<?php
$scraper = new DOMScraper();
//example couldent think of a site with an example table
$scraper->setSite('http://www.farsnews.com/economy/agriculture')->setSource();
//get only tables with id="some_table_id" or any attribute match eg class="somthing"
echo '<div>'.$scraper->getInnerHTML('div','class=ctgnewsmainpane').'</div>';
/**
* Generic DOM scapper using DOMDocument and cURL
*/
Class DOMScraper extends DOMDocument{
public $site;
private $source;
private $dom;
function __construct(){
libxml_use_internal_errors(true);
$this->preserveWhiteSpace = false;
$this->strictErrorChecking = false;
}
function setSite($site){
$this->site = $site;
return $this;
}
function setSource(){
if(empty($this->site))return 'Error: Missing $this->site, use setSite() first';
$this->source = $this->get_data($this->site);
return $this;
}
function getInnerHTML($tag, $class=null, $nodeValue = false){
if(empty($this->site))return 'Error: Missing $this->source, use setSource() first';
$this->loadHTML($this->source);
$tmp = $this->getElementsByTagName($tag);
$ret = null;
foreach ($tmp as $v){
if($class !== null){
$attr = explode('=',$class);
if($v->getAttribute($attr[0])==$attr[1]){
if($nodeValue == true){
$ret .= trim($v->nodeValue);
}else{
$ret .= $this->innerHTML($v);
}
}
}else{
if($nodeValue == true){
$ret .= trim($v->nodeValue);
}else{
$ret .= $this->innerHTML($v);
}
}
}
return $ret;
}
function innerHTML($dom){
$ret = "";
$nodes = $dom->childNodes;
foreach($nodes as $v){
$tmp = new DOMDocument();
$tmp->appendChild($tmp->importNode($v, true));
$ret .= trim($tmp->saveHTML());
}
return $ret;
}
function get_data($url){
if(function_exists('curl_init')){
$ch = curl_init();
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$data = curl_exec($ch);
curl_close($ch);
return $data;
}else{
return file_get_contents($url);
}
}
}
?>
preferences:
74.59 ms | 402 KiB | 5 Q