Crawler::getResults() - Code Metrics - Inspection of "Merge branch 'v1.2.0'" - CViniciusSDias/google-crawler - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 5fce14...dad0cb )

by Vinicius

created 2017-07-02 18:00 UTC

Crawler::getResults() B

↳ Parent: Crawler

Complexity

Conditions	3
Paths	4

Size

Total Lines	24
Code Lines	16

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	14
CRAP Score	3.0026

Importance

Changes

Metric	Value
dl	0
loc	24
ccs	14
cts	15
cp	0.9333
rs	8.9713
c	0
b	0
f	0
cc	3
eloc	16
nc	4
nop	0
crap	3.0026

<?php
namespace CViniciusSDias\GoogleCrawler;

use CViniciusSDias\GoogleCrawler\Exception\InvalidResultException;
use CViniciusSDias\GoogleCrawler\Proxy\{
    GoogleProxy, NoProxy
};
use Psr\Http\Message\ResponseInterface;
use Symfony\Component\DomCrawler\Crawler as DomCrawler;
use Symfony\Component\DomCrawler\Link;
use DOMElement;

/**
 * Google Crawler
 *
 * @package CViniciusSDias\GoogleCrawler
 * @author Vinicius Dias
 */
class Crawler
{
    /** @var string $url*/
    protected $url;
    /** @var GoogleProxy $proxy */
    protected $proxy;

    public function __construct(SearchTermInterface $searchTerm, GoogleProxy $proxy = null)
    {
        // You can concatenate &gl=XX replacing XX with your country code (BR = Brazil; US = United States)
        // You should also add the coutry specific part of the google url, (like .br or .es)
        $this->url = "http://www.google.com/search?q=$searchTerm&num=100";
        $this->proxy = is_null($proxy) ? new NoProxy() : $proxy;

    }

    /**
     * Returns the 100 first found results for the specified search term
     *
     * @return ResultList
     * @throws \GuzzleHttp\Exception\ServerException If the proxy was overused
     * @throws \GuzzleHttp\Exception\ConnectException If the proxy is unavailable
     */
    public function getResults(): ResultList
    {
        /** @var ResponseInterface $response */
        $response = $this->proxy->getHttpResponse($this->url);
        $stringResponse = (string) $response->getBody();
        $domCrawler = new DomCrawler($stringResponse);
        $googleResults = $domCrawler->filterXPath('//div[@class="g" and h3[@class="r" and a]]');
        $resultList = new ResultList($googleResults->count());

        foreach ($googleResults as $result) {
            $resultCrawler = new DomCrawler($result);
            $linkElement = $resultCrawler->filterXPath('//h3[@class="r"]/a')->getNode(0);
            $resultLink = new Link($linkElement, 'http://google.com/');
/** @return stdClass|null */
function mayReturnNull() { }

function doesNotAcceptNull(stdClass $x) { }

// With potential error.
function withoutCheck() {
    $x = mayReturnNull();
    doesNotAcceptNull($x); // Potential error here.
}

// Safe - Alternative 1
function withCheck1() {
    $x = mayReturnNull();
    if ( ! $x instanceof stdClass) {
        throw new \LogicException('$x must be defined.');
    }
    doesNotAcceptNull($x);
}

// Safe - Alternative 2
function withCheck2() {
    $x = mayReturnNull();
    if ($x instanceof stdClass) {
        doesNotAcceptNull($x);
    }
}
            $descriptionElement = $resultCrawler->filterXPath('//span[@class="st"]')->getNode(0);
            try {
                $googleResult = $this->parseResult($resultLink, $descriptionElement);
/** @return stdClass|null */
function mayReturnNull() { }

function doesNotAcceptNull(stdClass $x) { }

// With potential error.
function withoutCheck() {
    $x = mayReturnNull();
    doesNotAcceptNull($x); // Potential error here.
}

// Safe - Alternative 1
function withCheck1() {
    $x = mayReturnNull();
    if ( ! $x instanceof stdClass) {
        throw new \LogicException('$x must be defined.');
    }
    doesNotAcceptNull($x);
}

