|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace Pilipinews\Website\Inquirer; |
|
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
|
|
|
* Inquirer News Scraper |
|
13
|
|
|
* |
|
14
|
|
|
* @package Pilipinews |
|
15
|
|
|
* @author Rougin Royce Gutib <[email protected]> |
|
16
|
|
|
*/ |
|
17
|
|
|
class Scraper extends AbstractScraper implements ScraperInterface |
|
18
|
|
|
{ |
|
19
|
|
|
const TEXT_FOOTER = 'Subscribe to INQUIRER PLUS (http://www.inquirer.net/plus) to get access to The Philippine Daily Inquirer & other 70+ titles, share up to 5 gadgets, listen to the news, download as early as 4am & share articles on social media. Call 896 6000.'; |
|
20
|
|
|
|
|
21
|
|
|
/** |
|
22
|
|
|
* @var string[] |
|
23
|
|
|
*/ |
|
24
|
|
|
protected $refresh = array('Refresh this page for updates.'); |
|
25
|
|
|
|
|
26
|
|
|
/** |
|
27
|
|
|
* @var string[] |
|
28
|
|
|
*/ |
|
29
|
|
|
protected $removables = array( |
|
30
|
|
|
'script', |
|
31
|
|
|
'#billboard_article', |
|
32
|
|
|
'.ventuno-vid', |
|
33
|
|
|
'#article_disclaimer', |
|
34
|
|
|
'.OUTBRAIN', |
|
35
|
|
|
'#ch-follow-us', |
|
36
|
|
|
'.view-comments', |
|
37
|
|
|
'#article_tags', |
|
38
|
|
|
'.adsbygoogle', |
|
39
|
|
|
'#article-new-featured', |
|
40
|
|
|
'#read-next-2018', |
|
41
|
|
|
'#rn-lbl', |
|
42
|
|
|
'#fb-root', |
|
43
|
|
|
); |
|
44
|
|
|
|
|
45
|
|
|
/** |
|
46
|
|
|
* Returns the contents of an article. |
|
47
|
|
|
* |
|
48
|
|
|
* @param string $link |
|
49
|
|
|
* @return \Pilipinews\Common\Article |
|
50
|
|
|
*/ |
|
51
|
30 |
|
public function scrape($link) |
|
52
|
|
|
{ |
|
53
|
30 |
|
$this->prepare((string) mb_strtolower($link)); |
|
54
|
|
|
|
|
55
|
30 |
|
$title = $this->title('.entry-title'); |
|
56
|
|
|
|
|
57
|
30 |
|
$pattern = '/-(\d+)x(\d+).jpg/i'; |
|
58
|
|
|
|
|
59
|
30 |
|
$this->remove((array) $this->removables); |
|
60
|
|
|
|
|
61
|
30 |
|
$body = $this->body('#article_content'); |
|
62
|
|
|
|
|
63
|
30 |
|
$body = $this->caption($body); |
|
64
|
|
|
|
|
65
|
30 |
|
$body = $this->fbvideo($body); |
|
66
|
|
|
|
|
67
|
30 |
|
$body = $this->fbpost($body)->html(); |
|
68
|
|
|
|
|
69
|
30 |
|
$body = preg_replace($pattern, '.jpg', $body); |
|
70
|
|
|
|
|
71
|
30 |
|
$body = $this->html(new DomCrawler($body), $this->refresh); |
|
72
|
|
|
|
|
73
|
30 |
|
$body = str_replace(self::TEXT_FOOTER, '', trim($body)); |
|
74
|
|
|
|
|
75
|
30 |
|
return new Article($title, (string) trim($body)); |
|
76
|
|
|
} |
|
77
|
|
|
|
|
78
|
|
|
/** |
|
79
|
|
|
* Converts caption elements to readable string. |
|
80
|
|
|
* |
|
81
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
|
82
|
|
|
* @return \Pilipinews\Common\Crawler |
|
83
|
|
|
*/ |
|
84
|
20 |
|
protected function caption(DomCrawler $crawler) |
|
85
|
|
|
{ |
|
86
|
10 |
|
$callback = function (DomCrawler $crawler) |
|
87
|
|
|
