UNIFIED DATA PROCESSING FRAMEWORK

composer require flow-php/etl ~0.27.0

Changelog Release Cycle

Try Flow Online

Extracts

Read from various data sources.

Transforms

Shape and optimize for your needs.

Loads

Store and secure in one of many available data sinks.

Examples:

Download

▶ ▼ composer.json

{
    "name": "flow-php/examples",
    "description": "Flow PHP - Examples",
    "license": "MIT",
    "type": "library",
    "require": {
        "php": "^8.4",
        "flow-php/etl": "1.x-dev",
        "flow-php/etl-adapter-http": "1.x-dev",
        "nyholm/psr7": "^1.8",
        "symfony/http-client": "^6.4 || ^7.4"
    },
    "minimum-stability": "dev",
    "config": {
        "allow-plugins": {
            "php-http/discovery": false
        }
    }
}

code.php

<?php

declare(strict_types=1);

use function Flow\ETL\DSL\{data_frame, ref, to_stream};
use Flow\ETL\Adapter\Http\PsrHttpClientStaticExtractor;
use Nyholm\Psr7\Factory\Psr17Factory;
use Symfony\Component\HttpClient\{MockHttpClient, Psr18Client};
use Symfony\Component\HttpClient\Response\MockResponse;

require __DIR__ . '/vendor/autoload.php';

$requests = static function () : \Generator {
    yield (new Psr17Factory())
        ->createRequest('GET', 'https://example.com');
};

$client = new PsrHttpClientStaticExtractor(
    new Psr18Client(
        new MockHttpClient(
            [
                new MockResponse(
                    file_get_contents(__DIR__ . '/input/example.com.html'),
                    [
                        'response_headers' => [
                            'Content-Type' => 'text/html',
                        ],
                    ],
                ),
            ],
        ),
    ),
    $requests(),
);

data_frame()
    ->read($client)
    ->withEntry('title', ref('response_body')->htmlQuerySelector('body div h1')->domElementValue())
    ->withEntry('paragraphs', ref('response_body')->htmlQuerySelectorAll('body p')->expand())
    ->select('title', 'paragraphs')
    ->write(to_stream(__DIR__ . '/output.txt', truncate: false))
    ->run();

Output

+----------------+-------------------------------------------------------------------------------------------------------+
|          title |                                                                                            paragraphs |
+----------------+-------------------------------------------------------------------------------------------------------+
| Example Domain | This domain is for use in documentation examples without needing permission. Avoid use in operations. |
| Example Domain |                                             <a href="https://iana.org/domains/example">Learn more</a> |
+----------------+-------------------------------------------------------------------------------------------------------+
2 rows

Contributors

Join us on GitHub