juniorb2ss / zServices

src/ReceitaFederal/Services/Portais/AN/Service.php

Indentation +22 added lines, -22 removed lines

@@ -22,28 +22,28 @@
 			'data'		=> [
 				'error' => 'body > table:nth-child(3) > tr:nth-child(2) > td > b > font',
 				'numero_inscricao'  => 'body > table:nth-child(3) > tr > td > table:nth-child(3) > tr > td:nth-child(1) > font:nth-child(3) > b:nth-child(1)',
-		        'classificacao'     => 'body > table:nth-child(3) > tr > td > table:nth-child(3) > tr > td:nth-child(1) > font:nth-child(3) > b:nth-child(3)',
-		        'data_abertura'     => 'body > table:nth-child(3) > tr > td > table:nth-child(3) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'nome_empresarial'  => 'body > table:nth-child(3) > tr > td > table:nth-child(5) > tr > td > font:nth-child(3) > b',
-		        'nome_fantasia'     => 'body > table:nth-child(3) > tr > td > table:nth-child(7) > tr > td > font:nth-child(3) > b',
-		        'cnae_principal'    => 'body > table:nth-child(3) > tr > td > table:nth-child(9) > tr > td > font:nth-child(3) > b',
-		        'cnae_secundarios'  => ['body > table:nth-child(3) > tr > td > table:nth-child(11) > tr > td' => 'td > font > b'],
-		        'natureza_juridica' => 'body > table:nth-child(3) > tr > td > table:nth-child(13) > tr > td > font:nth-child(3) > b',
-		        'endereco'          => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(1) > font:nth-child(3) > b',
-		        'numero'            => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'complemento'       => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(5) > font:nth-child(3) > b',
-		        'cep'               => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(1) > font:nth-child(3) > b',
-		        'distrito'          => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'municipio'         => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(5) > font:nth-child(3) > b',
-		        'uf'                => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(7) > font:nth-child(3) > b',
-		        'email'             => 'body > table:nth-child(3) > tr > td > table:nth-child(19) > tr > td:nth-child(1) > font:nth-child(3) > b',
-		        'telefone'          => 'body > table:nth-child(3) > tr > td > table:nth-child(19) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'efr'               => 'body > table:nth-child(3) > tr > td > table:nth-child(21) > tr > td > font:nth-child(3) > b',
-		        'situacao'          => 'body > table:nth-child(3) > tr > td > table:nth-child(23) > tr > td:nth-child(1) > font:nth-child(3) > b',
-		        'data_situacao'     => 'body > table:nth-child(3) > tr > td > table:nth-child(23) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'motivo_situacao'   => 'body > table:nth-child(3) > tr > td > table:nth-child(25) > tr > td:nth-child(3) > font:nth-child(3) > b',
-		        'situacao_especial' => 'body > table:nth-child(3) > tr > td > table:nth-child(27) > tr > td:nth-child(1) > font:nth-child(3) > b',
-		        'data_situacao_especial' => 'body > table:nth-child(3) > tr > td > table:nth-child(27) > tr > td:nth-child(3) > font:nth-child(3) > b'
+				'classificacao'     => 'body > table:nth-child(3) > tr > td > table:nth-child(3) > tr > td:nth-child(1) > font:nth-child(3) > b:nth-child(3)',
+				'data_abertura'     => 'body > table:nth-child(3) > tr > td > table:nth-child(3) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'nome_empresarial'  => 'body > table:nth-child(3) > tr > td > table:nth-child(5) > tr > td > font:nth-child(3) > b',
+				'nome_fantasia'     => 'body > table:nth-child(3) > tr > td > table:nth-child(7) > tr > td > font:nth-child(3) > b',
+				'cnae_principal'    => 'body > table:nth-child(3) > tr > td > table:nth-child(9) > tr > td > font:nth-child(3) > b',
+				'cnae_secundarios'  => ['body > table:nth-child(3) > tr > td > table:nth-child(11) > tr > td' => 'td > font > b'],
+				'natureza_juridica' => 'body > table:nth-child(3) > tr > td > table:nth-child(13) > tr > td > font:nth-child(3) > b',
+				'endereco'          => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(1) > font:nth-child(3) > b',
+				'numero'            => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'complemento'       => 'body > table:nth-child(3) > tr > td > table:nth-child(15) > tr > td:nth-child(5) > font:nth-child(3) > b',
+				'cep'               => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(1) > font:nth-child(3) > b',
+				'distrito'          => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'municipio'         => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(5) > font:nth-child(3) > b',
+				'uf'                => 'body > table:nth-child(3) > tr > td > table:nth-child(17) > tr > td:nth-child(7) > font:nth-child(3) > b',
+				'email'             => 'body > table:nth-child(3) > tr > td > table:nth-child(19) > tr > td:nth-child(1) > font:nth-child(3) > b',
+				'telefone'          => 'body > table:nth-child(3) > tr > td > table:nth-child(19) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'efr'               => 'body > table:nth-child(3) > tr > td > table:nth-child(21) > tr > td > font:nth-child(3) > b',
+				'situacao'          => 'body > table:nth-child(3) > tr > td > table:nth-child(23) > tr > td:nth-child(1) > font:nth-child(3) > b',
+				'data_situacao'     => 'body > table:nth-child(3) > tr > td > table:nth-child(23) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'motivo_situacao'   => 'body > table:nth-child(3) > tr > td > table:nth-child(25) > tr > td:nth-child(3) > font:nth-child(3) > b',
+				'situacao_especial' => 'body > table:nth-child(3) > tr > td > table:nth-child(27) > tr > td:nth-child(1) > font:nth-child(3) > b',
+				'data_situacao_especial' => 'body > table:nth-child(3) > tr > td > table:nth-child(27) > tr > td:nth-child(3) > font:nth-child(3) > b'
 			]
 		],
 		'headers' => [

src/ReceitaFederal/Services/Portais/AN/Crawler.php

Indentation +82 added lines, -82 removed lines

@@ -12,99 +12,99 @@
 class Crawler extends BaseCrawler implements CrawlerInterface
 {
 
