Import::girlFromUrl() - Code Metrics - SierraTecnologia/integrations - Measure and Improve Code Quality continuously with Scrutinizer

Import::girlFromUrl() A
last analyzed 2021-05-27 22:55 UTC

↳ Parent: Import

Complexity

Conditions	1
Paths	1

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
nc	1
nop	1
dl	0
loc	10
rs	9.9332
c	0
b	0
f	0

<?php

namespace Integrations\Connectors\PhotoAcompanhante;

use Log;
use App\Models\User;
use QL\QueryList;
use Fabrica\Tools\Proxy;

class Import extends PhotoAcompanhante
{

    /**
     * Import Girl From Url
     */
    public static function girlFromUrl($url)
    {
        // @todo Fazer
        return true;
        QueryList::get($url, '', Proxy::getOpts())->map(
function fx() {
    try {
        doSomething();
        return true;
    }
    catch (\Exception $e) {
        return false;
    }

    return false;
}
            function ($img) {
                dd('Import Img', $img);
            }
        );
    }

    /**
     * Home Folders
     */
    public function girls()
    {
        QueryList::get(self::$URL)->find('.anuncio')->map(
            function ($img) {
                $nameAndPhone = $img->find('.anuncio_img')->children('img')->attrs('alt');
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}


                $nameAndPhone = $img->find('.anuncio_categoria')->map(
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
                    function ($data) {
                        dd('Import Data', $data);
                    }
                );
            }
        );

    }

    /**
     * Girl Page
     */
    public function girl()
    {


    }

    /**
     * others Page
     */
    public function others()
    {

        $ql = QueryList::get('https://www.google.co.jp/search?q=QueryList');

        $ql->find('title')->text(); //The page title
        $ql->find('meta[name=keywords]')->content; //The page keywords

        $ql->find('h3>a')->texts(); //Get a list of search results titles
        $ql->find('h3>a')->attrs('href'); //Get a list of search results links

        $ql->find('img')->src; //Gets the link address of the first image
        $ql->find('img:eq(1)')->src; //Gets the link address of the second image
        $ql->find('img')->eq(2)->src; //Gets the link address of the third image
        // Loop all the images
        $ql->find('img')->map(
            function ($img) {
                echo $img->alt;  //Print the alt attribute of the image
            }
        );

        // More usage

        $ql->find('#head')->append('<div>Append content</div>')->find('div')->htmls();
        $ql->find('.two')->children('img')->attrs('alt'); // Get the class is the "two" element under all img child nodes
        // Loop class is the "two" element under all child nodes
        $data = $ql->find('.two')->children()->map(
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
            function ($item) {
                // Use "is" to determine the node type
                if($item->is('a')) {
                    return $item->text();
                }elseif($item->is('img')) {
                    return $item->alt;
                }
            }
        );

        // $ql->find('a')->attr('href', 'newVal')->removeClass('className')->html('newHtml')->...
        // $ql->find('div > p')->add('div > ul')->filter(':has(a)')->find('p:first')->nextAll()->andSelf()->...
        // $ql->find('div.old')->replaceWith( $ql->find('div.new')->clone())->appendTo('.trash')->prepend('Deleted')->...

        // List crawl

        // Crawl the title and link of the Google search results list:

        $data = QueryList::get('https://www.google.co.jp/search?q=QueryList')
            // Set the crawl rules
            ->rules(
                [ 
                'title'=>array('h3','text'),
                'link'=>array('h3>a','href')
                ]
            )
            ->query()->getData();

        print_r($data->all());

        // Results:

        // Array
        // (
        //     [0] => Array
        //         (
        //             [title] => Angular - QueryList
        //             [link] => https://angular.io/api/core/QueryList
        //         )
        //     [1] => Array
        //         (
        //             [title] => QueryList | @angular/core - Angularリファレンス - Web Creative Park
        //             [link] => http://www.webcreativepark.net/angular/querylist/
        //         )
        //     [2] => Array
        //         (
        //             [title] => QueryListにQueryを追加したり、追加されたことを感知する | TIPS ...
        //             [link] => http://www.webcreativepark.net/angular/querylist_query_add_subscribe/
        //         )
        //         //...
        // )

        // Encode convert

        // Out charset :UTF-8
        // In charset :GB2312
        QueryList::get('https://top.etao.com')->encoding('UTF-8', 'GB2312')->find('a')->texts();

