PHP code example of ixnode / php-web-crawler

1. Go to this page and download the library: Download ixnode/php-web-crawler library. Choose the download type require.

2. Extract the ZIP file and open the index.php.

3. Add this code to the index.php. 
    
        
<?php
require_once('vendor/autoload.php');

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

ixnode / php-web-crawler example snippets


use Ixnode\PhpWebCrawler\Output\Field;
use Ixnode\PhpWebCrawler\Source\Raw;
use Ixnode\PhpWebCrawler\Value\Text;
use Ixnode\PhpWebCrawler\Value\XpathTextNode;

$rawHtml = <<<HTML
<html>
    <head>
        <title>Test Page</title>
    </head>
    <body>
        <h1>Test Title</h1>
        <p>Test Paragraph</p>
    </body>
</html>
HTML;

$html = new Raw(
    $rawHtml,
    new Field('version', new Text('1.0.0')),
    new Field('title', new XpathTextNode('//h1')),
    new Field('paragraph', new XpathTextNode('//p'))
);

$html->parse()->getJsonStringFormatted();
// See below


use Ixnode\PhpWebCrawler\Output\Field;
use Ixnode\PhpWebCrawler\Output\Group;
use Ixnode\PhpWebCrawler\Source\Raw;
use Ixnode\PhpWebCrawler\Value\XpathTextNode;

$rawHtml = <<<HTML
<html>
    <head>
        <title>Test Page</title>
    </head>
    <body>
        <h1>Test Title</h1>
        <p class="paragraph-1">Test Paragraph 1</p>
        <p class="paragraph-2">Test Paragraph 2</p>
    </body>
</html>
HTML;

$html = new Raw(
    $rawHtml,
    new Field('title', new XpathTextNode('/html/head/title')),
    new Group(
        'content',
        new Group(
            'header',
            new Field('h1', new XpathTextNode('/html/body//h1')),
        ),
        new Group(
            'text',
            new Field('p1', new XpathTextNode('/html/body//p[@class="paragraph-1"]')),
            new Field('p2', new XpathTextNode('/html/body//p[@class="paragraph-2"]')),
        )
    )
);

$html->parse()->getJsonStringFormatted();
// See below


use Ixnode\PhpWebCrawler\Output\Field;
use Ixnode\PhpWebCrawler\Output\Group;
use Ixnode\PhpWebCrawler\Source\Raw;
use Ixnode\PhpWebCrawler\Source\XpathSection;
use Ixnode\PhpWebCrawler\Value\XpathTextNode;

$rawHtml = <<<HTML
<html>
    <head>
        <title>Test Page</title>
    </head>
    <body>
        <div class="content">
            <h1>Test Title</h1>
            <p class="paragraph-1">Test Paragraph 1</p>
            <p class="paragraph-2">Test Paragraph 2</p>
        </div>
    </body>
</html>
HTML;

$html = new Raw(
    $rawHtml,
    new Field('title', new XpathTextNode('/html/head/title')),
    new Group(
        'content',
        new XpathSection(
            '/html/body//div[@class="content"]',
            new Group(
                'header',
                new Field('h1', new XpathTextNode('./h1')),
            ),
            new Group(
                'text',
                new Field('p1', new XpathTextNode('./p[@class="paragraph-1"]')),
                new Field('p2', new XpathTextNode('./p[@class="paragraph-2"]')),
            )
        )
    )
);

$html->parse()->getJsonStringFormatted();
// See below


use Ixnode\PhpWebCrawler\Output\Field;
use Ixnode\PhpWebCrawler\Output\Group;
use Ixnode\PhpWebCrawler\Source\Raw;
use Ixnode\PhpWebCrawler\Source\XpathSections;
use Ixnode\PhpWebCrawler\Value\XpathTextNode;

$rawHtml = <<<HTML
<html>
    <head>
        <title>Test Page</title>
    </head>
    <body>
        <div class="content">
            <h1>Test Title</h1>
            <p class="paragraph-1">Test Paragraph 1</p>
            <p class="paragraph-2">Test Paragraph 2</p>
            <ul>
                <li>Test Item 1</li>
                <li>Test Item 2</li>
            </ul>
        </div>
    </body>
</html>
HTML;

$html = new Raw(
    $rawHtml,
    new Field('title', new XpathTextNode('/html/head/title')),
    new Group(
        'hits',
        new XpathSections(
            '/html/body//div[@class="content"]/ul',
            new XpathTextNode('./li/text()'),
        )
    )
);

$html->parse()->getJsonStringFormatted();
// See below


use Ixnode\PhpWebCrawler\Output\Field;
use Ixnode\PhpWebCrawler\Output\Group;
use Ixnode\PhpWebCrawler\Source\Raw;
use Ixnode\PhpWebCrawler\Source\XpathSections;
use Ixnode\PhpWebCrawler\Value\XpathTextNode;

$rawHtml = <<<HTML
<html>
    <head>
        <title>Test Page</title>
    </head>
    <body>
        <div class="content">
            <h1>Test Title</h1>
            <p class="paragraph-1">Test Paragraph 1</p>
            <p class="paragraph-2">Test Paragraph 2</p>
            <table>
                <tbody>
                    <tr>
                        <th>Caption 1</th>
                        <td>Cell 1</td>
                    </tr>
                    <tr>
                        <th>Caption 2</th>
                        <td>Cell 2</td>
                    </tr>
                </tbody>
            </table>
        </div>
    </body>
</html>
HTML;

$html = new Raw(
    $rawHtml,
    new Field('title', new XpathTextNode('/html/head/title')),
    new Group(
        'hits',
        new XpathSections(
            '/html/body//div[@class="content"]/table/tbody/tr',
            new Field('caption', new XpathTextNode('./th/text()')),
            new Field('content', new XpathTextNode('./td/text()')),
        )
    )
);

$html->parse()->getJsonStringFormatted();
// See below

shell
composer 
shell
vendor/bin/php-web-crawler -V

shell
php-web-crawler 0.1.0 (02-24-2024 14:46:26) - Björn Hempel <[email protected]>

bash
git clone [email protected]:ixnode/php-web-crawler.git && cd php-web-crawler