-    /**
-     * [$selectors description]
-     * @var [type]
-     */
-    private $selectors = [];
+	/**
+	 * [$selectors description]
+	 * @var [type]
+	 */
+	private $selectors = [];
 
-    /**
-     * [__construct description]
-     * @param [type] $html      [description]
-     * @param array  $selectors [description]
-     */
-    public function __construct($html, $selectors)
-    {
-        $this->selectors = $selectors;
+	/**
+	 * [__construct description]
+	 * @param [type] $html      [description]
+	 * @param array  $selectors [description]
+	 */
+	public function __construct($html, $selectors)
+	{
+		$this->selectors = $selectors;
 
-        parent::__construct($html);
-    }
+		parent::__construct($html);
+	}
 
-    /**
-     * Verifica antes de fazer o crawler se possui erros
-     * na requisição
-     * @return boolean 
-     */
-    public function hasError()
-    {
-        if(count( $this->selectors) == 0) {
-            throw new NoSelectorsConfigured("NoSelectorsConfigured", 1);
-        }
+	/**
+	 * Verifica antes de fazer o crawler se possui erros
+	 * na requisição
+	 * @return boolean 
+	 */
+	public function hasError()
+	{
+		if(count( $this->selectors) == 0) {
+			throw new NoSelectorsConfigured("NoSelectorsConfigured", 1);
+		}
 
-        // verifica se a página seguida na requisição 
-        // é página de erro da receita federal
-        $node = $this->filter($this->selectors['error']);
+		// verifica se a página seguida na requisição 
+		// é página de erro da receita federal
+		$node = $this->filter($this->selectors['error']);
 
-        if($node->count()){
-             throw new ErrorFoundData( $this->clearString($node->text()), 1);
-        }
+		if($node->count()){
+			 throw new ErrorFoundData( $this->clearString($node->text()), 1);
+		}
         
-        // CNPJ informado é válido?
-        if($this->filter('#imgCaptcha')->count()){
-            throw new InvalidCaptcha('Captcha inválido', 99);
-        }
-    }
+		// CNPJ informado é válido?
+		if($this->filter('#imgCaptcha')->count()){
+			throw new InvalidCaptcha('Captcha inválido', 99);
+		}
+	}
 
-    /**
-     * Extrai informações do HTML através do DOM
-     *
-     * @return array
-     */
-    public function scraping()
-    {
-        $scrapped = [];
+	/**
+	 * Extrai informações do HTML através do DOM
+	 *
+	 * @return array
+	 */
+	public function scraping()
+	{
+		$scrapped = [];
 
-        $this->hasError();
+		$this->hasError();
 
-        foreach ($this->selectors as $name => $selector) {
-            if(is_string($selector)){
-                $node = $this->scrap($selector);
+		foreach ($this->selectors as $name => $selector) {
+			if(is_string($selector)){
+				$node = $this->scrap($selector);
 
-                if($node->count()){
-                    $scrapped[$name] = $this->clearString($node->text());
-                }
-            }elseif(is_array($selector)){
-                foreach ($selector as $selector => $repeat) {
-                    $node = $this->scrap($selector);
-                    if($node->count()){
-                        foreach ($node->filter($repeat) as $loop)
-                        {
-                            $scrapped[$name][] = $this->clearString($loop->nodeValue);
-                        }
-                    }
-                }
-            }
-        }
+				if($node->count()){
+					$scrapped[$name] = $this->clearString($node->text());
+				}
+			}elseif(is_array($selector)){
+				foreach ($selector as $selector => $repeat) {
+					$node = $this->scrap($selector);
+					if($node->count()){
+						foreach ($node->filter($repeat) as $loop)
+						{
+							$scrapped[$name][] = $this->clearString($loop->nodeValue);
+						}
+					}
+				}
+			}
+		}
 
-        return $scrapped;
-    }
+		return $scrapped;
+	}
 
-    /**
-     * Limpa o valor repassado
-     * @param  string $string
-     * @return string
-     */
-    public function clearString($string)
-    {
-        return trim(preg_replace(['/[\s]+/mu'], ' ', $string));
-    }
+	/**
+	 * Limpa o valor repassado
+	 * @param  string $string
+	 * @return string
+	 */
+	public function clearString($string)
+	{
+		return trim(preg_replace(['/[\s]+/mu'], ' ', $string));
+	}
 
-    /**
-     * Filtra selector no crawler
-     */
-    public function scrap($selector)
-    {
-        $node = $this->filter($selector);
-        return $node;
-    }
+	/**
+	 * Filtra selector no crawler
+	 */
+	public function scrap($selector)
+	{
+		$node = $this->filter($selector);
+		return $node;
+	}
 }
\ No newline at end of file

src/ReceitaFederal/Services/Portais/AN/Search.php

Indentation +110 added lines, -110 removed lines

@@ -71,13 +71,13 @@ 
 		$this->configurations = $configurations;
 
 		// instancia o client http
-        $this->client = new ClientHttp();
+		$this->client = new ClientHttp();
 
