Tonel

<?
curl_setopt($curl, CURLOPT_HTTPHEADER, 
	array( 
		"<HTTP_HEADER_1>: <HEADER_VALUE>", 
		"<HTTP_HEADER_2>: <HEADER_VALUE>", 
		// ... 
	) 
);

Tonel

<?
curl_setopt($curl, CURLOPT_USERAGENT, "<USER_AGENT_STRING>");

Tonel

[ 
	{ 
		"url": "https://scrapeme.live/shop/Bulbasaur/", 
		"image": "https://scrapeme.live/wp-content/uploads/2018/08/001-350x350.png", 
		"name": "Bulbasaur", 
		"price": "£63.00" 
	}, 
 
	... 
 

Tonel

<?
// iterate over all "/shop/page/X" pages and retrieve all product data 
for ($paginationNumber = 1; $paginationNumber <= $highestPaginationNumber; $paginationNumber++) { 
	$curl = curl_init(); 
	curl_setopt($curl, CURLOPT_URL, "https://scrapeme.live/shop/page/$paginationNumber/"); 
	curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); 
	$pageHtml = curl_exec($curl); 
	curl_close($curl); 
 
	$paginationHtmlDomParser = HtmlDomParser::str_get_html($pageHtml); 

Tonel

<?
$productDataLit = array(); 
 
// retrieve the list of products on the page 
$productElements = $htmlDomParser->find("li.product"); 
foreach ($productElements as $productElement) { 
	// extract the product data 
	$url = $productElement->findOne("a")->getAttribute("href"); 
	$image = $productElement->findOne("img")->getAttribute("src"); 
	$name = $productElement->findOne("h2")->text; 

Tonel

<?
// remove all non-numeric characters in the last element of 
// the $paginationLinks array to retrieve the highest pagination number 
$highestPaginationNumber = preg_replace("/\D/", "", end($paginationLinks));

Tonel

<?
// retrieve the HTML pagination elements with 
// the ".page-numbers a" CSS selector 
$paginationElements = $htmlDomParser->find(".page-numbers a"); 
$paginationLinks = []; 
foreach ($paginationElements as $paginationElement) { 
	// populate the paginationLinks set with the URL 
	// extracted from the href attribute of the HTML pagination element 
	$paginationLink = $paginationElement->getAttribute("href"); 
	// avoid duplicates in the list of URLs 

Tonel

<?
require_once __DIR__ . "/../../vendor/autoload.php"; 
 
use voku\helper\HtmlDomParser; 
 
$curl = curl_init(); 
curl_setopt($curl, CURLOPT_URL, "https://scrapeme.live/shop/"); 
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); 
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); 
$html = curl_exec($curl); 

Tonel

<?
// initialize the cURL request 
$curl = curl_init(); 
// set the URL to reach with a GET HTTP request 
curl_setopt($curl, CURLOPT_URL, "https://scrapeme.live/shop/"); 
// get the data returned by the cURL request as a string 
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); 
// make the cURL request follow eventual redirects, 
// and reach the final page of interest 
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); 

Tonel

{
  "name": "Maria",
  "surname": "Williams",
  "age": 35
}