UriClient::request() - Code Metrics - Inspection of "Various improvements:" - VIPnytt/RobotsTxtParser - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( c07126...706ec6 )

by Jan-Petter

created 2016-07-15 17:38 UTC

UriClient::request() A

↳ Parent: UriClient

Complexity

Conditions	2
Paths	2

Size

Total Lines	50
Code Lines	39

Duplication

Lines	0
Ratio	0 %

Importance

Changes	3
Bugs	2	Features	1

Metric	Value
c	3
b	2
f	1
dl	0
loc	50
rs	9.3333
cc	2
eloc	39
nc	2
nop	1

<?php
namespace vipnytt\RobotsTxtParser;

use Composer\CaBundle\CaBundle;
use vipnytt\RobotsTxtParser\Parser\StatusCodeParser;
use vipnytt\RobotsTxtParser\Parser\UriParser;

/**
 * Class UriClient
 *
 * @see https://github.com/VIPnytt/RobotsTxtParser/blob/master/docs/methods/UriClient.md for documentation
 * @package vipnytt\RobotsTxtParser
 */
class UriClient extends TxtClient
{
    /**
     * User-agent
     */
    const CURL_USER_AGENT = 'RobotsTxtParser-VIPnytt/2.0 (+https://github.com/VIPnytt/RobotsTxtParser/blob/master/README.md)';

    /**
     * Base uri
     * @var string
     */
    private $base;

    /**
     * Header parser
     * @var Parser\HeaderParser
     */
    private $headerParser;

    /**
     * RequestClient timestamp
     * @var int
     */
    private $time;

    /**
     * Status code
     * @var int|null
     */
    private $rawStatusCode;

    /**
     * Effective uri
     * @var string
     */
    private $effective;

    /**
     * Cache-Control max-age
     * @var int
     */
    private $rawMaxAge;

    /**
     * Robots.txt contents
     * @var string
     */
    private $rawContents;

    /**
     * Robots.txt character encoding
     * @var string
     */
    private $rawEncoding;

    /**
     * RequestClient constructor.
     *
     * @param string $baseUri
     * @param array $curlOptions
     * @param int|null $byteLimit
     */
    public function __construct($baseUri, array $curlOptions = [], $byteLimit = self::BYTE_LIMIT)
    {
        $uriParser = new UriParser($baseUri);
        $this->base = $uriParser->base();
        if ($this->request($curlOptions) === false) {
            $this->time = time();
            $this->effective = $this->base;
            $this->rawStatusCode = null;
            $this->rawContents = '';
            $this->rawEncoding = self::ENCODING;
            $this->rawMaxAge = 0;
        }
        parent::__construct($this->base, $this->rawStatusCode, $this->rawContents, $this->rawEncoding, $this->effective, $byteLimit);
    }

    /**
     * cURL request
     *
     * @param array $options
     * @return bool
     */
    private function request($options = [])
    {
        $curl = curl_init();
        // Set default cURL options
        curl_setopt_array($curl, [
            CURLOPT_AUTOREFERER => true,
            CURLOPT_CAINFO => CaBundle::getSystemCaRootBundlePath(),
            CURLOPT_CONNECTTIMEOUT => 30,
            CURLOPT_ENCODING => 'identity',
            CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_NONE,
            CURLOPT_IPRESOLVE => CURL_IPRESOLVE_WHATEVER,
            CURLOPT_SSL_VERIFYHOST => 2,
            CURLOPT_SSL_VERIFYPEER => true,
            //CURLOPT_SSL_VERIFYSTATUS => true, // PHP 7.0.7
            CURLOPT_TIMEOUT => 120,
            CURLOPT_USERAGENT => self::CURL_USER_AGENT,
        ]);
        // Apply custom cURL options
        curl_setopt_array($curl, $options);
        $this->headerParser = new Parser\HeaderParser($curl);
        // Make sure these cURL options stays untouched
        curl_setopt_array($curl, [
            CURLOPT_FAILONERROR => false,
            CURLOPT_FOLLOWLOCATION => true,
            CURLOPT_FTPSSLAUTH => CURLFTPAUTH_DEFAULT,
            CURLOPT_HEADER => false,
            CURLOPT_HEADERFUNCTION => [$this->headerParser, 'curlCallback'],
            CURLOPT_HTTPAUTH => CURLAUTH_BASIC,
            CURLOPT_MAXREDIRS => self::MAX_REDIRECTS,
            CURLOPT_NOBODY => false,
            CURLOPT_PROTOCOLS => CURLPROTO_FTP | CURLPROTO_FTPS | CURLPROTO_HTTP | CURLPROTO_HTTPS | CURLPROTO_SFTP,
            CURLOPT_REDIR_PROTOCOLS => CURLPROTO_FTP | CURLPROTO_FTPS | CURLPROTO_HTTP | CURLPROTO_HTTPS | CURLPROTO_SFTP,
            CURLOPT_RETURNTRANSFER => true,
            CURLOPT_URL => $this->base . self::PATH,
            CURLOPT_USERPWD => 'anonymous:anonymous@',
        ]);
        // Execute cURL request
        if (($this->rawContents = curl_exec($curl)) === false) {
            // Request failed
            return false;
        }
        $this->time = time();
        $this->rawStatusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE); // also works with FTP status codes
        $uriParser = new UriParser(curl_getinfo($curl, CURLINFO_EFFECTIVE_URL));
        $this->effective = $uriParser->base();
        curl_close($curl);
        $this->rawEncoding = $this->headerParser->getCharset();
        $this->rawMaxAge = $this->headerParser->getMaxAge();
        return true;
    }