-        // Executa um request para URL do serviço, retornando o cookie da requisição primária
-        $this->instanceResponse = $this->client->request('GET', $this->configurations['home']);
+		// Executa um request para URL do serviço, retornando o cookie da requisição primária
+		$this->instanceResponse = $this->client->request('GET', $this->configurations['home']);
 
-        // Captura o cookie da requisição, será usuado posteriormente
-        $this->cookie = $this->client->cookie();
+		// Captura o cookie da requisição, será usuado posteriormente
+		$this->cookie = $this->client->cookie();
 
 		return $this;
 	}
@@ -104,57 +104,57 @@ 
 		$this->hasRequested();
 
 		// Inicia instancia do cURL
-        $curl = new Curl;
-
-        // Inicia uma requisição para capturar a imagem do captcha
-        // informando cookie da requisição passada e os headers
-        //
-        // to-do: implementar guzzlehttp?
-        // ele é melhor que o curl? ou mais organizado?
-        $curl->init($this->configurations['captcha']);
-
-        // headers da requisição
-        $curl->options([
-                        CURLOPT_COOKIEJAR => 'cookiejar',
-                        CURLOPT_HTTPHEADER => array(
-                            "Pragma: no-cache",
-                            "Origin: " . $this->configurations['base'],
-                            "Host: ". array_get($this->configurations, 'headers.Host'),
-                            "User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
-                            "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
-                            "Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
-                            "Accept-Encoding: gzip, deflate",
-                            "Referer: " . $this->configurations['home'],
-                            "Cookie: flag=1; ". $this->cookie,
-                            "Connection: keep-alive"
-                        ),
-                        CURLOPT_RETURNTRANSFER => true,
-                        CURLOPT_FOLLOWLOCATION => 1,
-                        CURLOPT_BINARYTRANSFER => TRUE,
-                        CURLOPT_CONNECTTIMEOUT => 10,
-                        CURLOPT_TIMEOUT => 10,
-                ]);
-
-        // executa o curl, logo após fechando a conexão
-        $curl->exec();
-        $curl->close();
-
-        // captura do retorno do curl
-        // o esperado deverá ser o HTML da imagem
-        $this->captcha = $curl->response();
-
-        // é uma imagem o retorno?
-        if(@imagecreatefromstring($this->captcha) == false)
-        {
-            throw new NoCaptchaResponse('Não foi possível capturar o captcha');
-        }
-
-        // constroe o base64 da imagem para o usuário digitar
-        // to-do: um serviço automatizado para decifrar o captcha?
-        // talvez deathbycaptcha?
-        $this->captchaImage = 'data:image/png;base64,' . base64_encode($this->captcha);
-
-        return $this->captchaImage;
+		$curl = new Curl;
+
+		// Inicia uma requisição para capturar a imagem do captcha
+		// informando cookie da requisição passada e os headers
+		//
+		// to-do: implementar guzzlehttp?
+		// ele é melhor que o curl? ou mais organizado?
+		$curl->init($this->configurations['captcha']);
+
+		// headers da requisição
+		$curl->options([
+						CURLOPT_COOKIEJAR => 'cookiejar',
+						CURLOPT_HTTPHEADER => array(
+							"Pragma: no-cache",
+							"Origin: " . $this->configurations['base'],
+							"Host: ". array_get($this->configurations, 'headers.Host'),
+							"User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
+							"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+							"Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
+							"Accept-Encoding: gzip, deflate",
+							"Referer: " . $this->configurations['home'],
+							"Cookie: flag=1; ". $this->cookie,
+							"Connection: keep-alive"
+						),
+						CURLOPT_RETURNTRANSFER => true,
+						CURLOPT_FOLLOWLOCATION => 1,
+						CURLOPT_BINARYTRANSFER => TRUE,
+						CURLOPT_CONNECTTIMEOUT => 10,
+						CURLOPT_TIMEOUT => 10,
+				]);
+
+		// executa o curl, logo após fechando a conexão
+		$curl->exec();
+		$curl->close();
+
+		// captura do retorno do curl
+		// o esperado deverá ser o HTML da imagem
+		$this->captcha = $curl->response();
+
+		// é uma imagem o retorno?
+		if(@imagecreatefromstring($this->captcha) == false)
+		{
+			throw new NoCaptchaResponse('Não foi possível capturar o captcha');
+		}
+
+		// constroe o base64 da imagem para o usuário digitar
+		// to-do: um serviço automatizado para decifrar o captcha?
+		// talvez deathbycaptcha?
+		$this->captchaImage = 'data:image/png;base64,' . base64_encode($this->captcha);
+
+		return $this->captchaImage;
 	}
 
