3v4l.org

run code in 300+ PHP versions simultaneously

@ 2015-10-10T14:54:55Z

<?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);
        }
    }
}
?>

Output for git.master, git.master_jit, rfc.property-hooks: Warning: file_get_contents(): php_network_getaddresses: getaddrinfo for www.farsnews.com failed: System error in /in/ekWpF on line 84 Warning: file_get_contents(http://www.farsnews.com/economy/agriculture): Failed to open stream: php_network_getaddresses: getaddrinfo for www.farsnews.com failed: System error in /in/ekWpF on line 84 Fatal error: Uncaught ValueError: DOMDocument::loadHTML(): Argument #1 ($source) must not be empty in /in/ekWpF:38 Stack trace: #0 /in/ekWpF(38): DOMDocument->loadHTML('') #1 /in/ekWpF(8): DOMScraper->getInnerHTML('div', 'class=ctgnewsma...') #2 {main} thrown in /in/ekWpF on line 38
Process exited with code 255.

This tab shows result from various feature-branches currently under review by the php developers. Contact me to have additional branches featured.

Active branches

Archived branches

Once feature-branches are merged or declined, they are no longer available. Their functionality (when merged) can be viewed from the main output page

2020-03-21 RFC: Is_Literal - declined
2020-12-04 Enumerations - included in PHP 8.1
2018-06-15 Typed Properties v2 - implemented in PHP 7.4
2016-08-12 Object typehint - included in PHP 7.2
2016-08-14 Arrow functions - withdrawn
2016-05-29 array_change_keys() - withdrawn
2016-04-19 Lexical scope support for anonymous classes - suspended
2016-04-17 Functional Interfaces - declined
2016-03-16 Typed Properties - superseded in favor of Typed Properties 2.0
2015-08-27 Callable Prototypes - declined
2015-05-01 Short Closures - declined / withdrawn in favor of Arrow Functions
2015-02-18 Scalar type hints v5 - included in PHP 7
2015-02-14 Union Types - declined
2013-09-22 Anonymous classes - included in PHP 7

preferences:dark modelive preview

49.9 ms | 402 KiB | 8 Q