|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace Pilipinews\Website\Cnn; |
|
4
|
|
|
|
|
5
|
|
|
use Pilipinews\Common\Article; |
|
6
|
|
|
use Pilipinews\Common\Client; |
|
7
|
|
|
use Pilipinews\Common\Crawler as DomCrawler; |
|
8
|
|
|
use Pilipinews\Common\Interfaces\ScraperInterface; |
|
9
|
|
|
use Pilipinews\Common\Scraper as AbstractScraper; |
|
10
|
|
|
|
|
11
|
|
|
/** |
|
12
|
|
|
* CNN Philippines Scraper |
|
13
|
|
|
* |
|
14
|
|
|
* @package Pilipinews |
|
15
|
|
|
* @author Rougin Gutib <[email protected]> |
|
16
|
|
|
*/ |
|
17
|
|
|
class Scraper extends AbstractScraper implements ScraperInterface |
|
18
|
|
|
{ |
|
19
|
|
|
/** |
|
20
|
|
|
* @var string[] |
|
21
|
|
|
*/ |
|
22
|
|
|
protected $removables = array('p > script', '.flourish-credit'); |
|
23
|
|
|
|
|
24
|
|
|
/** |
|
25
|
|
|
* @var string[] |
|
26
|
|
|
*/ |
|
27
|
|
|
protected $reload = array( |
|
28
|
|
|
'Please click the source link below for more updates.', |
|
29
|
|
|
'Please refresh for updates.', |
|
30
|
|
|
'Please refresh the page for updates.', |
|
31
|
|
|
'Please refresh this page for updates.', |
|
32
|
|
|
'Refresh this page for more updates.', |
|
33
|
|
|
); |
|
34
|
|
|
|
|
35
|
|
|
/** |
|
36
|
|
|
* Returns the contents of an article. |
|
37
|
|
|
* |
|
38
|
|
|
* @param string $link |
|
39
|
|
|
* @return \Pilipinews\Common\Article |
|
40
|
|
|
*/ |
|
41
|
30 |
|
public function scrape($link) |
|
42
|
|
|
{ |
|
43
|
30 |
|
$this->prepare((string) $link); |
|
44
|
|
|
|
|
45
|
30 |
|
$title = $this->title('title', ' - CNN Philippines'); |
|
46
|
|
|
|
|
47
|
30 |
|
$body = $this->body('#content-body'); |
|
48
|
|
|
|
|
49
|
30 |
|
$body = $this->video($this->tweet($body)); |
|
50
|
|
|
|
|
51
|
30 |
|
$html = $this->html($body, $this->reload); |
|
52
|
|
|
|
|
53
|
30 |
|
$search = '/pic.twitter.com\/(.*)- CNN/i'; |
|
54
|
|
|
|
|
55
|
30 |
|
$replace = (string) 'pic.twitter.com/$1 - CNN'; |
|
56
|
|
|
|
|
57
|
30 |
|
$html = preg_replace($search, $replace, $html); |
|
58
|
|
|
|
|
59
|
30 |
|
return new Article($title, $html, $link); |
|
60
|
|
|
} |
|
61
|
|
|
|
|
62
|
|
|
/** |
|
63
|
|
|
* Initializes the crawler instance. |
|
64
|
|
|
* |
|
65
|
|
|
* @param string $link |
|
66
|
|
|
* @return void |
|
67
|
|
|
*/ |
|
68
|
30 |
|
protected function prepare($link) |
|
69
|
|
|
{ |
|
70
|
30 |
|
$pattern = '/content-body-[0-9]+(-[0-9]+)+/i'; |
|
71
|
|
|
|
|
72
|
30 |
|
$html = Client::request((string) $link); |
|
73
|
|
|
|
|
74
|
30 |
|
$html = str_replace(' </em> ', '</em> ', $html); |
|
75
|
|
|
|
|
76
|
30 |
|
preg_match($pattern, (string) $html, $matches); |
|
77
|
|
|
|
|
78
|
30 |
|
$html = str_replace($matches[0], 'content-body', $html); |
|
79
|
|
|
|
|
80
|
30 |
|
$html = str_replace(' </a>', '</a> ', $html); |
|
81
|
|
|
|
|
82
|
30 |
|
$html = str_replace('<strong> </strong>', ' ', $html); |
|
83
|
|
|
|
|
84
|
30 |
|
$this->crawler = new DomCrawler((string) $html); |
|
85
|
|
|
|
|
86
|
30 |
|
$this->remove((array) $this->removables); |
|
87
|
30 |
|
} |
|
88
|
|
|
|
|
89
|
|
|
/** |
|
90
|
|
|
* Converts video elements to readable string. |
|
91
|
|
|
* |
|
92
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
|
93
|
|
|
* @return \Pilipinews\Common\Crawler |
|
94
|
|
|
*/ |
|
95
|
|
|
protected function video(DomCrawler $crawler) |
|
96
|
|
|
{ |
|
97
|
30 |
|
$callback = function (DomCrawler $crawler) |
|
98
|
|
|
{ |
|
99
|
9 |
|
$embed = strpos($link = $crawler->attr('src'), 'embed'); |
|
100
|
|
|
|
|
101
|
9 |
|
$type = $embed !== false ? 'EMBED' : 'VIDEO'; |
|
102
|
|
|
|
|
103
|
9 |
|
return '<p>' . $type . ': ' . $link . '</p><br><br><br>'; |
|
104
|
30 |
|
}; |
|
105
|
|
|
|
|
106
|
30 |
|
return $this->replace($crawler, 'p > iframe', $callback); |
|
107
|
|
|
} |
|
108
|
|
|
} |
|
109
|
|
|
|
pilipinews /
cnn
