Crawler::crawl() - Code Metrics - pilipinews/cnn - Measure and Improve Code Quality continuously with Scrutinizer

Crawler::crawl() A
last analyzed 2020-07-06 22:48 UTC

↳ Parent: Crawler

Complexity

Conditions	1
Paths	1

Size

Total Lines	18
Code Lines	8

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	10
CRAP Score	1

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
cc	1
eloc	8
c	2
b	0
f	0
nc	1
nop	0
dl	0
loc	18
ccs	10
cts	10
cp	1
crap	1
rs	10

<?php

namespace Pilipinews\Website\Cnn;

use Pilipinews\Common\Client;
use Pilipinews\Common\Crawler as DomCrawler;
use Pilipinews\Common\Interfaces\CrawlerInterface;

/**
 * CNN Philippines Crawler
 *
 * @package Pilipinews
 * @author  Rougin Gutib <[email protected]>
 */
class Crawler implements CrawlerInterface
{
    /**
     * Returns an array of articles to scrape.
     *
     * @return string[]
     */
    public function crawl()
    {
        $base = 'https://cnnphilippines.com';

        $response = Client::request($base);

        $callback = function (DomCrawler $node) use ($base)
        {
            return $base . $node->filter('a')->attr('href');
        };

        $crawler = new DomCrawler((string) $response);

        $news = $crawler->filter('.cbwidget-list > li');

        $news = $this->verify($news->each($callback));

        return array_reverse((array) $news);
    }

    /**
     * Returns the allowed article URLs to scrape.
     *
     * @param  string[] $items
     * @return string[]
     */
    protected function verify($items)
    {
        $callback = function ($link)
        {
            return strpos($link, '/news/') !== false ? $link : null;
        };

        $items = array_map($callback, (array) $items);

        return array_values(array_filter($items));
    }
}


1		<?php
2
3		namespace Pilipinews\Website\Cnn;
4
5		use Pilipinews\Common\Client;
6		use Pilipinews\Common\Crawler as DomCrawler;
7		use Pilipinews\Common\Interfaces\CrawlerInterface;
8
9		/**
10		* CNN Philippines Crawler
11		*
12		* @package Pilipinews
13		* @author Rougin Gutib <[email protected]>
14		*/
15		class Crawler implements CrawlerInterface
16		{
17		/**
18		* Returns an array of articles to scrape.
19		*
20		* @return string[]
21		*/
22	3	public function crawl()
23		{
24	3	$base = 'https://cnnphilippines.com';
25
26	3	$response = Client::request($base);
27
28	2	$callback = function (DomCrawler $node) use ($base)
29		{
30	3	return $base . $node->filter('a')->attr('href');
31	3	};
32
33	3	$crawler = new DomCrawler((string) $response);
34
35	3	$news = $crawler->filter('.cbwidget-list > li');
36
37	3	$news = $this->verify($news->each($callback));
38
39	3	return array_reverse((array) $news);
40		}
41
42		/**
43		* Returns the allowed article URLs to scrape.
44		*
45		* @param string[] $items
46		* @return string[]
47		*/
48		protected function verify($items)
49		{
50	3	$callback = function ($link)
51		{
52	3	return strpos($link, '/news/') !== false ? $link : null;
53	3	};
54
55	1	$items = array_map($callback, (array) $items);
56
57	1	return array_values(array_filter($items));
58		}
59		}
60

pilipinews / cnn

Crawler::crawl() A last analyzed 2020-07-06 22:48 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

Crawler::crawl() A
last analyzed 2020-07-06 22:48 UTC