UserEventCrawler::crawlUrl() - Code Metrics - Inspection of "[MINOR] Added new crawler for events" - core23/lastfm-php-api - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( f85b82...dc3bec )

by Christian

created 2019-04-19 06:46 UTC

UserEventCrawler::crawlUrl() A

↳ Parent: UserEventCrawler

Complexity

Conditions	2
Paths	2

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	6
rs	10
c	0
b	0
f	0
cc	2
nc	2
nop	3

<?php

declare(strict_types=1);

/*
 * (c) Christian Gripp <[email protected]>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

namespace Core23\LastFm\Crawler;

use Symfony\Component\DomCrawler\Crawler;

final class UserEventCrawler extends AbstractCrawler implements UserEventCrawlerInterface
{
    /**
     * {@inheritdoc}
     */
    public function getUserYears(string $username): ?array
    {
        $node = $this->crawlUrl($username);

        if (null === $node) {
            return null;
        }

        $years = $node->filter('.content-top .secondary-nav-item-link')
            ->each(static function (Crawler $node) {
                return (int) trim($node->text());
            })
        ;

        sort($years);
        array_shift($years);

        return $years;
class Author {
    private $name;

    public function __construct($name) {
        $this->name = $name;
    }

    public function getName() {
        return $this->name;
    }
}

abstract class Post {
    public function getAuthor() {
        return 'Johannes';
    }
}

class BlogPost extends Post {
    public function getAuthor() {
        return new Author('Johannes');
    }
}

class ForumPost extends Post { /* ... */ }

function my_function(Post $post) {
    echo strtoupper($post->getAuthor());
}
    }

    /**
     * {@inheritdoc}
     */
    public function getEvents(string $username, ?int $year, int $page = 1): ?array
    {
        $node = $this->crawlUrl($username, $year, $page);

        if (null === $node) {
            return null;
        }

        return $this->crawlEventList($node);
class Author {
    private $name;

    public function __construct($name) {
        $this->name = $name;
    }

    public function getName() {
        return $this->name;
    }
}

abstract class Post {
    public function getAuthor() {
        return 'Johannes';
    }
}

class BlogPost extends Post {
    public function getAuthor() {
        return new Author('Johannes');
    }
}

class ForumPost extends Post { /* ... */ }

function my_function(Post $post) {
    echo strtoupper($post->getAuthor());
}
    }

    /**
     * {@inheritdoc}
     */
    public function getYearPages(string $username, ?int $year): ?int
    {
        $node = $this->crawlUrl($username, $year);

        if (null === $node) {
            return null;
        }

        return $this->countListPages($node);
    }

    /**
     * {@inheritdoc}
     */
    public function getYearCount(string $username, ?int $year, int $page = 1): ?int
    {
        $node = $this->crawlUrl($username, $year, $page);

        if (null === $node) {
            return null;
        }

        $perPage = $this->countListEvents($node);
        $pages   = $this->countListPages($node);

        if ($pages) {
            $node = $this->crawlUrl($username, $year, $pages);

            if (null === $node) {
                return $perPage;
            }

            $count = $this->countListEvents($node);

            return ($pages - 1) * $perPage + $count;
        }

        return $perPage;
    }

    /**
     * @param Crawler $node
     *
     * @return int
     */
    private function countListPages(Crawler $node): int
    {
        $pagination = $this->parseString($node->filter('.pagination .pages'));

        return $pagination ? (int) preg_replace('/.* of /', '', $pagination) : 1;
    }

    /**
     * @param Crawler $node
     *
     * @return int
     */
    private function countListEvents(Crawler $node): int
    {
        return $node->filter('.events-list-item')->count();
    }

    /**
     * @param string   $username
     * @param int|null $year
     * @param int      $page
     *
     * @return Crawler|null
     */
    private function crawlUrl(string $username, ?int $year = null, int $page = 1): ?Crawler
    {
        $url = 'http://www.last.fm/user/'.$username.'/events/'.($year ?: '').'?page='.$page;