    /**
     * Base uri
     *
     * @return string
     */
    public function getBaseUri()
    {
        return $this->base;
    }

    /**
     * Effective uri
     *
     * @return string|null
     */
    public function getEffectiveUri()
    {
        return $this->effective;
    }

    /**
     * Status code
     *
     * @return int|null
     */
    public function getStatusCode()
    {
        $statusCodeParser = new StatusCodeParser($this->rawStatusCode, parse_url($this->effective, PHP_URL_SCHEME));
        return $statusCodeParser->isValid() ? $this->rawStatusCode : null;
    }

    /**
     * Body content
     *
     * @return string
     */
    public function getContents()
    {
        return $this->rawContents;
    }

    /**
     * Encoding
     *
     * @return string
     */
    public function getEncoding()
    {
        return $this->rawEncoding;
    }

    /**
     * Next update timestamp
     *
     * @return int
     */
    public function nextUpdate()
    {
        if (
            $this->rawStatusCode === 503 &&
            strpos($this->base, 'http') === 0
        ) {
            return $this->time + min(self::CACHE_TIME, $this->headerParser->getRetryAfter($this->time));
        }
        return $this->time + self::CACHE_TIME;
    }

    /**
     * Valid until timestamp
     *
     * @return int
     */
    public function validUntil()
    {
        return $this->time + max(self::CACHE_TIME, $this->rawMaxAge);
    }
}


