Issues in Checker.php - All Issues - Inspection of "bugfix" - bootjp/crawler - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#31)

by Yoshiaki

created 2017-11-10 06:21 UTC

Checker.php (4 issues)

Labels

Severity

Upgrade to new PHP Analysis Engine

These results are based on our legacy PHP analysis, consider migrating to our new PHP analysis engine instead. Learn more

<?php


namespace Error;

require_once (__DIR__ . '/vendor/autoload.php');

/**
 * Description of Checker Main
 *
 * @author bootjp
 */
class Checker
{
    protected $client;

    protected $contentsSize = 500;

    protected $doubleCheck = true;

    protected $recursion = false;

    protected $garbage = [];

    protected $isContentsFetch = true;


    /**
     * initialisation.
     * @param array $args
     */
    public function __construct(array $args)
    {
        $this->client = new \GuzzleHttp\Client([
                'defaults' => [
                    'exceptions' => false,
                    'headers' => [
                        'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_2) ' .
                        'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36'
                    ]
                ]
            ]
        );
        if (array_key_exists('contentSize', $args)) {
            $this->contentsSize = (int) $args['contentSize'];
        }

        if (array_key_exists('doubleCheck', $args)) {
            $this->doubleCheck = (bool) $args['doubleCheck'];
        }

        if (array_key_exists('isContentsFetch', $args)) {
            $this->isContentsFetch = (bool) $args['isContentsFetch'];
        }

        if (array_key_exists('recursion', $args)) {
            $this->recursion = (bool) $args['recursion'];
        }

        if (array_key_exists('auth', $args)) {
            list($username, $password) = explode(':', $args['auth'], 2);
            $this->client->setDefaultOption('auth', [$username, $password]);
        }

    }

    /**
     * Wrapper
     * @param  mixed $url [require]
     * @return array
     * @throws \ErrorException
     * @throws \ReflectionException
     */
    public function start($url)
    {
        $urlList = [];
        $result = [];
        $result['white'] = [];
        $result['black'] = [];
        if (array_key_exists(0, $list)) {
            $getFlag = $list[0];
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
        }
        if (array_key_exists(1, $list)) {
            $this->recursion = $list[1];
        }

        if ((bool) $this->isContentsFetch) {
            echo 'Contents fetching..';
            $url = $this->fetchByContents($url);

            if ((bool) $this->recursion) {
                $url = $this->urlFilter($url);
            }
        }

        if (is_null($url)) {
            throw new \RuntimeException('Start URL is not null.');
        } else if (is_array($url)) {
            $urlList = $this->urlFilter($url);
        } else if (is_string($url)) {
            $urlList[] = $url;
        } else if (is_object($url)) {
            $urlList[] = (string) $url;
        }

        echo "\n";
        echo 'Cheking..';

        foreach ($urlList as $key => $url) {
            try {
                $metaData = $this->client->get($url);
            } catch (\Exception $e) {
                echo "\n {$url}\t {$e->getMessage()}";
            }
            $hardCheck = (array) $this->hardCheckByHeader($metaData);
            $softCheck = (array) $this->softCheckByContents($metaData);

            if ($hardCheck['result'] && $softCheck['result']) {
                $result['white'][$key]['url'] = $url;
                $result['white'][$key]['status'] = 'OK';
            } else {
                $result['black'][$key]['url'] = $url;
                $result['black'][$key]['status'] = array_key_exists('status', $hardCheck) ? $hardCheck['status'] : $softCheck['status'];
            }

            usleep(500000);
            echo '.';
        }
        $result['UnknownLinks'] = $this->garbage;

        return $result;
    }

    /**
     * Fetch Page Contents Links
     * @param  mixed $baseUrl
     * @return array URlList
     * @throws \ErrorException
     */
    private function fetchByContents($baseUrl)
    {
        $urlList = [];
        $matches = [];
        $urlList['baseUrl'] = (string) $baseUrl;
        try {
            $contents = $this->client->get($baseUrl)->getBody()->getContents();
        } catch (\Exception $e) {
            echo "\n {$baseUrl}\t {$e->getMessage()}";
        }