        return $this->crawl($url);
    }
}


1			<?php
2
3			declare(strict_types=1);
4
5			/*
6			* (c) Christian Gripp <[email protected]>
7			*
8			* For the full copyright and license information, please view the LICENSE
9			* file that was distributed with this source code.
10			*/
11
12			namespace Core23\LastFm\Crawler;
13
14			use Symfony\Component\DomCrawler\Crawler;
15
16			final class UserEventCrawler extends AbstractCrawler implements UserEventCrawlerInterface
17			{
18			/**
19			* {@inheritdoc}
20			*/
21			public function getUserYears(string $username): ?array
22			{
23			$node = $this->crawlUrl($username);
24
25			if (null === $node) {
26			return null;
27			}
28
29			$years = $node->filter('.content-top .secondary-nav-item-link')
30			->each(static function (Crawler $node) {
31			return (int) trim($node->text());
32			})
33			;
34
35			sort($years);
36			array_shift($years);
37
38			return $years;
			0 ignored issues – show Bug Best Practice introduced 2019-04-19 06:48 UTC by Report Bug Copy Issue Report The return type of `return $years;` (`array`) is incompatible with the return type declared by the interface `Core23\LastFm\Crawler\Us...Interface::getUserYears` of type `integer[]\|null`. If you return a value from a function or method, it should be a sub-type of the type that is given by the parent type f.e. an interface, or abstract method. This is more formally defined by the Lizkov substitution principle, and guarantees that classes that depend on the parent type can use any instance of a child type interchangably. This principle also belongs to the SOLID principles for object oriented design. Let’s take a look at an example: class Author { private $name; public function __construct($name) { $this->name = $name; } public function getName() { return $this->name; } } abstract class Post { public function getAuthor() { return 'Johannes'; } } class BlogPost extends Post { public function getAuthor() { return new Author('Johannes'); } } class ForumPost extends Post { /* ... */ } function my_function(Post $post) { echo strtoupper($post->getAuthor()); } Our function `my_function` expects a `Post` object, and outputs the author of the post. The base class `Post` returns a simple string and outputting a simple string will work just fine. However, the child class `BlogPost` which is a sub-type of `Post` instead decided to return an `object`, and is therefore violating the SOLID principles. If a `BlogPost` were passed to `my_function`, PHP would not complain, but ultimately fail when executing the `strtoupper` call in its body. Loading history...
39			}
40
41			/**
42			* {@inheritdoc}
43			*/
44			public function getEvents(string $username, ?int $year, int $page = 1): ?array
45			{
46			$node = $this->crawlUrl($username, $year, $page);
47
48			if (null === $node) {
49			return null;
50			}
51
52			return $this->crawlEventList($node);
			0 ignored issues – show Bug Best Practice introduced 2019-04-19 06:48 UTC by Report Bug Copy Issue Report The return type of `return $this->crawlEventList($node);` (`array`) is incompatible with the return type declared by the interface `Core23\LastFm\Crawler\Us...lerInterface::getEvents` of type `Core23\LastFm\Model\Event[]\|null`. If you return a value from a function or method, it should be a sub-type of the type that is given by the parent type f.e. an interface, or abstract method. This is more formally defined by the Lizkov substitution principle, and guarantees that classes that depend on the parent type can use any instance of a child type interchangably. This principle also belongs to the SOLID principles for object oriented design. Let’s take a look at an example: class Author { private $name; public function __construct($name) { $this->name = $name; } public function getName() { return $this->name; } } abstract class Post { public function getAuthor() { return 'Johannes'; } } class BlogPost extends Post { public function getAuthor() { return new Author('Johannes'); } } class ForumPost extends Post { /* ... */ } function my_function(Post $post) { echo strtoupper($post->getAuthor()); } Our function `my_function` expects a `Post` object, and outputs the author of the post. The base class `Post` returns a simple string and outputting a simple string will work just fine. However, the child class `BlogPost` which is a sub-type of `Post` instead decided to return an `object`, and is therefore violating the SOLID principles. If a `BlogPost` were passed to `my_function`, PHP would not complain, but ultimately fail when executing the `strtoupper` call in its body. Loading history...
53			}
54
55			/**
56			* {@inheritdoc}
57			*/
58			public function getYearPages(string $username, ?int $year): ?int
59			{
60			$node = $this->crawlUrl($username, $year);
61
62			if (null === $node) {
63			return null;
64			}
65
66			return $this->countListPages($node);
67			}
68
69			/**
70			* {@inheritdoc}
71			*/
72			public function getYearCount(string $username, ?int $year, int $page = 1): ?int
73			{
74			$node = $this->crawlUrl($username, $year, $page);
75
76			if (null === $node) {
77			return null;
78			}
79
80			$perPage = $this->countListEvents($node);
81			$pages = $this->countListPages($node);
82
83			if ($pages) {
84			$node = $this->crawlUrl($username, $year, $pages);
85
86			if (null === $node) {
87			return $perPage;
88			}
89
90			$count = $this->countListEvents($node);
91
92			return ($pages - 1) * $perPage + $count;
93			}
94
95			return $perPage;
96			}
97
98			/**
99			* @param Crawler $node
100			*
101			* @return int
102			*/
103			private function countListPages(Crawler $node): int
104			{
105			$pagination = $this->parseString($node->filter('.pagination .pages'));
106
107			return $pagination ? (int) preg_replace('/.* of /', '', $pagination) : 1;
108			}
109
110			/**
111			* @param Crawler $node
112			*
113			* @return int
114			*/
115			private function countListEvents(Crawler $node): int
116			{
117			return $node->filter('.events-list-item')->count();
118			}
119
120			/**
121			* @param string $username
122			* @param int\|null $year
123			* @param int $page
124			*
125			* @return Crawler\|null
126			*/
127			private function crawlUrl(string $username, ?int $year = null, int $page = 1): ?Crawler
128			{
129			$url = 'http://www.last.fm/user/'.$username.'/events/'.($year ?: '').'?page='.$page;
130
131			return $this->crawl($url);
132			}
133			}
134

core23 / lastfm-php-api

GitHub Access Token became invalid

Push — master ( f85b82...dc3bec )

UserEventCrawler::crawlUrl() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like