Quasar/example.php at main · Vxsilisk/Quasar · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
<?php

/**
 * Quasar — runnable demo.  `php example.php`
 *
 * @author  Vxsilisk — Quasar
 * @license MIT
 */
require __DIR__ . '/autoload.php';

$html = <<<'HTML'
<!doctype html>
<html>
<head><title>Nebula — Latest Posts</title></head>
<body>
  <main>
    <article class="post" data-id="1">
      <h2><a href="https://nebula.dev/pulsar">PulsarX 1.1 released</a></h2>
      <p class="lead">Retries, backoff, per-request timeouts.</p>
      <ul class="tags"><li>http</li><li>php</li><li class="hot">scraping</li></ul>
    </article>
    <article class="post draft" data-id="2">
      <h2><a href="https://nebula.dev/quasar">Meet Quasar</a></h2>
      <p class="lead">A zero-dep HTML scraper.</p>
    </article>
  </main>
</body>
</html>
HTML;

$doc = Quasar::html($html);

echo "Title: ", $doc->title(), "\n\n";

echo "Published posts (skipping drafts):\n";
$doc->find('article:not(.draft)')->each(function ($post) {
    $link = $post->first('h2 a');
    printf("  • %-24s %s\n", $link->text(), $link->attr('href'));
    echo "    tags: ", implode(', ', $post->find('.tags li')->texts()), "\n";
});

echo "\nAll links on the page:\n";
foreach ($doc->links() as $href) {
    echo "  - {$href}\n";
}

echo "\nHottest tag: ", $doc->first('li.hot')->text(), "\n";

// Fetch-and-parse, the intended pairing with PulsarX:
//
//   $r   = (new Pulsar())->impersonate('chrome')->get('https://news.ycombinator.com');
//   $doc = Quasar::html($r->getBody());
//   foreach ($doc->find('.titleline > a') as $story) {
//       echo $story->text(), "\n";
//   }