => $val){
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No external CSS found</div><br/>”;
}
// get keywords
if(!empty($keywords[0])){
echo“<br/>Keywords found: $keywords[0]“;
}else{
echo “<br/><div class=\”error\”>No keywords specified</div><br/>”;
}
echo“<h1>Content properties</h1>”;
// get h1 tags
if($h1[1] != 0){
echo “<br/>H1 Tags found: $h1[1]<ul>”;
foreach($h1[0] as $key => $val){
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No H1 Tags found</div><br/>”;
}
// get h2 tags
if($h2[1] != 0){
echo “<br/>H2 Tags found: $h2[1]<ul>”;
foreach($h2[0] as $key => $val){
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No H2 Tags found</div><br/>”;
}
// get h3 tags
if($h3[1] != 0){
echo “<br/>H3 Tags found: $h3[1]<ul>”;
foreach($h3[0] as $key => $val){
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No H3 Tags found</div><br/>”;
}
// get p tags
if($p[1] != 0){
echo “<br/>p Tags found: $p[1]<ul>”;
foreach($p[0] as $key => $val){
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No p Tags found</div><br/>”;
}
echo “<h1>Link structure</h1>”;
if(!empty($links[0])){
echo “<br/>Links found:<ul>”;
foreach($links as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No Links found</div><br/>”;
}
if(!empty($href_add[0])){
echo “<br/>href additional tags:<ul>”;
foreach($href_add as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/><div class=\”error\”>No additional styles for href found</div><br/>”;
}
echo “<h1>Images</h1>”;
if(!empty($images[0])){
echo “<br/>images:<ul>”;
foreach($images[0] as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/>No images found”;
}
echo “<h1>Styles, ID’s & Classes</h1>”;
if(!empty($ids[0])){
echo “<br/>ID’s:<ul>”;
foreach($ids[0] as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/>No ID’s found<br/>”;
}
if(!empty($classes[0])){
echo “<br/>classes:<ul>”;
foreach($classes[0] as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “</ul>”;
}else{
echo “<br/>No classes found<br/>”;
}
if(!empty($styles[0])){
echo “<br/>inline styles:<ul>”;
foreach($styles[0] as $key => $val){
$val = preg_replace(“/</”,“<”,$val);
echo “<li>” . htmlentities($val) . “</li>”;
}
echo “<div class=\”notice\”>Your document uses inline styles. If applicable, try to put them into a separate CSS file and restyle them to ID’s or CLASSES.</div></ul>”;
}else{
echo “<br/>No inline styles used”;
}
}
?>
</body>
</html> |
|
