Get Inner HTML - PHP - php

Question

I have the following code:
$data = file_get_contents('http://www.robotevents.com/robot-competitions/vex-robotics-competition?limit=all');
echo "Downloaded";
$dom = new domDocument;
#$dom->loadHTML($data);
$dom->preserveWhiteSpace = false;
$tables = $dom->getElementsByTagName('table');
$rows = $tables->item(2)->getElementsByTagName('tr');
foreach ($rows as $row) {
$cols = $row->getElementsByTagName('td');
for ($i = 0; $i < $cols->length; $i++) {
echo $cols->item($i)->nodeValue . "\n";
}
}
The final field has an Link which I need to store the URL of. Also, The script outputs characters such as "Â". Does anyone know how to do/fix these things?

Answer 1

I would recommend not using DOM to parse HTML, as it has problems with invalid HTML. INstead use regular expression
I use this class:
<?php
/**
* Class to return HTML elements from a HTML document
* #version 0.3.1
*/
class HTMLQuery
{
protected $selfClosingTags = array( 'area', 'base', 'br', 'hr', 'img', 'input', 'link', 'meta', 'param' );
private $html;
function __construct( $html = false )
{
if( $html !== false )
$this->load( $html );
}
/**
* Load a HTML string
*/
public function load( $html )
{
$this->html = $html;
}
/**
* Returns elements from the HTML
*/
public function getElements( $element, $attribute_match = false, $value_match = false )
{
if( in_array( $element, $this->selfClosingTags ) )
preg_match_all( "/<$element *(.*)*\/>/isU", $this->html, $matches );
else
preg_match_all( "/<$element(.*)>(.*)<\/$element>/isU", $this->html, $matches );
if( $matches )
{
#Create an array of matched elements with attributes and content
foreach( $matches[0] as $key => $el )
{
$current_el = array( 'name' => $element );
$attributes = $this->parseAttributes( $matches[1][$key] );
if( $attributes )
$current_el['attributes'] = $attributes;
if( $matches[2][$key] )
$current_el['content'] = $matches[2][$key];
$elements[] = $current_el;
}
#Return only elements with a specific attribute and or value if specified
if( $attribute_match != false && $elements )
{
foreach( $elements as $el_key => $current_el )
{
if( $current_el['attributes'] )
{
foreach( $current_el['attributes'] as $att_name => $att_value )
{
$keep = false;
if( $att_name == $attribute_match )
{
$keep = true;
if( $value_match == false )
break;
}
if( $value_match && ( $att_value == $value_match ) )
{
$keep = true;
break;
}
elseif( $value_match && ( $att_value != $value_match ) )
$keep = false;
}
if( $keep == false )
unset( $elements[$el_key] );
}
else
unset( $elements[$el_key] );
}
}
}
if( $elements )
return array_values( $elements );
else
return array();
}
/**
* Return an associateive array of all the form inputs
*/
public function getFormValues()
{
$inputs = $this->getElements( 'input' );
$textareas = $this->getElements( 'textarea' );
$buttons = $this->getElements( 'button' );
$elements = array_merge( $inputs, $textareas, $buttons );
if( $elements )
{
foreach( $elements as $current_el )
{
$attribute_name = mb_strtolower( $current_el['attributes']['name'] );
if( in_array( $current_el['name'], array( 'input', 'button' ) ) )
{
if( isset( $current_el['attributes']['name'] ) && isset( $current_el['attributes']['value'] ) )
$form_values[$attribute_name] = $current_el['attributes']['value'];
}
else
{
if( isset( $current_el['attributes']['name'] ) && isset( $current_el['content'] ) )
$form_values[$attribute_name] = $current_el['content'];
}
}
}
return $form_values;
}
/**
* Parses attributes into an array
*/
private function parseAttributes( $str )
{
$str = trim( rtrim( trim( $str ), '/' ) );
if( $str )
{
preg_match_all( "/([^ =]+)\s*=\s*[\"'“”]{0,1}([^\"'“”]*)[\"'“”]{0,1}/i", $str, $matches );
if( $matches[1] )
{
foreach( $matches[1] as $key => $att )
{
$attribute_name = mb_strtolower( $att );
$attributes[$attribute_name] = $matches[2][$key];
}
}
}
return $attributes;
}
}
?>
Usage is:
$c = new HTMLQuery();
$x = $c->getElements( 'tr' );
print_r( $x );