mkdir php_scraper
cd php_scraper

composer init — require=”php >=7.4" --no-interaction
composer update

composer require guzzlehttp/guzzle

<?php#
scraping books to scrape: https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \GuzzleHttp\Client();
$response = $httpClient->get(‘https://books.toscrape.com/');
$htmlString = (string) $response->getBody();
//add this line to suppress any warnings
libxml_use_internal_errors(true);
$doc = new DOMDocument();
$doc->loadHTML($htmlString);
$xpath = new DOMXPath($doc);

$titles = $xpath->evaluate(‘//ol[@class="row"]//li//article//h3/a’);
$extractedTitles = [];
foreach ($titles as $title) {
$extractedTitles[] = $title->textContent.PHP_EOL;
echo $title->textContent.PHP_EOL;
}

php guzzle_requests.php

$titles = $xpath->evaluate(‘//ol[@class=”row”]//li//article//h3/a’);
$prices = $xpath->evaluate(‘//ol[@class=”row”]//li//article//div[@class=”product_price”]//p[@class=”price_color”]’);
foreach ($titles as $key => $title) {
echo $title->textContent . ‘ @ ‘. $prices[$key]->textContent.PHP_EOL;
}

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \GuzzleHttp\Client();
$response = $httpClient->get(‘https://books.toscrape.com/');
$htmlString = (string) $response->getBody();
//add this line to suppress any warnings
libxml_use_internal_errors(true);
$doc = new DOMDocument();
$doc->loadHTML($htmlString);
$xpath = new DOMXPath($doc);
$titles = $xpath->evaluate(‘//ol[@class=”row”]//li//article//h3/a’);
$prices = $xpath->evaluate(‘//ol[@class=”row”]//li//article//div[@class=”product_price”]//p[@class=”price_color”]’);
foreach ($titles as $key => $title) {
echo $title->textContent . ‘ @ ‘. $prices[$key]->textContent.PHP_EOL;
}

composer require fabpot/goutte

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \Goutte\Client();
$response = $httpClient->request(‘GET’, ‘https://books.toscrape.com/');
$titles = $response->evaluate(‘//ol[@class=”row”]//li//article//h3/a’);
$prices = $response->evaluate(‘//ol[@class=”row”]//li//article//div[@class=”product_price”]//p[@class=”price_color”]’);
// we can store the prices into an array
$priceArray = [];
foreach ($prices as $key => $price) {
$priceArray[] = $price->textContent;
}
// we extract the titles and display to the terminal together with the prices
foreach ($titles as $key => $title) {
echo $title->textContent . ‘ @ ‘. $priceArray[$key] . PHP_EOL;
}

php goutte_requests.php

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \Goutte\Client();
$response = $httpClient->request(‘GET’, ‘https://books.toscrape.com/');
// get prices into an array
$prices = [];
$response->filter(‘.row li article div.product_price p.price_color’)->each(function ($node) use (&$prices) {
$prices[] = $node->text();
});
// echo titles and prices
$priceIndex = 0;
$response->filter(‘.row li article h3 a’)->each(function ($node) use ($prices, &$priceIndex) {
echo $node->text() . ‘ @ ‘ . $prices[$priceIndex] .PHP_EOL;
$priceIndex++;
});

php goutte_css_requests.php

composer require masterminds/html5

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \Goutte\Client();
$response = $httpClient->request(‘GET’, ‘https://books.toscrape.com/');
// get prices into an array
$prices = [];
$response->filter(‘.row li article div.product_price p.price_color’)
->each(function ($node) use (&$prices) {
$prices[] = $node->text();
});
// echo title, price, and description
$priceIndex = 0;
$response->filter(‘.row li article h3 a’)
->each(function ($node) use ($prices, &$priceIndex, $httpClient) {
$title = $node->text();
$price = $prices[$priceIndex];
//getting the description
$description = $httpClient->click($node->link())
->filter(‘.content #content_inner article p’)->eq(3)->text();
// display the result
echo “{$title} @ {$price} : {$description}\n\n”;
$priceIndex++;
});

“minimum-stability”: “dev”,
“prefer-stable”: true

composer require simplehtmldom/simplehtmldom

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = new \simplehtmldom\HtmlWeb();
$response = $httpClient->load(‘https://books.toscrape.com/');
// echo the title
echo $response->find(‘title’, 0)->plaintext . PHP_EOL . PHP_EOL;
// get the prices into an array
$prices = [];
foreach ($response->find(‘.row li article div.product_price p.price_color’) as $price) {
$prices[] = $price->plaintext;
}
// echo titles and prices
foreach ($response->find(‘.row li article h3 a’) as $key => $title) {
echo “{$title->plaintext} @ {$prices[$key]} \n”;
}

composer require symfony/panther

<?php
# scraping books to scrape:https://books.toscrape.com/
require ‘vendor/autoload.php’;
$httpClient = \Symfony\Component\Panther\Client::createChromeClient();
// for a Firefox client use the line below instead
//$httpClient = \Symfony\Component\Panther\Client::createFirefoxClient();
// get response
$response = $httpClient->get(‘https://books.toscrape.com/');
// take screenshot and store in current directory
$response->takeScreenshot($saveAs = ‘books_scrape_homepage.jpg’);
// let’s display some book titles
$response->getCrawler()->filter(‘.row li article h3 a’)
->each(function ($node) {
echo $node->text() . PHP_EOL;
});

composer require --dev dbrekelmans/bdi && vendor/bin/bdi detect drivers