<?php if (! defined('BASEPATH')) exit('No direct script access allowed');
include_once("simple_html_dom.php");
class robot
{
	var $html;
	var $html_content = '';
    var $arr_att_clean = array();
	
	function robot(){
		$this->html = new simple_html_dom();
    }
    
	function Dom(){
		return $this->html;
    }
	
    function getHTML($link)
	{
        if($this->html_content==''){
            $html = file_get_html($link);
            $this->html_content = $html;    
        }else{
            $html = $this->html_content;
        }
		return $html ;	//return object
    }
	
	function getCurl($link)
	{
        //Begin connect
        $ch = curl_init($link);
        if (!$ch){
           //$this->setErr(RB_ERR_NOT_INIT_CURL);
           //$this->setErr($url);
           //return false;
        }
        // Chúng ta sẽ nhận trị trả về và nhận dưới dạng binary
        // Dó đó ta phải set 2 option như sau
		curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.6 (KHTML, like Gecko) Chrome/16.0.897.0 Safari/535.6");
		curl_setopt($ch, CURLOPT_HEADER, true);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
		//curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt");
		//curl_setopt($ch, CURLOPT_COOKIEFILE, "cookie.txt");
        curl_setopt($ch, CURLOPT_BINARYTRANSFER, 1);
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
        curl_setopt($ch, CURLOPT_FRESH_CONNECT, 1); 
        curl_setopt($ch, CURLOPT_TIMEOUT,30);
        // Nếu không set như trên, bạn sẽ không nhận được gì
        // khi curl được thực thi, tức giá trị NULL
        // run curl and save value into data
        $html = curl_exec($ch);
        // close connect
        curl_close($ch);	
        //End connect
		
		return $html ;	//return boolean
    }
	
	public function getCurlMuti($nodes)
	{
        $mh = curl_multi_init();
        for($i=0;$i<count($nodes);$i++)
        {
			$url			= $nodes[$i];
            $curl_array[$i] = curl_init($url);
			curl_setopt($curl_array[$i], CURLOPT_USERAGENT, "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.6 (KHTML, like Gecko) Chrome/16.0.897.0 Safari/535.6");
			//curl_setopt($curl_array[$i], CURLOPT_URL, $nodes[$i]);
			curl_setopt($curl_array[$i], CURLOPT_HEADER, true);
            curl_setopt($curl_array[$i], CURLOPT_RETURNTRANSFER, true);			        
            curl_setopt($curl_array[$i], CURLOPT_BINARYTRANSFER, 1);
            curl_setopt($curl_array[$i], CURLOPT_FOLLOWLOCATION, 1);
            curl_setopt($curl_array[$i], CURLOPT_FRESH_CONNECT, 1); 
            curl_setopt($curl_array[$i], CURLOPT_TIMEOUT,30);
            curl_multi_add_handle($mh, $curl_array[$i]);
        }
		
        $running = NULL;
        do {
            //usleep(10000);
            curl_multi_exec($mh,$running);
        } while($running > 0);
		
       
        for($i=0;$i<count($nodes);$i++)
        {
            $data[$i]['content'] = curl_multi_getcontent($curl_array[$i]);	
        }
       
        for($i=0;$i<count($nodes);$i++)
		{
            curl_multi_remove_handle($mh, $curl_array[$i]);
        }
        curl_multi_close($mh);     
		
        return $data;
    }
	
	public function multiRequest($data, $options = array())
	{
		// array of curl handles
		$curly = array();
		// data to be returned
		$result = array();
		
		// multi handle
		$mh = curl_multi_init();
		
		// loop through $data and create curl handles
		// then add them to the multi-handle
		foreach ($data as $id => $d) {
		
		$curly[$id] = curl_init();
		
		$url = (is_array($d) && !empty($d['url'])) ? $d['url'] : $d;
		curl_setopt($curly[$id], CURLOPT_URL,            $url);
		curl_setopt($curly[$id], CURLOPT_HEADER,         0);
		curl_setopt($curly[$id], CURLOPT_RETURNTRANSFER, 1);
		
		// post?
		if (is_array($d)) {
		  if (!empty($d['post'])) {
			curl_setopt($curly[$id], CURLOPT_POST,       1);
			curl_setopt($curly[$id], CURLOPT_POSTFIELDS, $d['post']);
		  }
		}
		
		// extra options?
		if (!empty($options)) {
		  curl_setopt_array($curly[$id], $options);
		}
		
		curl_multi_add_handle($mh, $curly[$id]);
		}
		
		// execute the handles
		$running = null;
		do {
		curl_multi_exec($mh, $running);
		} while($running > 0);
		
		
		// get content and remove handles
		foreach($curly as $id => $c) {
		$result[$id] = curl_multi_getcontent($c);
		curl_multi_remove_handle($mh, $c);
		}
		
		// all done
		curl_multi_close($mh);
		
		return $result;
	}
	//*******************************************
	
	function getBlock($content, $rule)
	{
        $this->html->load($content);
		$arr = array();
		foreach($this->html->find($rule) as $e)
    		array_push($arr, $e->innertext);
        return $arr;
    }
	
	function getNodes($content, $rule, $num=-1)
	{
        $this->html->load($content);
		$arr = array();
		if($num==-1)
			foreach($this->html->find($rule) as $e)
				array_push($arr, $e->innertext);
		else
			foreach($this->html->find($rule,$num) as $e)
				array_push($arr, $e->innertext);
        return $arr;
    }
	
	function getLink($content, $rule, $num=-1)
	{
        $this->html->load($content);
		$arr = array();
		if($num==-1)
			foreach($this->html->find($rule) as $e)
				array_push($arr, $e->href);
		else
			foreach($this->html->find($rule,$num) as $e)
				array_push($arr, $e->href);
        return $arr;
    }
    
	
    function removeLink($content)
	{
        $html = str_get_html($content);
        // link content
        foreach($html->find('a') as $e){
            $e->outertext = $e->innertext;
        }
        $ret = $html->save();
        return $ret;
    }
    
    function removeLastElement($content, $element)
	{
        $html = str_get_html($content);
        // link content
        $html->find($element, -1)->outertext = '';
        $ret = $html->save();
        return $ret;
    }
    
    function removeFirstElement($content, $element)
	{
        $html = str_get_html($content);        
        $html->find($element, 0)->outertext = '';
        $ret = $html->save();
        return $ret;
    }
}
?>