        // Out charset:UTF-8
        // In charset:Automatic Identification
        QueryList::get('https://top.etao.com')->encoding('UTF-8')->find('a')->texts();

        // HTTP Client (GuzzleHttp)

        //     Carry cookie login GitHub

        //Crawl GitHub content
        $ql = QueryList::get(
            'https://github.com', 'param1=testvalue & params2=somevalue', [
            'headers' => [
            // Fill in the cookie from the browser
            'Cookie' => 'SINAGLOBAL=546064; wb_cmtLike_2112031=1; wvr=6;....'
            ]
            ]
        );
        //echo $ql->getHtml();
        $userName = $ql->find('.header-nav-current-user>.css-truncate-target')->text();
        echo $userName;

            // Use the Http proxy

        $urlParams = ['param1' => 'testvalue','params2' => 'somevalue'];
        $opts = [
            // Set the http proxy
            'proxy' => 'http://222.141.11.17:8118',
            //Set the timeout time in seconds
            'timeout' => 30,
            // Fake HTTP headers
            'headers' => [
                'Referer' => 'https://querylist.cc/',
                'User-Agent' => 'testing/1.0',
                'Accept'     => 'application/json',
                'X-Foo'      => ['Bar', 'Baz'],
                'Cookie'    => 'abc=111;xxx=222'
            ]
        ];
        $ql->get('http://httpbin.org/get', $urlParams, $opts);
        // echo $ql->getHtml();

            // Analog login

        // Post login
        $ql = QueryList::post(
            'http://xxxx.com/login', [
            'username' => 'admin',
            'password' => '123456'
            ]
        )->get('http://xxx.com/admin');
        // Crawl pages that need to be logged in to access
        $ql->get('http://xxx.com/admin/page');
        //echo $ql->getHtml();

        // Submit forms

        // Login GitHub

        // Get the QueryList instance
        $ql = QueryList::getInstance();
        // Get the login form
        $form = $ql->get('https://github.com/login')->find('form');

        // Fill in the GitHub username and password
        $form->find('input[name=login]')->val('your github username or email');
        $form->find('input[name=password]')->val('your github password');

        // Serialize the form data
        $fromData = $form->serializeArray();
        $postData = [];
        foreach ($fromData as $item) {
            $postData[$item['name']] = $item['value'];
        }

        // Submit the login form
        $actionUrl = 'https://github.com'.$form->attr('action');
        $ql->post($actionUrl, $postData);
        // To determine whether the login is successful
        // echo $ql->getHtml();
        $userName = $ql->find('.header-nav-current-user>.css-truncate-target')->text();
        if($userName) {
            echo 'Login successful ! Welcome:'.$userName;
        }else{
            echo 'Login failed !';
        }

        // Bind function extension

        // Customize the extension of a myHttp method:

        $ql = QueryList::getInstance();

        //Bind a `myHttp` method to the QueryList object
        $ql->bind(
            'myHttp', function ($url) {
                // $this is the current QueryList object
                $html = file_get_contents($url);
                $this->setHtml($html);
                return $this;
            }
        );

        // And then you can call by the name of the binding
        $data = $ql->myHttp('https://toutiao.io')->find('h3 a')->texts();
        print_r($data->all());

        // Or package to class, and then bind:

        $ql->bind(
            'myHttp', function ($url) {
                return new MyHttp($this, $url);
            }
        );

        // Plugin used

            // Use the PhantomJS plugin to crawl JavaScript dynamically rendered pages:

        // Set the PhantomJS binary file path during installation
        $ql = QueryList::use(PhantomJs::class, '/usr/local/bin/phantomjs');

        // Crawl「500px」all picture links
        $data = $ql->browser('https://500px.com/editors')->find('img')->attrs('src');
        print_r($data->all());

        // Use the HTTP proxy
        $ql->browser(
            'https://500px.com/editors', false, [
            '--proxy' => '192.168.1.42:8080',
            '--proxy-type' => 'http'
            ]
        );

            // Using the CURL multithreading plug-in, multi-threaded crawling GitHub trending :