1			<?php
2			namespace vipnytt\RobotsTxtParser;
3
4			use Composer\CaBundle\CaBundle;
5			use vipnytt\RobotsTxtParser\Parser\StatusCodeParser;
6			use vipnytt\RobotsTxtParser\Parser\UriParser;
7
8			/**
9			* Class UriClient
10			*
11			* @see https://github.com/VIPnytt/RobotsTxtParser/blob/master/docs/methods/UriClient.md for documentation
12			* @package vipnytt\RobotsTxtParser
13			*/
14			class UriClient extends TxtClient
15			{
16			/**
17			* User-agent
18			*/
19			const CURL_USER_AGENT = 'RobotsTxtParser-VIPnytt/2.0 (+https://github.com/VIPnytt/RobotsTxtParser/blob/master/README.md)';
20
21			/**
22			* Base uri
23			* @var string
24			*/
25			private $base;
26
27			/**
28			* Header parser
29			* @var Parser\HeaderParser
30			*/
31			private $headerParser;
32
33			/**
34			* RequestClient timestamp
35			* @var int
36			*/
37			private $time;
38
39			/**
40			* Status code
41			* @var int\|null
42			*/
43			private $rawStatusCode;
44
45			/**
46			* Effective uri
47			* @var string
48			*/
49			private $effective;
50
51			/**
52			* Cache-Control max-age
53			* @var int
54			*/
55			private $rawMaxAge;
56
57			/**
58			* Robots.txt contents
59			* @var string
60			*/
61			private $rawContents;
62
63			/**
64			* Robots.txt character encoding
65			* @var string
66			*/
67			private $rawEncoding;
68
69			/**
70			* RequestClient constructor.
71			*
72			* @param string $baseUri
73			* @param array $curlOptions
74			* @param int\|null $byteLimit
75			*/
76			public function __construct($baseUri, array $curlOptions = [], $byteLimit = self::BYTE_LIMIT)
77			{
78			$uriParser = new UriParser($baseUri);
79			$this->base = $uriParser->base();
80			if ($this->request($curlOptions) === false) {
81			$this->time = time();
82			$this->effective = $this->base;
83			$this->rawStatusCode = null;
84			$this->rawContents = '';
85			$this->rawEncoding = self::ENCODING;
86			$this->rawMaxAge = 0;
87			}
88			parent::__construct($this->base, $this->rawStatusCode, $this->rawContents, $this->rawEncoding, $this->effective, $byteLimit);
89			}
90
91			/**
92			* cURL request
93			*
94			* @param array $options
95			* @return bool
96			*/
97			private function request($options = [])
98			{
99			$curl = curl_init();
100			// Set default cURL options
101			curl_setopt_array($curl, [
102			CURLOPT_AUTOREFERER => true,
103			CURLOPT_CAINFO => CaBundle::getSystemCaRootBundlePath(),
104			CURLOPT_CONNECTTIMEOUT => 30,
105			CURLOPT_ENCODING => 'identity',
106			CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_NONE,
107			CURLOPT_IPRESOLVE => CURL_IPRESOLVE_WHATEVER,
108			CURLOPT_SSL_VERIFYHOST => 2,
109			CURLOPT_SSL_VERIFYPEER => true,
110			//CURLOPT_SSL_VERIFYSTATUS => true, // PHP 7.0.7
111			CURLOPT_TIMEOUT => 120,
112			CURLOPT_USERAGENT => self::CURL_USER_AGENT,
113			]);
114			// Apply custom cURL options
115			curl_setopt_array($curl, $options);
116			$this->headerParser = new Parser\HeaderParser($curl);
117			// Make sure these cURL options stays untouched
118			curl_setopt_array($curl, [
119			CURLOPT_FAILONERROR => false,
120			CURLOPT_FOLLOWLOCATION => true,
121			CURLOPT_FTPSSLAUTH => CURLFTPAUTH_DEFAULT,
122			CURLOPT_HEADER => false,
123			CURLOPT_HEADERFUNCTION => [$this->headerParser, 'curlCallback'],
124			CURLOPT_HTTPAUTH => CURLAUTH_BASIC,
125			CURLOPT_MAXREDIRS => self::MAX_REDIRECTS,
126			CURLOPT_NOBODY => false,
127			CURLOPT_PROTOCOLS => CURLPROTO_FTP \| CURLPROTO_FTPS \| CURLPROTO_HTTP \| CURLPROTO_HTTPS \| CURLPROTO_SFTP,
128			CURLOPT_REDIR_PROTOCOLS => CURLPROTO_FTP \| CURLPROTO_FTPS \| CURLPROTO_HTTP \| CURLPROTO_HTTPS \| CURLPROTO_SFTP,
129			CURLOPT_RETURNTRANSFER => true,
130			CURLOPT_URL => $this->base . self::PATH,
131			CURLOPT_USERPWD => 'anonymous:anonymous@',
132			]);
133			// Execute cURL request
134			if (($this->rawContents = curl_exec($curl)) === false) {
135			// Request failed
136			return false;
137			}
138			$this->time = time();
139			$this->rawStatusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE); // also works with FTP status codes
140			$uriParser = new UriParser(curl_getinfo($curl, CURLINFO_EFFECTIVE_URL));
141			$this->effective = $uriParser->base();
142			curl_close($curl);
143			$this->rawEncoding = $this->headerParser->getCharset();
144			$this->rawMaxAge = $this->headerParser->getMaxAge();
145			return true;
146			}
147
148			/**
149			* Base uri
150			*
151			* @return string
152			*/
153			public function getBaseUri()
154			{
155			return $this->base;
156			}
157
158			/**
159			* Effective uri
160			*
161			* @return string\|null
162			*/
163			public function getEffectiveUri()
164			{
165			return $this->effective;
166			}
167
168			/**
169			* Status code
170			*
171			* @return int\|null
172			*/
173			public function getStatusCode()
174			{
175			$statusCodeParser = new StatusCodeParser($this->rawStatusCode, parse_url($this->effective, PHP_URL_SCHEME));
176			return $statusCodeParser->isValid() ? $this->rawStatusCode : null;
177			}
178
179			/**
180			* Body content
181			*
182			* @return string
183			*/
184			public function getContents()
185			{
186			return $this->rawContents;
187			}
188
189			/**
190			* Encoding
191			*
192			* @return string
193			*/
194			public function getEncoding()
195			{
196			return $this->rawEncoding;
197			}
198
199			/**
200			* Next update timestamp
201			*
202			* @return int
203			*/
204			public function nextUpdate()
205			{
206			if (
207			$this->rawStatusCode === 503 &&
208			strpos($this->base, 'http') === 0
209			) {
210			return $this->time + min(self::CACHE_TIME, $this->headerParser->getRetryAfter($this->time));
211			}
212			return $this->time + self::CACHE_TIME;
213			}
214
215			/**
216			* Valid until timestamp
217			*
218			* @return int
219			*/
220			public function validUntil()
221			{
222			return $this->time + max(self::CACHE_TIME, $this->rawMaxAge);
223			}
224			}
225

VIPnytt / RobotsTxtParser

Push — master ( c07126...706ec6 )

UriClient::request() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like