Data Scraping - Read data from another website.

website-content-reader.php

<?php
class WebContentReader{
public $global_url;
function __construct(){
$this->global_url = array();
// Create connection
 $con=mysqli_connect("localhost","root","","dbname");
 if (mysqli_connect_errno($con))
 {
  echo "Failed to connect to MySQL: " . mysqli_connect_error();
 }
$url = "site url.)";
 $page_contents = $this->getWebPage( $url );
 print "page URL-----".$url."<br><br>";
 if ( $page_contents['errno'] != 0 ){
  print    "error: bad url, timeout, redirect loop ...";
 }
 if ( $page_contents['http_code'] != 200 ){
  print   "error: no page, no permissions, no service ...";
 }
 /**
 * LIMIT for Execute URL
 **/
 $contents = $page_contents['content'];
 $dom = new DOMDocument;
 @$dom->loadHTML($contents);
 $xpath = new DomXPath($dom);
 // $elements = $xpath->query("//ul[@class='cat-list']/li/ul[@class='subcat-list']/ul[@class='subcat-list']/li/a");
 $elements = $xpath->query("element path");
 if (!is_null($elements)) {
 $count = 0;
  foreach ($elements as $element) {
     $product_url = $element->getAttribute('href');
	if($product_url != '#' && (!in_array($product_url,$this->global_url ))){
	   $this->readDataFromUrl($product_url, $con);
	 }
	 array_push($this->global_url , $product_list_url);
	$count++;
  }

}
$con->close();
}
/**
 clean strin special charactors
**/
function clean($string) {
   $string = str_replace('', '-', $string); // Replaces all spaces with hyphens.
   return preg_replace('/[^A-Za-z0-9\-]/', '', $string); // Removes special chars.
}
 /**
Get a web file
**/
function getWebPage( $url )
{
    $options = array(
        CURLOPT_RETURNTRANSFER => true,     // return web page
        CURLOPT_HEADER         => false,    // don't return headers
        CURLOPT_FOLLOWLOCATION => true,     // follow redirects
        CURLOPT_ENCODING       => "",       // handle all encodings
        CURLOPT_USERAGENT      => "spider", // who am i
        CURLOPT_AUTOREFERER    => true,     // set referer on redirect
        CURLOPT_CONNECTTIMEOUT => 240,      // timeout on connect
        CURLOPT_TIMEOUT        => 240,      // timeout on response
        CURLOPT_MAXREDIRS      => 10,       // stop after 10 redirects
    );

    $ch      = curl_init( $url );
    curl_setopt_array( $ch, $options );
    $content = curl_exec( $ch );
    $err     = curl_errno( $ch );
    $errmsg  = curl_error( $ch );
    $header  = curl_getinfo( $ch );
    curl_close( $ch );

    $header['errno']   = $err;
    $header['errmsg']  = $errmsg;
    $header['content'] = $content;
    return $header;
}


/**
 read data from URL page
**/
function readDataFromUrl( $url, $con){
 $page_contents = $this->getWebPage( $url );
 // print "prodcut URL-----".$url."<br><br>";
 if ( $page_contents['errno'] != 0 ){
  print    "error: bad url, timeout, redirect loop ...";
 }
 if ( $page_contents['http_code'] != 200 ){
  print   "error: no page, no permissions, no service ...";
 }
 $contents = $page_contents['content'];
 $dom = new DOMDocument;
 @$dom->loadHTML($contents);
 $xpath = new DomXPath($dom);
 /**
 read image from anchor tag with class name called picture-link.
 **/
 $image_500 = "";
 $elements = $xpath->query("//a[@class='picture-link']");
 if (!is_null($elements)) {
  foreach ($elements as $element) {
	$image_500 = $element->getAttribute('href');
  }
  // print "<br>Enlarged image url is---".$image_500."<br>";
 }
 /**
  read image from img tag 
 **/
 $elements = $xpath->query("//a[@class='picture-link']/img");
 $image_200 = "";
 if (!is_null($elements)) {
  foreach ($elements as $element) {
   $image_200 = $element->getAttribute('src');
  }
  // print "<br>image_200 url is---".$image_200."<br>";
 }
 /**
 read product name 
 **/
 $elements = $xpath->query('//table[@id="product-attribute-specs-table"]//h3[@itemprop="name"]');
 $product_name = "";
 if (!is_null($elements)) {
  foreach ($elements as $element) {
   $product_name = $element->nodeValue;
   // print "<br>product_name  is---".$product_name."<br>";
  }
 }
 /**
 read  product_description 
 **/
 $product_description = "";
 $elements = $xpath->query('//h2[@itemprop="description"]');
 if (!is_null($elements)) {
  foreach ($elements as $element) {
   $product_description = $element->nodeValue;
   // print "<br>product_name  is---".$product_description."<br>";
  }
 }
 $specification_array = array();
 for($i=0; $i<count($specification_data_array);$i++){
 $specification_array[$specification_label_array[$i]] = $specification_data_array[$i];
 }
 
}

}
$obj = new WebContentReader();
?>