        preg_match_all('{<a.+?href=[\"|\'](?<url>.+?)[\"\|\'].*?>}is', $contents, $matches);

        if (!array_key_exists('url', $matches)) {
            throw new \RuntimeException('Not match contents on url.');
        }

        foreach ($matches['url'] as $url) {

            if (preg_match('{https?://[\w/:%#\$&\?\(\)~\.=\+\-]+}i', $url)) {
                $urlList[] = $url;
            } else if (preg_match('{^https?:\/\/[\w/:%#\$&\?\(\)~\.=\+\-]+$}i', $baseUrl . $url)) {
                if (preg_match("{(^#[A-Z0-9].+?$)}i", $url)) {
                    $this->garbage[] = $url;
                } else if (preg_match("#javascript.*#i", $url)) {
                    $this->garbage[] = $url;
                } else {
                    // start slash ?
                    $startSlash = substr($url, 0, 1) === '/';
                    $secondSlash = substr($url, 1, 1) === '/';
                    if ($startSlash && $secondSlash) {
                        $parsedUrl = parse_url($baseUrl);
                        $urlList[] = $parsedUrl['scheme'] . ':' . $url;
                    } else if ($startSlash) {
                        // end is slash?
                        $parsedUrl = parse_url($baseUrl);
                        if (substr($baseUrl, -1, 1) === '/') {
                            // has slash
                            $root = $parsedUrl['scheme'] . '://' . $parsedUrl['host'];
                        } else {
                            // add slash
                            $root = $parsedUrl['scheme'] . '://' . $parsedUrl['host'] . '/';
                        }
                        $urlList[] = $root . $url;
                    } else {
                        $urlList[] = $baseUrl . $url;
                    }
                }
            } else {
                $this->garbage[] = $url;
            }

            usleep(500000);
            echo '.';
        }

        return array_unique($urlList);
    }

    /**
     * Error check by header
     * @param \GuzzleHttp\Message\Response $metaData
     * @return array
     */
    private function hardCheckByHeader($metaData)

    {
        $headers = array_change_key_case($metaData->getHeaders());
        $statusCode = (int) $metaData->getStatusCode();

        $isErrorPageCode = [
            '40x' => [401, 403, 404],
            '50x' => [500, 502, 503],
            '30x' => [301, 302, 308]
        ];

        foreach($isErrorPageCode as $errorType => $statuses) {
            if (in_array($statusCode, $statuses)) {
                return [
                    'result' => false,
                    'status' => "NG : status code {$errorType}"
                ];
            }
        }

        if ($statusCode === 200 && $statusCode === 304) {
            return [
                'result' => true
            ];
        }

        if (array_key_exists('content-length', $headers) && $headers['content-length'][0] < $this->contentsSize) {
            return [
                'result' => false,
                'status' => 'NG : contentsSize'
            ];
        }

        return [
            'result' => true
        ];
    }

    /**
     * Soft404 check by contents Length
     * @param \GuzzleHttp\Message\Response $metaData
     * @return array
     */
    public function softCheckByContents($metaData)
    {
        if ($metaData->getBody()->getSize() <= $this->contentsSize) {
            return [
                'result' => false,
                'status' => 'NG : contentsSize'
            ];
        }

        if ($this->doubleCheck) {
            $result = $this->softCheckByContentsWords($metaData);
            if (!$result['result']) {
                return [
                    'result' => $result['result'],
                    'status' => $result['status']
                ];
            }
        }

        return [
            'result' => true
        ];
    }

    /**
     * Soft404 Error check by words
     * @param \GuzzleHttp\Message\Response $metaData
     * @return array Result
     */
    private function softCheckByContentsWords($metaData)
    {
        foreach (self::getSoftErrorWords() as $word) {
            if (mb_stripos($metaData->getBody()->getContents(), $word) !== false) {
                return [
                    'result' => false,
                    'status' => 'NG WORD : ' . $word
                ];
            }
        }

        return [
            'result' => true
        ];

