1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace Pilipinews\Website\Pna; |
4
|
|
|
|
5
|
|
|
use Pilipinews\Common\Article; |
6
|
|
|
use Pilipinews\Common\Crawler as DomCrawler; |
7
|
|
|
use Pilipinews\Common\Interfaces\ScraperInterface; |
8
|
|
|
use Pilipinews\Common\Scraper as AbstractScraper; |
9
|
|
|
|
10
|
|
|
/** |
11
|
|
|
* Philippine News Agency Scraper |
12
|
|
|
* |
13
|
|
|
* @package Pilipinews |
14
|
|
|
* @author Rougin Gutib <[email protected]> |
15
|
|
|
*/ |
16
|
|
|
class Scraper extends AbstractScraper implements ScraperInterface |
17
|
|
|
{ |
18
|
|
|
/** |
19
|
|
|
* Returns the contents of an article. |
20
|
|
|
* |
21
|
|
|
* @param string $link |
22
|
|
|
* @return \Pilipinews\Common\Article |
23
|
|
|
*/ |
24
|
36 |
|
public function scrape($link) |
25
|
|
|
{ |
26
|
36 |
|
$this->prepare(mb_strtolower($link)); |
27
|
|
|
|
28
|
36 |
|
$title = (string) $this->title('h1'); |
29
|
|
|
|
30
|
36 |
|
$body = $this->body('.page-content'); |
31
|
|
|
|
32
|
36 |
|
$body = $this->image($body); |
33
|
|
|
|
34
|
36 |
|
$html = (string) $this->html($body); |
35
|
|
|
|
36
|
36 |
|
return new Article($title, $html, $link); |
37
|
|
|
} |
38
|
|
|
|
39
|
|
|
/** |
40
|
|
|
* Converts image elements to readable string. |
41
|
|
|
* |
42
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
43
|
|
|
* @return \Pilipinews\Common\Crawler |
44
|
|
|
*/ |
45
|
|
|
protected function image(DomCrawler $crawler) |
46
|
|
|
{ |
47
|
36 |
|
$callback = function (DomCrawler $crawler) |
48
|
|
|
{ |
49
|
9 |
|
$result = $crawler->filter('img')->first(); |
50
|
|
|
|
51
|
9 |
|
$image = (string) $result->attr('src'); |
52
|
|
|
|
53
|
9 |
|
$text = $crawler->filter('figcaption')->first(); |
54
|
|
|
|
55
|
9 |
|
$message = $image . ' - ' . $text->text(); |
56
|
|
|
|
57
|
9 |
|
return '<p>PHOTO: ' . $message . '</p>'; |
58
|
36 |
|
}; |
59
|
|
|
|
60
|
|
|
return $this->replace($crawler, 'figure.image', $callback); |
61
|
|
|
} |
62
|
|
|
} |
63
|
|
|
|