        $ql = QueryList::use(CurlMulti::class);
        $ql->curlMulti(
            [
            'https://github.com/trending/php',
            'https://github.com/trending/go',
            //.....more urls
            ]
        )
        // Called if task is success
            ->success(
                function (QueryList $ql,CurlMulti $curl,$r) {
                    echo "Current url:{$r['info']['url']} \r\n";
                    $data = $ql->find('h3 a')->texts();
                    print_r($data->all());
                }
            )
        // Task fail callback
        ->error(
            function ($errorInfo,CurlMulti $curl) {

                echo "Current url:{$errorInfo['info']['url']} \r\n";
                print_r($errorInfo['error']);
            }
        )
        ->start(
            [
            // Maximum number of threads
            'maxThread' => 10,
            // Number of error retries
            'maxTry' => 3,
            ]
        );

        // Plugins

        //     jae-jae/QueryList-PhantomJS:Use PhantomJS to crawl Javascript dynamically rendered page.
        //     jae-jae/QueryList-CurlMulti : Curl multi threading.
        //     jae-jae/QueryList-AbsoluteUrl : Converting relative urls to absolute.
        //     jae-jae/QueryList-Rule-Google : Google searcher.
        //     jae-jae/QueryList-Rule-Baidu : Baidu searcher.

        // View more QueryList plugins and QueryList-based products: QueryList Community
    }
}