 	/**
@@ -196,59 +196,59 @@ 
 	public function getData($document, $cookie, $captcha, $params, $configurations)
 	{
 		// prepara o form
-        $postParams = [
-            'origem' => 'comprovante',
-            'cnpj' => $document, // apenas números
-            'txtTexto_captcha_serpro_gov_br' => $captcha,
-            'submit1' => 'Consultar',
-            'search_type' => 'cnpj'
-        ];
-
-        $postParams = array_merge($postParams, $params);
-
-        // inicia o cURL
-        $curl = new Curl;
-
-        // vamos registrar qual serviço será consultado
-        $curl->init($configurations['data']);
-
-        // define os headers para requisição curl.
-        $curl->options(
-            array(
-            	 CURLOPT_HTTPHEADER => array(
-                    "Pragma: no-cache",
-                    "Origin: " . $this->configurations['base'],
-                    "Host: ". array_get($configurations, 'headers.Host'),
-                    "User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
-                    "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
-                    "Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
-                    "Accept-Encoding: gzip, deflate",
-                    "Referer: " . $this->configurations['home'] .'?cnpj='. $document,
-                    "Cookie: flag=1; ". $cookie,
-                    "Connection: keep-alive"
-                ),
-                CURLOPT_RETURNTRANSFER  => 1,
-                CURLOPT_BINARYTRANSFER => 1,
-                CURLOPT_FOLLOWLOCATION => 1,
-            )
-        );
-
-        // efetua a chamada passando os parametros de form
-        $curl->post($postParams);
-        $curl->exec();
-
-        // completa a chamda
-        $curl->close();
-
-        // vamos capturar retorno, que deverá ser o HTML para scrapping
-        $html = $curl->response();
-
-        if(empty($html)) {
-            throw new NoServiceResponse('No response from service', 99);
-        }
-
-        $crawler = new Crawler($html, array_get($configurations, 'selectors.data'));
-
-        return $crawler;
+		$postParams = [
+			'origem' => 'comprovante',
+			'cnpj' => $document, // apenas números
+			'txtTexto_captcha_serpro_gov_br' => $captcha,
+			'submit1' => 'Consultar',
+			'search_type' => 'cnpj'
+		];
+
+		$postParams = array_merge($postParams, $params);
+
+		// inicia o cURL
+		$curl = new Curl;
+
+		// vamos registrar qual serviço será consultado
+		$curl->init($configurations['data']);
+
+		// define os headers para requisição curl.
+		$curl->options(
+			array(
+				 CURLOPT_HTTPHEADER => array(
+					"Pragma: no-cache",
+					"Origin: " . $this->configurations['base'],
+					"Host: ". array_get($configurations, 'headers.Host'),
+					"User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
+					"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+					"Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
+					"Accept-Encoding: gzip, deflate",
+					"Referer: " . $this->configurations['home'] .'?cnpj='. $document,
+					"Cookie: flag=1; ". $cookie,
+					"Connection: keep-alive"
+				),
+				CURLOPT_RETURNTRANSFER  => 1,
+				CURLOPT_BINARYTRANSFER => 1,
+				CURLOPT_FOLLOWLOCATION => 1,
+			)
+		);
+
+		// efetua a chamada passando os parametros de form
+		$curl->post($postParams);
+		$curl->exec();
+
+		// completa a chamda
+		$curl->close();
+
+		// vamos capturar retorno, que deverá ser o HTML para scrapping
+		$html = $curl->response();
+
+		if(empty($html)) {
+			throw new NoServiceResponse('No response from service', 99);
+		}
+
+		$crawler = new Crawler($html, array_get($configurations, 'selectors.data'));
+
+		return $crawler;
 	}
 }
\ No newline at end of file

src/Sintegra/Services/Portais/SP/Service.php

Indentation +18 added lines, -18 removed lines

@@ -23,24 +23,24 @@
 			'data'		=> [
 				'error' => 'body > center:nth-child(8) > table > tr > td > font > b',
 				'inscricao_estadual'  => 'body > center:nth-child(9) > table > tr > td:nth-child(4) > font',
-		        'razao_social' => 'body > center:nth-child(10) > table > tr > td:nth-child(2) > font',
-		        'logradouro' => 'body > center:nth-child(13) > table > tr > td:nth-child(2) > font',
-		        'numero'    => 'body > center:nth-child(14) > table > tr > td:nth-child(2) > font',
-		        'complemento' => 'body > center:nth-child(14) > table > tr > td:nth-child(4) > font',
-		        'bairro'    => 'body > center:nth-child(15) > table > tr > td:nth-child(2) > font',
-		        'municipio' => 'body > center:nth-child(16) > table > tr > td:nth-child(2) > font',
-		        'uf'        => 'body > center:nth-child(16) > table > tr > td:nth-child(4) > font',
-		        'cep'  => 'body > center:nth-child(17) > table > tr > td:nth-child(2) > font',
-		        'atividade_economica' => 'body > center:nth-child(20) > table > tr > td:nth-child(2) > font',
-		        'situacao'  => 'body > center:nth-child(21) > table > tr > td:nth-child(2) > font',
-		        'situacao2'  => 'body > center:nth-child(21) > table > tr > td:nth-child(3) > font',
-		        'data_situacao' => 'body > center:nth-child(22) > table > tr > td:nth-child(2) > font',
-		        'regime'    => 'body > center:nth-child(23) > table > tr > td:nth-child(2) > font',
-		        'data_emissor_nfe'  => 'body > center:nth-child(24) > table > tr > td:nth-child(2) > font',
-		        'indicator_obrigatoriedade_nfe' => 'body > center:nth-child(25) > table > tr > td:nth-child(2) > font',
-		        'data_inicio_obrigatoriedade_nfe'   => 'body > center:nth-child(26) > table > tr > td:nth-child(2) > font',
-		        'consulta'  => 'body > center:nth-child(28) > table > tr:nth-child(2) > td:nth-child(2) > font > b',
-		        'observacoes'   => 'body > center:nth-child(30) > table > tr > td > font:nth-child(1)',
+				'razao_social' => 'body > center:nth-child(10) > table > tr > td:nth-child(2) > font',
+				'logradouro' => 'body > center:nth-child(13) > table > tr > td:nth-child(2) > font',
+				'numero'    => 'body > center:nth-child(14) > table > tr > td:nth-child(2) > font',
+				'complemento' => 'body > center:nth-child(14) > table > tr > td:nth-child(4) > font',
+				'bairro'    => 'body > center:nth-child(15) > table > tr > td:nth-child(2) > font',
+				'municipio' => 'body > center:nth-child(16) > table > tr > td:nth-child(2) > font',
+				'uf'        => 'body > center:nth-child(16) > table > tr > td:nth-child(4) > font',
+				'cep'  => 'body > center:nth-child(17) > table > tr > td:nth-child(2) > font',
+				'atividade_economica' => 'body > center:nth-child(20) > table > tr > td:nth-child(2) > font',
+				'situacao'  => 'body > center:nth-child(21) > table > tr > td:nth-child(2) > font',
+				'situacao2'  => 'body > center:nth-child(21) > table > tr > td:nth-child(3) > font',
+				'data_situacao' => 'body > center:nth-child(22) > table > tr > td:nth-child(2) > font',
+				'regime'    => 'body > center:nth-child(23) > table > tr > td:nth-child(2) > font',
+				'data_emissor_nfe'  => 'body > center:nth-child(24) > table > tr > td:nth-child(2) > font',
+				'indicator_obrigatoriedade_nfe' => 'body > center:nth-child(25) > table > tr > td:nth-child(2) > font',
+				'data_inicio_obrigatoriedade_nfe'   => 'body > center:nth-child(26) > table > tr > td:nth-child(2) > font',
+				'consulta'  => 'body > center:nth-child(28) > table > tr:nth-child(2) > td:nth-child(2) > font > b',
+				'observacoes'   => 'body > center:nth-child(30) > table > tr > td > font:nth-child(1)',
 			]
 		],
 		'headers' => [