    }

    /**
     * Return soft404 Page on Words.
     * @param  none
     * @return array
     */
    private static function getSoftErrorWords()
    {
        return file(__DIR__ . '/ErrorPageWords.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
    }

    /**
     * multidimensional array to single arry comvert.
     * @param array $urlList
     * @return array URLLIST
     */
    private function urlFilter(array $urlList)
    {
        $result = [];
        array_walk_recursive($urlList, function($v) use (&$result) {
            $result[] = $v;
        });

        return array_values(array_unique($result));
    }
}


1			<?php
			0 ignored issues – show Coding Style Compatibility introduced 2016-06-04 13:05 UTC by Report Bug Copy Issue Report Show Similar Issues like this For compatibility and reusability of your code, PSR1 recommends that a file should introduce either new symbols (like classes, functions, etc.) or have side-effects (like outputting something, or including other files), but not both at the same time. The first symbol is defined on line 12 and the first side effect is on line 5. The PSR-1: Basic Coding Standard recommends that a file should either introduce new symbols, that is classes, functions, constants or similar, or have side effects. Side effects are anything that executes logic, like for example printing output, changing ini settings or writing to a file. The idea behind this recommendation is that merely auto-loading a class should not change the state of an application. It also promotes a cleaner style of programming and makes your code less prone to errors, because the logic is not spread out all over the place. To learn more about the PSR-1, please see the PHP-FIG site on the PSR-1. Loading history...
2
3			namespace Error;
4
5			require_once (__DIR__ . '/vendor/autoload.php');
6
7			/**
8			* Description of Checker Main
9			*
10			* @author bootjp
11			*/
12			class Checker
13			{
14			protected $client;
15
16			protected $contentsSize = 500;
17
18			protected $doubleCheck = true;
19
20			protected $recursion = false;
21
22			protected $garbage = [];
23
24			protected $isContentsFetch = true;
25
26
27			/**
28			* initialisation.
29			* @param array $args
30			*/
31			public function __construct(array $args)
32			{
33			$this->client = new \GuzzleHttp\Client([
34			'defaults' => [
35			'exceptions' => false,
36			'headers' => [
37			'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_2) ' .
38			'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36'
39			]
40			]
41			]
42			);
43			if (array_key_exists('contentSize', $args)) {
44			$this->contentsSize = (int) $args['contentSize'];
45			}
46
47			if (array_key_exists('doubleCheck', $args)) {
48			$this->doubleCheck = (bool) $args['doubleCheck'];
49			}
50
51			if (array_key_exists('isContentsFetch', $args)) {
52			$this->isContentsFetch = (bool) $args['isContentsFetch'];
53			}
54
55			if (array_key_exists('recursion', $args)) {
56			$this->recursion = (bool) $args['recursion'];
57			}
58
59			if (array_key_exists('auth', $args)) {
60			list($username, $password) = explode(':', $args['auth'], 2);
61			$this->client->setDefaultOption('auth', [$username, $password]);
62			}
63
64			}
65
66			/**
67			* Wrapper
68			* @param mixed $url [require]
69			* @return array
70			* @throws \ErrorException
71			* @throws \ReflectionException
72			*/
73			public function start($url)
74			{
75			$urlList = [];
76			$result = [];
77			$result['white'] = [];
78			$result['black'] = [];
79			if (array_key_exists(0, $list)) {
80			$getFlag = $list[0];