1			<?php
2
3			namespace Integrations\Connectors\PhotoAcompanhante;
4
5			use Log;
6			use App\Models\User;
7			use QL\QueryList;
8			use Fabrica\Tools\Proxy;
9
10			class Import extends PhotoAcompanhante
11			{
12
13			/**
14			* Import Girl From Url
15			*/
16			public static function girlFromUrl($url)
17			{
18			// @todo Fazer
19			return true;
20			QueryList::get($url, '', Proxy::getOpts())->map(
			0 ignored issues – show Unused Code introduced 2020-07-28 00:54 UTC by Report Bug Copy Issue Report `\QL\QueryList::get($url,...Import Img', $img); });` does not seem to be reachable. This check looks for unreachable code. It uses sophisticated control flow analysis techniques to find statements which will never be executed. Unreachable code is most often the result of `return`, `die` or `exit` statements that have been added for debug purposes. function fx() { try { doSomething(); return true; } catch (\Exception $e) { return false; } return false; } In the above example, the last `return false` will never be executed, because a return statement has already been met in every possible execution path. Loading history...
21			function ($img) {
22			dd('Import Img', $img);
23			}
24			);
25			}
26
27			/**
28			* Home Folders
29			*/
30			public function girls()
31			{
32			QueryList::get(self::$URL)->find('.anuncio')->map(
33			function ($img) {
34			$nameAndPhone = $img->find('.anuncio_img')->children('img')->attrs('alt');
			0 ignored issues – show Unused Code introduced 2020-07-28 00:54 UTC by Report Bug Copy Issue Report `$nameAndPhone` 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...
35
36
37			$nameAndPhone = $img->find('.anuncio_categoria')->map(
			0 ignored issues – show Unused Code introduced 2020-07-28 00:54 UTC by Report Bug Copy Issue Report `$nameAndPhone` 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 `$higher` is always overwritten for every possible time line. Loading history...
38			function ($data) {
39			dd('Import Data', $data);
40			}
41			);
42			}
43			);
44
45			}
46
47			/**
48			* Girl Page
49			*/
50			public function girl()
51			{
52
53
54			}
55
56			/**
57			* others Page
58			*/
59			public function others()
60			{
61
62			$ql = QueryList::get('https://www.google.co.jp/search?q=QueryList');
63
64			$ql->find('title')->text(); //The page title
65			$ql->find('meta[name=keywords]')->content; //The page keywords
66
67			$ql->find('h3>a')->texts(); //Get a list of search results titles
68			$ql->find('h3>a')->attrs('href'); //Get a list of search results links
69
70			$ql->find('img')->src; //Gets the link address of the first image
71			$ql->find('img:eq(1)')->src; //Gets the link address of the second image
72			$ql->find('img')->eq(2)->src; //Gets the link address of the third image
73			// Loop all the images
74			$ql->find('img')->map(
75			function ($img) {
76			echo $img->alt; //Print the alt attribute of the image
77			}
78			);
79
80			// More usage
81
82			$ql->find('#head')->append('<div>Append content</div>')->find('div')->htmls();
83			$ql->find('.two')->children('img')->attrs('alt'); // Get the class is the "two" element under all img child nodes
84			// Loop class is the "two" element under all child nodes
85			$data = $ql->find('.two')->children()->map(
			0 ignored issues – show Unused Code introduced 2020-07-28 00:54 UTC by Report Bug Copy Issue Report `$data` 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 `$higher` is always overwritten for every possible time line. Loading history...
86			function ($item) {
87			// Use "is" to determine the node type
88			if($item->is('a')) {
89			return $item->text();
90			}elseif($item->is('img')) {
91			return $item->alt;
92			}
93			}
94			);
95
96			// $ql->find('a')->attr('href', 'newVal')->removeClass('className')->html('newHtml')->...
97			// $ql->find('div > p')->add('div > ul')->filter(':has(a)')->find('p:first')->nextAll()->andSelf()->...
98			// $ql->find('div.old')->replaceWith( $ql->find('div.new')->clone())->appendTo('.trash')->prepend('Deleted')->...
99
100			// List crawl
101
102			// Crawl the title and link of the Google search results list:
103
104			$data = QueryList::get('https://www.google.co.jp/search?q=QueryList')
105			// Set the crawl rules
106			->rules(
107			[
108			'title'=>array('h3','text'),
109			'link'=>array('h3>a','href')
110			]
111			)
112			->query()->getData();
113
114			print_r($data->all());
115
116			// Results:
117
118			// Array
119			// (
120			// [0] => Array
121			// (
122			// [title] => Angular - QueryList
123			// [link] => https://angular.io/api/core/QueryList
124			// )
125			// [1] => Array
126			// (
127			// [title] => QueryList \| @angular/core - Angularリファレンス - Web Creative Park
128			// [link] => http://www.webcreativepark.net/angular/querylist/
129			// )
130			// [2] => Array
131			// (
132			// [title] => QueryListにQueryを追加したり、追加されたことを感知する \| TIPS ...
133			// [link] => http://www.webcreativepark.net/angular/querylist_query_add_subscribe/
134			// )
135			// //...
136			// )
137
138			// Encode convert
139
140			// Out charset :UTF-8
141			// In charset :GB2312
142			QueryList::get('https://top.etao.com')->encoding('UTF-8', 'GB2312')->find('a')->texts();
143
144			// Out charset:UTF-8
145			// In charset:Automatic Identification
146			QueryList::get('https://top.etao.com')->encoding('UTF-8')->find('a')->texts();
147
148			// HTTP Client (GuzzleHttp)
149
150			// Carry cookie login GitHub
151
152			//Crawl GitHub content
153			$ql = QueryList::get(
