Crawler::crawl() - Code Metrics - Inspection of "Modify ScraperTest" - pilipinews/cnn - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 3c53c8...6b2cdf )

by Rougin

created 2020-03-29 14:45 UTC

Crawler::crawl() A

↳ Parent: Crawler

Complexity

Conditions	1
Paths	1

Size

Total Lines	24
Code Lines	11

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	11
CRAP Score	1.0036

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
cc	1
eloc	11
c	2
b	0
f	0
nc	1
nop	0
dl	0
loc	24
ccs	11
cts	13
cp	0.8462
crap	1.0036
rs	9.9

<?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 = (string) 'https://cnnphilippines.com';

        $url = 'https://cnnphilippines.com/search/?order=DESC';

        $query = '&page=1&q=a&sort=PUBLISHDATE';

        $response = Client::request($url . $query);

        $callback = function (DomCrawler $node) use ($base)
        {
            $link = $node->filter('.media-heading > a');

            return (string) $base . $link->attr('href');
        };

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

        $news = $crawler->filter('.results > .media');

        $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 = (string) 'https://cnnphilippines.com';
25
26	3	$url = 'https://cnnphilippines.com/search/?order=DESC';
27
28	3	$query = '&page=1&q=a&sort=PUBLISHDATE';
29
30	3	$response = Client::request($url . $query);
31
32	2	$callback = function (DomCrawler $node) use ($base)
33		{
34		$link = $node->filter('.media-heading > a');
35
36		return (string) $base . $link->attr('href');
37	3	};
38
39	3	$crawler = new DomCrawler((string) $response);
40
41	3	$news = $crawler->filter('.results > .media');
42
43	3	$news = $this->verify($news->each($callback));
44
45	3	return array_reverse((array) $news);
46		}
47
48		/**
49		* Returns the allowed article URLs to scrape.
50		*
51		* @param string[] $items
52		* @return string[]
53		*/
54		protected function verify($items)
55		{
56	3	$callback = function ($link)
57		{
58		return strpos($link, '/news/') !== false ? $link : null;
59	3	};
60
61	1	$items = array_map($callback, (array) $items);
62
63	1	return array_values(array_filter($items));
64		}
65		}
66

pilipinews / cnn

Push — master ( 3c53c8...6b2cdf )

Crawler::crawl() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like