src/Sintegra/Services/Portais/SP/Crawler.php

Indentation +74 added lines, -74 removed lines

@@ -11,89 +11,89 @@
 class Crawler extends BaseCrawler implements CrawlerInterface
 {
 
-    /**
-     * [$selectors description]
-     * @var [type]
-     */
-    private $selectors = [];
+	/**
+	 * [$selectors description]
+	 * @var [type]
+	 */
+	private $selectors = [];
 
-    /**
-     * [__construct description]
-     * @param [type] $html      [description]
-     * @param array  $selectors [description]
-     */
-    public function __construct($html, $selectors)
-    {
-        $this->selectors = $selectors;
+	/**
+	 * [__construct description]
+	 * @param [type] $html      [description]
+	 * @param array  $selectors [description]
+	 */
+	public function __construct($html, $selectors)
+	{
+		$this->selectors = $selectors;
 
-        parent::__construct($html);
-    }
+		parent::__construct($html);
+	}
 
-    /**
-     * Verifica antes de fazer o crawler se possui erros
-     * na requisição
-     * @return boolean 
-     */
-    public function hasError()
-    {
-        $node = $this->scrap($this->selectors['razao_social']);
+	/**
+	 * Verifica antes de fazer o crawler se possui erros
+	 * na requisição
+	 * @return boolean 
+	 */
+	public function hasError()
+	{
+		$node = $this->scrap($this->selectors['razao_social']);
 
-        if(!$node->count())
-        {
-            throw new ErrorFoundData($this->clearString($this->scrap($this->selectors['error'])->text()), 1);
-        }
-    }
+		if(!$node->count())
+		{
+			throw new ErrorFoundData($this->clearString($this->scrap($this->selectors['error'])->text()), 1);
+		}
+	}
 
-    /**
-     * Extrai informações do HTML através do DOM
-     *
-     * @return array
-     */
-    public function scraping()
-    {
-        $scrapped = [];
+	/**
+	 * Extrai informações do HTML através do DOM
+	 *
+	 * @return array
+	 */
+	public function scraping()
+	{
+		$scrapped = [];
 
-        $this->hasError();
+		$this->hasError();
 
-        foreach ($this->selectors as $name => $selector) {
-            if(is_string($selector)){
-                $node = $this->scrap($selector);
+		foreach ($this->selectors as $name => $selector) {
+			if(is_string($selector)){
+				$node = $this->scrap($selector);
 
-                if($node->count()){
-                    $scrapped[$name] = $this->clearString($node->text());
-                }
-            }elseif(is_array($selector)){
-                foreach ($selector as $selector => $repeat) {
-                    $node = $this->scrap($selector);
-                    if($node->count()){
-                        foreach ($node->filter($repeat) as $loop)
-                        {
-                            $scrapped[$name][] = $this->clearString($loop->nodeValue);
-                        }
-                    }
-                }
-            }
-        }
+				if($node->count()){
+					$scrapped[$name] = $this->clearString($node->text());
+				}
+			}elseif(is_array($selector)){
+				foreach ($selector as $selector => $repeat) {
+					$node = $this->scrap($selector);
+					if($node->count()){
+						foreach ($node->filter($repeat) as $loop)
+						{
+							$scrapped[$name][] = $this->clearString($loop->nodeValue);
+						}
+					}
+				}
+			}
+		}
 
-        return $scrapped;
-    }
+		return $scrapped;
+	}
 
-    /**
-     * Limpa o valor repassado
-     * @param  string $string
-     * @return string
-     */
-    public function clearString($string)
-    {
-        return trim(preg_replace(['/[\s]+/mu'], ' ', $string));
-    }
+	/**
+	 * Limpa o valor repassado
+	 * @param  string $string
+	 * @return string
+	 */
+	public function clearString($string)
+	{
+		return trim(preg_replace(['/[\s]+/mu'], ' ', $string));
+	}
 