{ |
|
88
|
12 |
|
$image = $crawler->filter('img')->first()->attr('src'); |
|
89
|
|
|
|
|
90
|
12 |
|
$format = (string) '<p>PHOTO: %s</p><p>%s</p>'; |
|
91
|
|
|
|
|
92
|
12 |
|
$text = $crawler->filter('.wp-caption-text')->first(); |
|
93
|
|
|
|
|
94
|
12 |
|
return sprintf($format, $image, $text->html()); |
|
95
|
30 |
|
}; |
|
96
|
|
|
|
|
97
|
30 |
|
return $this->replace($crawler, '.wp-caption', $callback); |
|
98
|
|
|
} |
|
99
|
|
|
|
|
100
|
|
|
/** |
|
101
|
|
|
* Converts Facebook embedded posts to readable string. |
|
102
|
|
|
* |
|
103
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
|
104
|
|
|
* @return \Pilipinews\Common\Crawler |
|
105
|
|
|
*/ |
|
106
|
20 |
|
protected function fbpost(DomCrawler $crawler) |
|
107
|
|
|
{ |
|
108
|
10 |
|
$callback = function (DomCrawler $crawler) |
|
109
|
|
|
{ |
|
110
|
|
|
$link = $crawler->attr('cite'); |
|
|
|
|
|
|
111
|
|
|
|
|
112
|
|
|
$text = '<p>POST: ' . $crawler->attr('cite') . '</p>'; |
|
113
|
|
|
|
|
114
|
|
|
$message = $crawler->filter('p > a')->first(); |
|
115
|
|
|
|
|
116
|
|
|
return $text . '<p>' . $message->text() . '</p>'; |
|
117
|
30 |
|
}; |
|
118
|
|
|
|
|
119
|
30 |
|
return $this->replace($crawler, '.fb-xfbml-parse-ignore', $callback); |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
|
|
/** |
|
123
|
|
|
* Converts fbvideo elements to readable string. |
|
124
|
|
|
* |
|
125
|
|
|
* @param \Pilipinews\Common\Crawler $crawler |
|
126
|
|
|
* @return \Pilipinews\Common\Crawler |
|
127
|
|
|
*/ |
|
128
|
|
|
protected function fbvideo(DomCrawler $crawler) |
|
129
|
|
|
{ |
|
130
|
30 |
|
$callback = function (DomCrawler $crawler) |
|
131
|
|
|
{ |
|
132
|
3 |
|
$link = $crawler->attr('data-href'); |
|
133
|
|
|
|
|
134
|
3 |
|
return '<p>VIDEO: ' . $link . '</p>'; |
|
135
|
30 |
|
}; |
|
136
|
|
|
|
|
137
|
30 |
|
return $this->replace($crawler, '.fb-video', $callback); |
|
138
|
|
|
} |
|
139
|
|
|
|
|
140
|
|
|
/** |
|
141
|
|
|
* Initializes the crawler instance. |
|
142
|
|
|
* |
|
143
|
|
|
* @param string $link |
|
144
|
|
|
* @return void |
|
145
|
|
|
*/ |
|
146
|
30 |
|
protected function prepare($link) |
|
147
|
|
|
{ |
|
148
|
30 |
|
$response = Client::request((string) $link); |
|
149
|
|
|
|
|
150
|
30 |
|
$response = str_replace('<p>Click <a href="https://www.inquirer.net/philippine-typhoon-news">here</a> for more weather related news."</p>', '', $response); |
|
151
|
|
|
|
|
152
|
30 |
|
$response = str_replace('<p>Click <a href="https://www.inquirer.net/philippine-typhoon-news">here</a> for more weather related news.</p>', '', $response); |
|
153
|
|
|
|
|
154
|
30 |
|
$response = str_replace('<strong> </strong>', ' ', $response); |
|
155
|
|
|
|
|
156
|
30 |
|
$this->crawler = new DomCrawler($response); |
|
157
|
30 |
|
} |
|
158
|
|
|
} |
|
159
|
|
|
|
pilipinews /
inquirer
Loading history...