// Safe - Alternative 2
function withCheck2() {
    $x = mayReturnNull();
    if ($x instanceof stdClass) {
        doesNotAcceptNull($x);
    }
}
                $resultList->addResult($googleResult);
            } catch (InvalidResultException $invalidResult) {
                // TODO Maybe log this exception. Other than that, there's nothing to do, cause it isn't an error.
            }
        }

        return $resultList;
    }

    /**
     * If $resultLink is a valid link, this method assembles the Result and adds it to $googleResults
     *
     * @param Link $resultLink
     * @param DOMElement $descriptionElement
     * @return Result
     * @throws InvalidResultException
     */
    private function parseResult(Link $resultLink, DOMElement $descriptionElement): Result
    {
        $description = $descriptionElement->nodeValue
            ?? 'A description for this result isn\'t available due to the robots.txt file.';

        $googleResult = new Result();
        $googleResult
            ->setTitle($resultLink->getNode()->nodeValue)
            ->setUrl($this->getUrl($resultLink->getUri()))
            ->setDescription($description);

        return $googleResult;
    }

    /**
     * Parses the URL using the parser provided by $proxy
     *
     * @param string $url
     * @return string
     * @throws InvalidResultException
     */
    private function getUrl(string $url): string
    {
        return $this->proxy->parseUrl($url);
    }
}