			0 ignored issues – show Bug introduced 2017-11-10 06:23 UTC by Report Bug Copy Issue Report Show Similar Issues like this The variable `$list` does not exist. Did you forget to declare it? This check marks access to variables or properties that have not been declared yet. While PHP has no explicit notion of declaring a variable, accessing it before a value is assigned to it is most likely a bug. Loading history... Unused Code introduced 2017-11-10 06:23 UTC by Report Bug Copy Issue Report Show Similar Issues like this `$getFlag` is not used, you could remove the assignment. This check looks for variable assignements that are either overwritten by other assignments or where the variable is not used subsequently. $myVar = 'Value'; $higher = false; if (rand(1, 6) > 3) { $higher = true; } else { $higher = false; } Both the `$myVar` assignment in line 1 and the `$higher` assignment in line 2 are dead. The first because `$myVar` is never used and the second because `$higher` is always overwritten for every possible time line. Loading history...
81			}
82			if (array_key_exists(1, $list)) {
83			$this->recursion = $list[1];
84			}
85
86			if ((bool) $this->isContentsFetch) {
87			echo 'Contents fetching..';
88			$url = $this->fetchByContents($url);
89
90			if ((bool) $this->recursion) {
91			$url = $this->urlFilter($url);
92			}
93			}
94
95			if (is_null($url)) {
96			throw new \RuntimeException('Start URL is not null.');
97			} else if (is_array($url)) {
98			$urlList = $this->urlFilter($url);
99			} else if (is_string($url)) {
100			$urlList[] = $url;
101			} else if (is_object($url)) {
102			$urlList[] = (string) $url;
103			}
104
105			echo "\n";
106			echo 'Cheking..';
107
108			foreach ($urlList as $key => $url) {
109			try {
110			$metaData = $this->client->get($url);
111			} catch (\Exception $e) {
112			echo "\n {$url}\t {$e->getMessage()}";
113			}
114			$hardCheck = (array) $this->hardCheckByHeader($metaData);
115			$softCheck = (array) $this->softCheckByContents($metaData);
116
117			if ($hardCheck['result'] && $softCheck['result']) {
118			$result['white'][$key]['url'] = $url;
119			$result['white'][$key]['status'] = 'OK';
120			} else {
121			$result['black'][$key]['url'] = $url;
122			$result['black'][$key]['status'] = array_key_exists('status', $hardCheck) ? $hardCheck['status'] : $softCheck['status'];
123			}
124
125			usleep(500000);
126			echo '.';
127			}
128			$result['UnknownLinks'] = $this->garbage;
129
130			return $result;
131			}
132
133			/**
134			* Fetch Page Contents Links
135			* @param mixed $baseUrl
136			* @return array URlList
137			* @throws \ErrorException
138			*/
139			private function fetchByContents($baseUrl)
140			{
141			$urlList = [];
142			$matches = [];
143			$urlList['baseUrl'] = (string) $baseUrl;
144			try {
145			$contents = $this->client->get($baseUrl)->getBody()->getContents();
146			} catch (\Exception $e) {
147			echo "\n {$baseUrl}\t {$e->getMessage()}";
148			}
149
150			preg_match_all('{<a.+?href=[\"\|\'](?<url>.+?)[\"\\|\'].*?>}is', $contents, $matches);
151
152			if (!array_key_exists('url', $matches)) {
153			throw new \RuntimeException('Not match contents on url.');
154			}
155
156			foreach ($matches['url'] as $url) {
157
158			if (preg_match('{https?://[\w/:%#\$&\?\(\)~\.=\+\-]+}i', $url)) {
159			$urlList[] = $url;
160			} else if (preg_match('{^https?:\/\/[\w/:%#\$&\?\(\)~\.=\+\-]+$}i', $baseUrl . $url)) {
161			if (preg_match("{(^#[A-Z0-9].+?$)}i", $url)) {
162			$this->garbage[] = $url;
163			} else if (preg_match("#javascript.*#i", $url)) {
164			$this->garbage[] = $url;
165			} else {
166			// start slash ?
167			$startSlash = substr($url, 0, 1) === '/';
168			$secondSlash = substr($url, 1, 1) === '/';
169			if ($startSlash && $secondSlash) {
170			$parsedUrl = parse_url($baseUrl);
171			$urlList[] = $parsedUrl['scheme'] . ':' . $url;
172			} else if ($startSlash) {
173			// end is slash?
174			$parsedUrl = parse_url($baseUrl);