-    /**
-     * Filtra selector no crawler
-     */
-    public function scrap($selector)
-    {
-        $node = $this->filter($selector);
-        return $node;
-    }
+	/**
+	 * Filtra selector no crawler
+	 */
+	public function scrap($selector)
+	{
+		$node = $this->filter($selector);
+		return $node;
+	}
 }
\ No newline at end of file

src/Sintegra/Services/Portais/SP/Search.php

Indentation +115 added lines, -115 removed lines

@@ -69,13 +69,13 @@ 
 		$this->configurations = $configurations;
 
 		// instancia o client http
-        $this->client = new ClientHttp();
+		$this->client = new ClientHttp();
 
-        // Executa um request para URL do serviço, retornando o cookie da requisição primária
-        $this->instanceResponse = $this->client->request('GET', $this->configurations['home']);
+		// Executa um request para URL do serviço, retornando o cookie da requisição primária
+		$this->instanceResponse = $this->client->request('GET', $this->configurations['home']);
 
-        // Captura o cookie da requisição, será usuado posteriormente
-        $this->cookie = $this->client->cookie();
+		// Captura o cookie da requisição, será usuado posteriormente
+		$this->cookie = $this->client->cookie();
 
 		return $this;
 	}
@@ -109,68 +109,68 @@ 
 			throw new ImageNotFound("Impossible to crawler image from response", 1);
 		}
 
-        $paramBot = $this->instanceResponse->filter(
-        				array_get($this->configurations, 'selectors.paramBot')
-        			);
+		$paramBot = $this->instanceResponse->filter(
+						array_get($this->configurations, 'selectors.paramBot')
+					);
 
-        if(!$paramBot->count()){
+		if(!$paramBot->count()){
 			throw new ImageNotFound("Impossible to crawler parambot from response", 1);
 		}
 
 		// Inicia instancia do cURL
-        $curl = new Curl;
-
-        // Inicia uma requisição para capturar a imagem do captcha
-        // informando cookie da requisição passada e os headers
-        //
-        // to-do: implementar guzzlehttp?
-        // ele é melhor que o curl? ou mais organizado?
-        $curl->init($this->configurations['base'] . $imageSrc->attr('src'));
-
-        $this->params['parambot'] = trim($paramBot->attr('value'));
-
-        // headers da requisição
-        $curl->options([
-                        CURLOPT_COOKIEJAR => 'cookiejar',
-                        CURLOPT_HTTPHEADER => array(
-                            "Pragma: no-cache",
-                            "Origin: " . $this->configurations['base'],
-                            "Host: ". array_get($this->configurations, 'headers.Host'),
-                            "User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
-                            "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
-                            "Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
-                            "Accept-Encoding: gzip, deflate",
-                            "Referer: " . $this->configurations['captcha'],
-                            "Cookie: flag=1; ". $this->cookie,
-                            "Connection: keep-alive"
-                        ),
-                        CURLOPT_RETURNTRANSFER => true,
-                        CURLOPT_FOLLOWLOCATION => 1,
-                        CURLOPT_BINARYTRANSFER => TRUE,
-                        CURLOPT_CONNECTTIMEOUT => 10,
-                        CURLOPT_TIMEOUT => 10,
-                ]);
-
-        // executa o curl, logo após fechando a conexão
-        $curl->exec();
-        $curl->close();
-
-        // captura do retorno do curl
-        // o esperado deverá ser o HTML da imagem
-        $this->captcha = $curl->response();
-
-        // é uma imagem o retorno?
-        if(@imagecreatefromstring($this->captcha) == false)
-        {
-            throw new NoCaptchaResponse('Não foi possível capturar o captcha');
-        }
-
-        // constroe o base64 da imagem para o usuário digitar
-        // to-do: um serviço automatizado para decifrar o captcha?
-        // talvez deathbycaptcha?
-        $this->captchaImage = 'data:image/png;base64,' . base64_encode($this->captcha);
-
-        return $this->captchaImage;
+		$curl = new Curl;
+
+		// Inicia uma requisição para capturar a imagem do captcha
+		// informando cookie da requisição passada e os headers
+		//
+		// to-do: implementar guzzlehttp?
+		// ele é melhor que o curl? ou mais organizado?
+		$curl->init($this->configurations['base'] . $imageSrc->attr('src'));
+
+		$this->params['parambot'] = trim($paramBot->attr('value'));
+
+		// headers da requisição
+		$curl->options([
+						CURLOPT_COOKIEJAR => 'cookiejar',
+						CURLOPT_HTTPHEADER => array(
+							"Pragma: no-cache",
+							"Origin: " . $this->configurations['base'],
+							"Host: ". array_get($this->configurations, 'headers.Host'),
+							"User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:32.0) Gecko/20100101 Firefox/32.0",
+							"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+							"Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.5,en;q=0.3",
+							"Accept-Encoding: gzip, deflate",
+							"Referer: " . $this->configurations['captcha'],
+							"Cookie: flag=1; ". $this->cookie,
+							"Connection: keep-alive"
+						),
+						CURLOPT_RETURNTRANSFER => true,
+						CURLOPT_FOLLOWLOCATION => 1,
+						CURLOPT_BINARYTRANSFER => TRUE,
+						CURLOPT_CONNECTTIMEOUT => 10,
+						CURLOPT_TIMEOUT => 10,
+				]);
+
+		// executa o curl, logo após fechando a conexão
+		$curl->exec();
+		$curl->close();
+
+		// captura do retorno do curl
+		// o esperado deverá ser o HTML da imagem
+		$this->captcha = $curl->response();
+
+		// é uma imagem o retorno?
+		if(@imagecreatefromstring($this->captcha) == false)
+		{
+			throw new NoCaptchaResponse('Não foi possível capturar o captcha');
+		}
+
+		// constroe o base64 da imagem para o usuário digitar
+		// to-do: um serviço automatizado para decifrar o captcha?
+		// talvez deathbycaptcha?
+		$this->captchaImage = 'data:image/png;base64,' . base64_encode($this->captcha);
+
+		return $this->captchaImage;
 	}
 
