Mystalia Studios » php

Useful HTMLParse Class for PHP

Mystalia — Sat, 11 Apr 2009 02:43:52 +0000

class HTMLParse
{
// the missing InnerHTML function!
function innerHTML($node){
$doc = new DOMDocument();
foreach ($node->childNodes as $child)
{
$doc->appendChild($doc->importNode($child, true));
}
$result = $doc->saveHTML();
return $result;
}
// Get the inner html of all elements inside tag from the source (input).
function GetInnerArray($tag, $input)
{
$doc = new DOMDocument();
@$doc->loadHTML($input);
$dataset = $doc->getElementsByTagName($tag);
$stringarr = array();
foreach( $dataset as $row )
{
array_push($stringarr, trim($this->innerHTML($row)));
}
return $stringarr;
}
// Get the inner html of all elements inside tag where an attribute exists with the value.
function GetInnerArrayFilter($input, $tag, $attribute, $value)
{
$doc = new DOMDocument();
@$doc->loadHTML($input);
$dataset = $doc->getElementsByTagName($tag);
$stringarr = array();
foreach( $dataset as $row )
{
if($row->getAttribute($attribute) == $value)
{
array_push($stringarr, trim($this->innerHTML($row)));
}
}
return $stringarr;
}
// Get attribute of tags.
function GetTagAttribute($input, $tag, $attribute)
{
$doc = new DOMDocument();
@$doc->loadHTML($input);
$dataset = $doc->getElementsByTagName($tag);
$stringarr = array();
foreach( $dataset as $row )
{
array_push($stringarr, $row->getAttribute($attribute));
}
return $stringarr;
}
// Get attribute of tags where the tag attrib has the value.
function GetTagAttributeFilter($input, $tag, $attribute, $qattrib, $value)
{
$doc = new DOMDocument();
@$doc->loadHTML($input);
$dataset = $doc->getElementsByTagName($tag);
$stringarr = array();
foreach( $dataset as $row )
{
if($row->getAttribute($qattrib) == $value)
{
array_push($stringarr, $row->getAttribute($attribute));
}
}
return $stringarr;
}
}
?>

Mostly written by me.

Useful PHP class for parsing HTML

Mystalia — Tue, 03 Mar 2009 03:00:51 +0000

I’m hoping this is commented well enough.

GeSHi Error: GeSHi could not find the language phplines (using path /home1/mystalia/public_html/wp-content/plugins/codecolorer/lib/geshi/) (code 2)

If you would like help with this class, please comment!
If you have an idea to improve this class, please comment!

Plain Google Results in PHP

Mystalia — Mon, 26 May 2008 03:29:21 +0000

function PlainResults($term)
{
$content = file_get_contents('http://www.google.com/search?num=100&safe=off&q=' . $term);
if ($content !== false)
{
$content = str_replace("http", "\nhttp", $content);
$content = str_replace("\"", "\n\"", $content);

$line = explode(“\n“, $content);
$i = 0;

while($line[$i] != “”)
{
$temp = trim($line[$i]);
if(substr($temp, 0, 21) !== “http://www.google.com” and substr($temp, 0, 1) !== “\”” and substr($temp, strlen($temp) – 1, 1) == “/“)
{
echo “$temp
\n“;
}
$i++;
}
}

This script will output googles directory results as just plain urls.