175			if (substr($baseUrl, -1, 1) === '/') {
176			// has slash
177			$root = $parsedUrl['scheme'] . '://' . $parsedUrl['host'];
178			} else {
179			// add slash
180			$root = $parsedUrl['scheme'] . '://' . $parsedUrl['host'] . '/';
181			}
182			$urlList[] = $root . $url;
183			} else {
184			$urlList[] = $baseUrl . $url;
185			}
186			}
187			} else {
188			$this->garbage[] = $url;
189			}
190
191			usleep(500000);
192			echo '.';
193			}
194
195			return array_unique($urlList);
196			}
197
198			/**
199			* Error check by header
200			* @param \GuzzleHttp\Message\Response $metaData
201			* @return array
202			*/
203			private function hardCheckByHeader($metaData)
			0 ignored issues – show Unused Code introduced 2017-11-10 05:41 UTC by Report Bug Copy Issue Report Show Similar Issues like this This method is not used, and could be removed. Loading history...
204			{
205			$headers = array_change_key_case($metaData->getHeaders());
206			$statusCode = (int) $metaData->getStatusCode();
207
208			$isErrorPageCode = [
209			'40x' => [401, 403, 404],
210			'50x' => [500, 502, 503],
211			'30x' => [301, 302, 308]
212			];
213
214			foreach($isErrorPageCode as $errorType => $statuses) {
215			if (in_array($statusCode, $statuses)) {
216			return [
217			'result' => false,
218			'status' => "NG : status code {$errorType}"
219			];
220			}
221			}
222
223			if ($statusCode === 200 && $statusCode === 304) {
224			return [
225			'result' => true
226			];
227			}
228
229			if (array_key_exists('content-length', $headers) && $headers['content-length'][0] < $this->contentsSize) {
230			return [
231			'result' => false,
232			'status' => 'NG : contentsSize'
233			];
234			}
235
236			return [
237			'result' => true
238			];
239			}
240
241			/**
242			* Soft404 check by contents Length
243			* @param \GuzzleHttp\Message\Response $metaData
244			* @return array
245			*/
246			public function softCheckByContents($metaData)
247			{
248			if ($metaData->getBody()->getSize() <= $this->contentsSize) {
249			return [
250			'result' => false,
251			'status' => 'NG : contentsSize'
252			];
253			}
254
255			if ($this->doubleCheck) {
256			$result = $this->softCheckByContentsWords($metaData);
257			if (!$result['result']) {
258			return [
259			'result' => $result['result'],
260			'status' => $result['status']
261			];
262			}
263			}
264
265			return [
266			'result' => true
267			];
268			}
269
270			/**
271			* Soft404 Error check by words
272			* @param \GuzzleHttp\Message\Response $metaData
273			* @return array Result
274			*/
275			private function softCheckByContentsWords($metaData)
276			{
277			foreach (self::getSoftErrorWords() as $word) {
278			if (mb_stripos($metaData->getBody()->getContents(), $word) !== false) {
279			return [
280			'result' => false,
281			'status' => 'NG WORD : ' . $word
282			];
283			}
284			}
285
286			return [
287			'result' => true
288			];
289
290			}
291
292			/**
293			* Return soft404 Page on Words.
294			* @param none
295			* @return array
296			*/
297			private static function getSoftErrorWords()
298			{
299			return file(__DIR__ . '/ErrorPageWords.txt', FILE_IGNORE_NEW_LINES \| FILE_SKIP_EMPTY_LINES);
300			}
301
302			/**
303			* multidimensional array to single arry comvert.
304			* @param array $urlList
305			* @return array URLLIST
306			*/
307			private function urlFilter(array $urlList)
308			{
309			$result = [];
310			array_walk_recursive($urlList, function($v) use (&$result) {
311			$result[] = $v;
312			});
313
314			return array_values(array_unique($result));
315			}
316			}
317

bootjp / crawler

Pull Request — master (#31)

Checker.php (4 issues)

Labels

Severity

Introduced By

Upgrade to new PHP Analysis Engine

Duplication Side-by-Side

Filter issues like