 	/**
@@ -212,58 +212,58 @@ 
 	public function getData($document, $cookie, $captcha, $params, $configurations)
 	{
 		// prepara o form
-        $postParams = [
-            'cnpj' => $document, // apenas números
-            'Key' => $captcha,
-            'botao' => 'Consulta por CNPJ',
-            'hidFlag' => '1',
-            'ie' => '',
-            'servico' => 'cnpj',
-            'paramBot' => $params['parambot']
-        ];
-
-        // inicia o cURL
-        $curl = new Curl;
-
-        // vamos registrar qual serviço será consultado
-        $curl->init($configurations['data']);
-
-        // define os headers para requisição curl.
-        $curl->options(
-            array(
-                CURLOPT_HTTPHEADER => array(
-                    "Origin: http://pfeserv1.fazenda.sp.gov.br",
-                    "Host: pfeserv1.fazenda.sp.gov.br",
-                    "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36",
-                    "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
-                    "Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2",
-                    "Accept-Encoding: gzip, deflate",
-                    "Referer: http://pfeserv1.fazenda.sp.gov.br/sintegrapfe/consultaSintegraServlet",
-                    "Cookie: flag=1; ". $cookie,
-                    "Connection: keep-alive"
-                ),
-                CURLOPT_RETURNTRANSFER  => 1,
-                CURLOPT_BINARYTRANSFER => 1,
-                CURLOPT_FOLLOWLOCATION => 1,
-            )
-        );
-
-        // efetua a chamada passando os parametros de form
-        $curl->post($postParams);
-        $curl->exec();
-
-        // completa a chamda
-        $curl->close();
-
-        // vamos capturar retorno, que deverá ser o HTML para scrapping
-        $html = $curl->response();
-
-        if(empty($html)) {
-            throw new NoServiceResponse('No response from service', 99);
-        }
-
-        $crawler = new Crawler($html, array_get($configurations, 'selectors.data'));
-
-        return $crawler;
+		$postParams = [
+			'cnpj' => $document, // apenas números
+			'Key' => $captcha,
+			'botao' => 'Consulta por CNPJ',
+			'hidFlag' => '1',
+			'ie' => '',
+			'servico' => 'cnpj',
+			'paramBot' => $params['parambot']
+		];
+
+		// inicia o cURL
+		$curl = new Curl;
+
+		// vamos registrar qual serviço será consultado
+		$curl->init($configurations['data']);
+
+		// define os headers para requisição curl.
+		$curl->options(
+			array(
+				CURLOPT_HTTPHEADER => array(
+					"Origin: http://pfeserv1.fazenda.sp.gov.br",
+					"Host: pfeserv1.fazenda.sp.gov.br",
+					"User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36",
+					"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+					"Accept-Language: pt-BR,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2",
+					"Accept-Encoding: gzip, deflate",
+					"Referer: http://pfeserv1.fazenda.sp.gov.br/sintegrapfe/consultaSintegraServlet",
+					"Cookie: flag=1; ". $cookie,
+					"Connection: keep-alive"
+				),
+				CURLOPT_RETURNTRANSFER  => 1,
+				CURLOPT_BINARYTRANSFER => 1,
+				CURLOPT_FOLLOWLOCATION => 1,
+			)
+		);
+
+		// efetua a chamada passando os parametros de form
+		$curl->post($postParams);
+		$curl->exec();
+
+		// completa a chamda
+		$curl->close();
+
+		// vamos capturar retorno, que deverá ser o HTML para scrapping
+		$html = $curl->response();
+
+		if(empty($html)) {
+			throw new NoServiceResponse('No response from service', 99);
+		}
+
+		$crawler = new Crawler($html, array_get($configurations, 'selectors.data'));
+
+		return $crawler;
 	}
 }
\ No newline at end of file

src/Miscellany/ClientHttp.php

Indentation +53 added lines, -53 removed lines

@@ -8,64 +8,64 @@
 */
 class ClientHttp extends BaseClient
 {
-    /**
-     * [$protocol description]
-     * @var [type]
-     */
-    protected $method;
+	/**
+	 * [$protocol description]
+	 * @var [type]
+	 */
+	protected $method;
 
-    /**
-     * [$url description]
-     * @var [type]
-     */
-    protected $url;
+	/**
+	 * [$url description]
+	 * @var [type]
+	 */
+	protected $url;
 
-    /**
-     * [$cookie description]
-     * @var [type]
-     */
-    protected $cookie;
+	/**
+	 * [$cookie description]
+	 * @var [type]
+	 */
+	protected $cookie;
 
-    /**
-     * [$response description]
-     * @var [type]
-     */
-    protected $response;
+	/**
+	 * [$response description]
+	 * @var [type]
+	 */
+	protected $response;
 