1		<?php
2		namespace CViniciusSDias\GoogleCrawler;
3
4		use CViniciusSDias\GoogleCrawler\Exception\InvalidResultException;
5		use CViniciusSDias\GoogleCrawler\Proxy\{
6		GoogleProxy, NoProxy
7		};
8		use Psr\Http\Message\ResponseInterface;
9		use Symfony\Component\DomCrawler\Crawler as DomCrawler;
10		use Symfony\Component\DomCrawler\Link;
11		use DOMElement;
12
13		/**
14		* Google Crawler
15		*
16		* @package CViniciusSDias\GoogleCrawler
17		* @author Vinicius Dias
18		*/
19		class Crawler
20		{
21		/** @var string $url*/
22		protected $url;
23		/** @var GoogleProxy $proxy */
24		protected $proxy;
25
26	13	public function __construct(SearchTermInterface $searchTerm, GoogleProxy $proxy = null)
27		{
28		// You can concatenate &gl=XX replacing XX with your country code (BR = Brazil; US = United States)
29		// You should also add the coutry specific part of the google url, (like .br or .es)
30	13	$this->url = "http://www.google.com/search?q=$searchTerm&num=100";
31	13	$this->proxy = is_null($proxy) ? new NoProxy() : $proxy;
		0 ignored issues – show Documentation Bug introduced 2017-02-26 14:52 UTC by Report Bug Copy Issue Report It seems like `is_null($proxy) ? new \C...roxy\NoProxy() : $proxy` of type `object<CViniciusSDias\Go...wler\Proxy\GoogleProxy>` is incompatible with the declared type `object<GoogleProxy>` of property `$proxy`. Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property. Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property.. Loading history...
32	13	}
33
34		/**
35		* Returns the 100 first found results for the specified search term
36		*
37		* @return ResultList
38		* @throws \GuzzleHttp\Exception\ServerException If the proxy was overused
39		* @throws \GuzzleHttp\Exception\ConnectException If the proxy is unavailable
40		*/
41	13	public function getResults(): ResultList
42		{
43		/** @var ResponseInterface $response */
44	13	$response = $this->proxy->getHttpResponse($this->url);
45	13	$stringResponse = (string) $response->getBody();
46	13	$domCrawler = new DomCrawler($stringResponse);
47	13	$googleResults = $domCrawler->filterXPath('//div[@class="g" and h3[@class="r" and a]]');
48	13	$resultList = new ResultList($googleResults->count());
49
50	13	foreach ($googleResults as $result) {
51	13	$resultCrawler = new DomCrawler($result);
52	13	$linkElement = $resultCrawler->filterXPath('//h3[@class="r"]/a')->getNode(0);
53	13	$resultLink = new Link($linkElement, 'http://google.com/');
		0 ignored issues – show Bug introduced 2017-07-02 18:03 UTC by Report Bug Copy Issue Report It seems like `$linkElement` defined by `$resultCrawler->filterXP...ss="r"]/a')->getNode(0)` on line `52` can be `null`; however, `Symfony\Component\DomCra...iElement::__construct()` does not accept `null`, maybe add an additional type check? Unless you are absolutely sure that the expression can never be null because of other conditions, we strongly recommend to add an additional type check to your code: /** @return stdClass\|null */ function mayReturnNull() { } function doesNotAcceptNull(stdClass $x) { } // With potential error. function withoutCheck() { $x = mayReturnNull(); doesNotAcceptNull($x); // Potential error here. } // Safe - Alternative 1 function withCheck1() { $x = mayReturnNull(); if ( ! $x instanceof stdClass) { throw new \LogicException('$x must be defined.'); } doesNotAcceptNull($x); } // Safe - Alternative 2 function withCheck2() { $x = mayReturnNull(); if ($x instanceof stdClass) { doesNotAcceptNull($x); } } Loading history...
54	13	$descriptionElement = $resultCrawler->filterXPath('//span[@class="st"]')->getNode(0);
55		try {
56	13	$googleResult = $this->parseResult($resultLink, $descriptionElement);
		0 ignored issues – show Bug introduced 2017-07-02 18:03 UTC by Report Bug Copy Issue Report It seems like `$descriptionElement` defined by `$resultCrawler->filterXP...ass="st"]')->getNode(0)` on line `54` can be `null`; however, `CViniciusSDias\GoogleCra...\Crawler::parseResult()` does not accept `null`, maybe add an additional type check? Unless you are absolutely sure that the expression can never be null because of other conditions, we strongly recommend to add an additional type check to your code: /** @return stdClass\|null */ function mayReturnNull() { } function doesNotAcceptNull(stdClass $x) { } // With potential error. function withoutCheck() { $x = mayReturnNull(); doesNotAcceptNull($x); // Potential error here. } // Safe - Alternative 1 function withCheck1() { $x = mayReturnNull(); if ( ! $x instanceof stdClass) { throw new \LogicException('$x must be defined.'); } doesNotAcceptNull($x); } // Safe - Alternative 2 function withCheck2() { $x = mayReturnNull(); if ($x instanceof stdClass) { doesNotAcceptNull($x); } } Loading history...
57	13	$resultList->addResult($googleResult);
58		} catch (InvalidResultException $invalidResult) {
59		// TODO Maybe log this exception. Other than that, there's nothing to do, cause it isn't an error.
60		}
61		}
62
63	13	return $resultList;
64		}
65
66		/**
67		* If $resultLink is a valid link, this method assembles the Result and adds it to $googleResults
68		*
69		* @param Link $resultLink
70		* @param DOMElement $descriptionElement
71		* @return Result
72		* @throws InvalidResultException
73		*/
74	13	private function parseResult(Link $resultLink, DOMElement $descriptionElement): Result
75		{
76	13	$description = $descriptionElement->nodeValue
77	13	?? 'A description for this result isn\'t available due to the robots.txt file.';
78
79	13	$googleResult = new Result();
80		$googleResult
81	13	->setTitle($resultLink->getNode()->nodeValue)
82	13	->setUrl($this->getUrl($resultLink->getUri()))
83	13	->setDescription($description);
84
85	13	return $googleResult;
86		}
87
88		/**
89		* Parses the URL using the parser provided by $proxy
90		*
91		* @param string $url
92		* @return string
93		* @throws InvalidResultException
94		*/
95	13	private function getUrl(string $url): string
96		{
97	13	return $this->proxy->parseUrl($url);
98		}
99		}
100

CViniciusSDias / google-crawler

Push — master ( 5fce14...dad0cb )

Crawler::getResults() B

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like