PHP code example of webscraping-ai / webscraping-ai-php

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

webscraping-ai / webscraping-ai-php example snippets

use WebScrapingAI\Client;

$client = new Client(apiKey: getenv('WEBSCRAPING_AI_KEY'));

// Full HTML
$html = $client->html(url: 'https://example.com');

// Visible text
$text = $client->text(url: 'https://example.com');

// HTML for one selector
$h1 = $client->selected(url: 'https://example.com', selector: 'h1');

// HTML for multiple selectors (returns array)
$chunks = $client->selectedMultiple(
    url: 'https://example.com',
    selectors: ['h1', 'p', 'a'],
);

// LLM question over a page
$answer = $client->question(
    url: 'https://example.com',
    question: 'What is the main topic?',
);

// LLM-extracted structured fields
$fields = $client->fields(
    url: 'https://example.com',
    fields: [
        'title' => 'Main product title',
        'price' => 'Current price',
    ],
);

// Structured data for a page on a supported site (YouTube, TikTok, X, ...)
$video = $client->data(url: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ');

// Account quota
$account = $client->account();

$serp = $client->serp(q: 'coffee machines', gl: 'us', hl: 'en', page: 1);

foreach ($serp['organic_results'] as $result) {
    printf("%d. %s — %s\n", $result['position'], $result['title'], $result['link']);
}

$nextPage = $serp['pagination']['next'] ?? null; // absent on the last page

use WebScrapingAI\Exception\BadRequestException;

$result = $client->data(url: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ', transcript: true);

if ($result['parse_status'] === 'ok') {
    echo $result['request_parameters']['provider'], ': ', $result['data']['title'], "\n";
}

try {
    $client->data(url: 'https://example.com/');
} catch (BadRequestException $e) {
    echo $e->getMessage(); // "Unsupported URL for /data. ..." — lists what is supported
}

$client->data(url: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ', params: ['some_new_option' => 'value']);

use GuzzleHttp\Client as Guzzle;
use Nyholm\Psr7\Factory\Psr17Factory;
use WebScrapingAI\Client;

$factory = new Psr17Factory();
$client = new Client(
    apiKey: getenv('WEBSCRAPING_AI_KEY'),
    httpClient: new Guzzle(['timeout' => 30.0]),
    requestFactory: $factory,
    uriFactory: $factory,
);

$client = new Client(
    apiKey: getenv('WEBSCRAPING_AI_KEY'),
    timeout: 120.0,        // total request deadline, seconds
    connectTimeout: 5.0,   // TCP connect deadline, seconds
);