|
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 $link |
|
22
|
|
|
* @return \Pilipinews\Common\Article |
|
23
|
30 |
|
*/ |
|
24
|
|
|
public function scrape($link) |
|
25
|
30 |
|
{ |
|
26
|
|
|
$this->prepare(mb_strtolower($link)); |
|
27
|
30 |
|
|
|
28
|
|
|
$title = (string) $this->title('h1'); |
|
29
|
30 |
|
|
|
30
|
|
|
$body = $this->body('.page-content'); |
|
31
|
30 |
|
|
|
32
|
|
|
$body = $this->image($body); |
|
33
|
|
|
|
|
34
|
|
|
return new Article($title, $this->html($body)); |
|
35
|
|
|
} |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* Converts image elements to readable string. |
|
39
|
|
|
* |
|
40
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
|
41
|
|
|
* @return \Pilipinews\Common\Crawler |
|
42
|
|
|
*/ |
|
43
|
|
|
protected function image(DomCrawler $crawler) |
|
44
|
|
|
{ |
|
45
|
|
|
$callback = function (DomCrawler $crawler) { |
|
46
|
|
|
$result = $crawler->filter('img')->first(); |
|
47
|
|
|
|
|
48
|
|
|
$image = (string) $result->attr('src'); |
|
49
|
|
|
|
|
50
|
|
|
$text = $crawler->filter('p')->first(); |
|
51
|
|
|
|
|
52
|
|
|
$message = $image . ' - ' . $text->html(); |
|
53
|
|
|
|
|
54
|
|
|
return '<p>PHOTO: ' . $message . '</p>'; |
|
55
|
|
|
}; |
|
56
|
|
|
|
|
57
|
|
|
return $this->replace($crawler, 'figure.image', $callback); |
|
58
|
|
|
} |
|
59
|
|
|
} |
|
60
|
|
|
|
pilipinews /
pna