-    /**
-     * [request description]
-     * @param  string  $method        [description]
-     * @param  string  $url           [description]
-     * @param  array   $parameters    [description]
-     * @param  array   $files         [description]
-     * @param  array   $server        [description]
-     * @param  [type]  $content       [description]
-     * @param  boolean $changeHistory [description]
-     * @return @instance
-     */
-    public function request($method, $url, array $parameters = array(), array $files = array(), array $server = array(), $content = null, $changeHistory = true)
-    {
-        $this->method = $method;
-        $this->url = $url;
+	/**
+	 * [request description]
+	 * @param  string  $method        [description]
+	 * @param  string  $url           [description]
+	 * @param  array   $parameters    [description]
+	 * @param  array   $files         [description]
+	 * @param  array   $server        [description]
+	 * @param  [type]  $content       [description]
+	 * @param  boolean $changeHistory [description]
+	 * @return @instance
+	 */
+	public function request($method, $url, array $parameters = array(), array $files = array(), array $server = array(), $content = null, $changeHistory = true)
+	{
+		$this->method = $method;
+		$this->url = $url;
 
-        return parent::request($this->method, $this->url, $parameters, $files, $server, $content, $changeHistory);
-    }
+		return parent::request($this->method, $this->url, $parameters, $files, $server, $content, $changeHistory);
+	}
 
-    /**
-     * [headers description]
-     * @return [type] [description]
-     */
-    private function headers()
-    {
-        return $this->response->getHeaders();
-    }
+	/**
+	 * [headers description]
+	 * @return [type] [description]
+	 */
+	private function headers()
+	{
+		return $this->response->getHeaders();
+	}
 
-    /**
-     * [cookie description]
-     * @return [type] [description]
-     */
-    public function cookie()
-    {
-        return $this->headers()['Set-Cookie'][0];
-    }
+	/**
+	 * [cookie description]
+	 * @return [type] [description]
+	 */
+	public function cookie()
+	{
+		return $this->headers()['Set-Cookie'][0];
+	}
 }
\ No newline at end of file

src/Miscellany/Curl.php

Indentation +102 added lines, -102 removed lines

@@ -7,106 +7,106 @@
 class Curl
 {
 
-    /**
-     * [$url description]
-     * @var [type]
-     */
-    private $url;
-
-    /**
-     * [$options description]
-     * @var [type]
-     */
-    private $options;
-
-    /**
-     * [$instance description]
-     * @var [type]
-     */
-    private $instance;
-
-    /**
-     * [$response description]
-     * @var [type]
-     */
-    private $response;
-
-    /**
-     * [init description]
-     * @return [type] [description]
-     */
-    public function init($url)
-    {
-        $this->instance = curl_init($url);
-
-        $this->url = $url;
-
-        return $this;
-    }
-
-    /**
-     * [options description]
-     * @param  array  $options [description]
-     * @return [type]          [description]
-     */
-    public function options(array $options)
-    {
-        $this->options = $options;
-
-        curl_setopt_array($this->instance, $this->options);
-
-        return $this;
-    }
-
-    /**
-     * [post description]
-     * @param  [type] $params [description]
-     * @return [type]         [description]
-     */
-    public function post(array $fields)
-    {
-        $this->option(CURLOPT_POST, count($fields));
-        $this->option(CURLOPT_POSTFIELDS, http_build_query($fields));
-
-        return $this;
-    }
-
-    /**
-     * Set option in cURL
-     * @param  mix $option 
-     * @param  mix $value 
-     */
-    public function option($option, $value)
-    {
-        curl_setopt($this->instance, $option, $value);
-    }
-
-    /**
-     * [exec description]
-     * @return [type] [description]
-     */
-    public function exec()
-    {
-        $this->response = curl_exec($this->instance);
-    }
-
-    /**
-     * [close description]
-     * @return [type] [description]
-     */
-    public function close()
-    {
-        curl_close($this->instance);
-
-        return $this;
-    }
-
-    /**
-     * [response description]
-     * @return [type] [description]
-     */
-    public function response()
-    {
-        return $this->response;
-    }
+	/**
+	 * [$url description]
+	 * @var [type]
+	 */
+	private $url;
+
+	/**
+	 * [$options description]
+	 * @var [type]
+	 */
+	private $options;
+
+	/**
+	 * [$instance description]
+	 * @var [type]
+	 */
+	private $instance;
+
+	/**
+	 * [$response description]
+	 * @var [type]
+	 */
+	private $response;
+
+	/**
+	 * [init description]
+	 * @return [type] [description]
+	 */
+	public function init($url)
+	{
+		$this->instance = curl_init($url);
+
+		$this->url = $url;
+
+		return $this;
+	}
+
+	/**
+	 * [options description]
+	 * @param  array  $options [description]
+	 * @return [type]          [description]
+	 */
+	public function options(array $options)
+	{
+		$this->options = $options;
+
+		curl_setopt_array($this->instance, $this->options);
+
+		return $this;
+	}
+
+	/**
+	 * [post description]
+	 * @param  [type] $params [description]
+	 * @return [type]         [description]
+	 */
+	public function post(array $fields)
+	{
+		$this->option(CURLOPT_POST, count($fields));
+		$this->option(CURLOPT_POSTFIELDS, http_build_query($fields));
+
+		return $this;
+	}
+
+	/**
+	 * Set option in cURL
+	 * @param  mix $option 
+	 * @param  mix $value 
+	 */
+	public function option($option, $value)
+	{
+		curl_setopt($this->instance, $option, $value);
+	}
+
+	/**
+	 * [exec description]
+	 * @return [type] [description]
+	 */
+	public function exec()
+	{
+		$this->response = curl_exec($this->instance);
+	}
+
+	/**
+	 * [close description]
+	 * @return [type] [description]
+	 */
+	public function close()
+	{
+		curl_close($this->instance);
+
+		return $this;
+	}
+
+	/**
+	 * [response description]
+	 * @return [type] [description]
+	 */
+	public function response()
+	{
+		return $this->response;
+	}
 }
\ No newline at end of file