Ferramentas para capturar e converter a Web

Capturar tabelas HTML de sites com Node.jsAPI do Node.js

Existem v√°rias maneiras de converter tabelas HTML into JSON, CSV e planilhas do Excel usando API Node.js do GrabzIt, detalhadas aqui est√£o algumas das t√©cnicas mais √ļteis. No entanto, antes de come√ßar, lembre-se de que depois de ligar para o url_to_table, html_to_table or file_to_table m√©todos os save or save_to O m√©todo deve ser chamado para capturar a tabela. Se voc√™ quiser ver rapidamente se este servi√ßo √© adequado para voc√™, tente uma demonstra√ß√£o ao vivo da captura de tabelas HTML de um URL.

Op√ß√Ķes B√°sicas

Essa chamada de método específica converterá a primeira tabela HTML na página da Web do URL especificado, into um documento CSV. Esse snippet de código converterá a primeira tabela HTML encontrada em uma página da Web ou entrada HTML especificada into um documento CSV.

client.url_to_table("https://www.tesla.com");
//Then call the save or save_to method
client.html_to_table("<html><body><table><tr><th>Name</th><th>Age</th></tr>
    <tr><td>Tom</td><td>23</td></tr><tr><td>Nicola</td><td>26</td></tr>
    </table></body></html>");
//Then call the save or save_to method
client.file_to_table("tables.html");
//Then call the save or save_to method

Por padr√£o, isso converter√° a primeira tabela que identifica intuma mesa. No entanto, a segunda tabela em uma p√°gina da web pode ser convertida passando um 2 para o tableNumberToInclude propriedade.

var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"tableNumberToInclude":2};

client.url_to_table("https://www.tesla.com", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"tableNumberToInclude":2};

client.html_to_table("<html><body><table><tr><th>Name</th><th>Age</th></tr>
    <tr><td>Tom</td><td>23</td></tr><tr><td>Nicola</td><td>26</td></tr>
    </table></body></html>", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"tableNumberToInclude":2};

client.file_to_table("tables.html", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});

Você também pode especificar o targetElement A propriedade que garantirá que apenas as tabelas dentro do ID do elemento especificado serão convertidas.

var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"targetElement":"stocks_table"};

client.url_to_table("https://www.tesla.com", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"targetElement":"stocks_table"};

client.html_to_table("<html><body><table id='stocks_table'><tr><th>Name</th><th>Age</th></tr>
    <tr><td>Tom</td><td>23</td></tr><tr><td>Nicola</td><td>26</td></tr>
    </table></body></html>", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"targetElement":"stocks_table"};

client.file_to_table("tables.html", options);
//Then call the save or save_to method
client.save_to("result.csv", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});

Como alternativa, você pode capturar todas as tabelas em uma página da Web passando true para o includeAllTables , no entanto, isso funcionará apenas com os formatos JSON e XLSX. Essa opção colocará cada tabela em uma nova planilha na pasta de trabalho da planilha gerada.

var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"format","xlsx","includeHeaderNames":true,"includeAllTables":true};

client.url_to_table("https://www.tesla.com", options);
//Then call the save or save_to method
client.save_to("result.xlsx", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"format","xlsx","includeHeaderNames":true,"includeAllTables":true};

client.html_to_table("<html><body><table><tr><th>Name</th><th>Age</th></tr>
    <tr><td>Tom</td><td>23</td></tr><tr><td>Nicola</td><td>26</td></tr>
    </table></body></html>", options);
//Then call the save or save_to method
client.save_to("result.xlsx", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"format","xlsx","includeHeaderNames":true,"includeAllTables":true};

client.file_to_table("tables.html", options);
//Then call the save or save_to method
client.save_to("result.xlsx", function (error, id){
    //this callback is called once the capture is downloaded
    if (error != null){
        throw error;
    }
});

Converter tabelas HTML em JSON

Usando Node.js e GrabzIt, voc√™ pode converter tabelas HTML into JSON, basta especificar json no par√Ęmetro format. Como mostrado no exemplo abaixo, uma vez que o save_to Quando o m√©todo √© conclu√≠do, a fun√ß√£o oncomplete √© chamada com o JSON na vari√°vel result, que √© ent√£o analisada pelo Node.js embutido. JSON.parse para criar um objeto que representa a tabela HTML.

var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"format","json","includeHeaderNames":true,"includeAllTables":true};
client.url_to_table("https://www.tesla.com", options);

client.save_to(null, function(error, result){
    if (result != null)
    {
        var tableObj = JSON.parse(result);
    }
});

Identificador Personalizado

Você pode passar um identificador personalizado para o mesa Como mostrado abaixo, esse valor é retornado ao seu manipulador GrabzIt Node.js. Por exemplo, esse identificador personalizado pode ser um identificador de banco de dados, permitindo que uma captura de tela seja associada a um registro específico do banco de dados.

var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"customId":123456};

client.url_to_table("https://www.tesla.com", options);
//Then call the save method
client.save("http://www.example.com/handler", function (error, id){
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"customId":123456};

client.html_to_table("<html><body><h1>Hello World!</h1></body></html>", options);
//Then call the save method
client.save("http://www.example.com/handler", function (error, id){
    if (error != null){
        throw error;
    }
});
var grabzit = require('grabzit');

var client = new grabzit("Sign in to view your Application Key", "Sign in to view your Application Secret");

var options = {"customId":123456};

client.file_to_table("example.html", options);
//Then call the save method
client.save("http://www.example.com/handler", function (error, id){
    if (error != null){
        throw error;
    }
});