154			'https://github.com', 'param1=testvalue & params2=somevalue', [
155			'headers' => [
156			// Fill in the cookie from the browser
157			'Cookie' => 'SINAGLOBAL=546064; wb_cmtLike_2112031=1; wvr=6;....'
158			]
159			]
160			);
161			//echo $ql->getHtml();
162			$userName = $ql->find('.header-nav-current-user>.css-truncate-target')->text();
163			echo $userName;
164
165			// Use the Http proxy
166
167			$urlParams = ['param1' => 'testvalue','params2' => 'somevalue'];
168			$opts = [
169			// Set the http proxy
170			'proxy' => 'http://222.141.11.17:8118',
171			//Set the timeout time in seconds
172			'timeout' => 30,
173			// Fake HTTP headers
174			'headers' => [
175			'Referer' => 'https://querylist.cc/',
176			'User-Agent' => 'testing/1.0',
177			'Accept' => 'application/json',
178			'X-Foo' => ['Bar', 'Baz'],
179			'Cookie' => 'abc=111;xxx=222'
180			]
181			];
182			$ql->get('http://httpbin.org/get', $urlParams, $opts);
183			// echo $ql->getHtml();
184
185			// Analog login
186
187			// Post login
188			$ql = QueryList::post(
189			'http://xxxx.com/login', [
190			'username' => 'admin',
191			'password' => '123456'
192			]
193			)->get('http://xxx.com/admin');
194			// Crawl pages that need to be logged in to access
195			$ql->get('http://xxx.com/admin/page');
196			//echo $ql->getHtml();
197
198			// Submit forms
199
200			// Login GitHub
201
202			// Get the QueryList instance
203			$ql = QueryList::getInstance();
204			// Get the login form
205			$form = $ql->get('https://github.com/login')->find('form');
206
207			// Fill in the GitHub username and password
208			$form->find('input[name=login]')->val('your github username or email');
209			$form->find('input[name=password]')->val('your github password');
210
211			// Serialize the form data
212			$fromData = $form->serializeArray();
213			$postData = [];
214			foreach ($fromData as $item) {
215			$postData[$item['name']] = $item['value'];
216			}
217
218			// Submit the login form
219			$actionUrl = 'https://github.com'.$form->attr('action');
220			$ql->post($actionUrl, $postData);
221			// To determine whether the login is successful
222			// echo $ql->getHtml();
223			$userName = $ql->find('.header-nav-current-user>.css-truncate-target')->text();
224			if($userName) {
225			echo 'Login successful ! Welcome:'.$userName;
226			}else{
227			echo 'Login failed !';
228			}
229
230			// Bind function extension
231
232			// Customize the extension of a myHttp method:
233
234			$ql = QueryList::getInstance();
235
236			//Bind a `myHttp` method to the QueryList object
237			$ql->bind(
238			'myHttp', function ($url) {
239			// $this is the current QueryList object
240			$html = file_get_contents($url);
241			$this->setHtml($html);
242			return $this;
243			}
244			);
245
246			// And then you can call by the name of the binding
247			$data = $ql->myHttp('https://toutiao.io')->find('h3 a')->texts();
248			print_r($data->all());
249
250			// Or package to class, and then bind:
251
252			$ql->bind(
253			'myHttp', function ($url) {
254			return new MyHttp($this, $url);
255			}
256			);
257
258			// Plugin used
259
260			// Use the PhantomJS plugin to crawl JavaScript dynamically rendered pages:
261
262			// Set the PhantomJS binary file path during installation
263			$ql = QueryList::use(PhantomJs::class, '/usr/local/bin/phantomjs');
264
265			// Crawl「500px」all picture links
266			$data = $ql->browser('https://500px.com/editors')->find('img')->attrs('src');
267			print_r($data->all());
268
269			// Use the HTTP proxy
270			$ql->browser(
271			'https://500px.com/editors', false, [
272			'--proxy' => '192.168.1.42:8080',
273			'--proxy-type' => 'http'
274			]
275			);
276
277			// Using the CURL multithreading plug-in, multi-threaded crawling GitHub trending :
278
279			$ql = QueryList::use(CurlMulti::class);
280			$ql->curlMulti(
281			[
282			'https://github.com/trending/php',
283			'https://github.com/trending/go',
284			//.....more urls
285			]
286			)
287			// Called if task is success
288			->success(
289			function (QueryList $ql,CurlMulti $curl,$r) {
290			echo "Current url:{$r['info']['url']} \r\n";
291			$data = $ql->find('h3 a')->texts();
292			print_r($data->all());
293			}
294			)
295			// Task fail callback
296			->error(
297			function ($errorInfo,CurlMulti $curl) {
			0 ignored issues – show Unused Code introduced 2020-07-28 00:54 UTC by Report Bug Copy Issue Report The parameter `$curl` is not used and could be removed. This check looks from parameters that have been defined for a function or method, but which are not used in the method body. Loading history...
298			echo "Current url:{$errorInfo['info']['url']} \r\n";
299			print_r($errorInfo['error']);
300			}
301			)
302			->start(
303			[
304			// Maximum number of threads
305			'maxThread' => 10,
306			// Number of error retries
307			'maxTry' => 3,
308			]
309			);
310
311			// Plugins
312
313			// jae-jae/QueryList-PhantomJS:Use PhantomJS to crawl Javascript dynamically rendered page.
314			// jae-jae/QueryList-CurlMulti : Curl multi threading.
315			// jae-jae/QueryList-AbsoluteUrl : Converting relative urls to absolute.
316			// jae-jae/QueryList-Rule-Google : Google searcher.
317			// jae-jae/QueryList-Rule-Baidu : Baidu searcher.
318
319			// View more QueryList plugins and QueryList-based products: QueryList Community
320			}
321			}
322

SierraTecnologia / integrations

Import::girlFromUrl() A last analyzed 2021-05-27 22:55 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

Import::girlFromUrl() A
last analyzed 2021-05-27 22:55 UTC