I am doing scraping
of the site tematika.com to be able to create a book base. The problem is that I need to go over the page but I can not, so I always get the same books. I think that with the code they will understand it better.
const phantom = require("phantom");
const cheerio = require("cheerio");
let _instance, _page;
let _books = [];
phantom.create().then(instance => {
_instance = instance;
return _instance.createPage();
}).then(page => {
_page = page;
return _page.open('http://www.tematika.com/catalogo/libros/arte__arquitectura_y_diseno--9.htm');
}).then(status => {
console.log(status);
return _page.property('content')
}).then(html => {
//Transformo el html en objeto para manipularlo con cheerio
let $ = cheerio.load(html);
//Obtengo todos los libros y los paso a un array para recorrerlos y extraer la info que busco
let books = $('.Gcentro').find('.moduleproductob').toArray();
//Como siempre hay 10 paginas hago un for que itere 10 veces
for(let i=0;i<10;i++){
books.forEach(book => {
let _book = {};
_book.imageMin = $(book).find('.Gimagesproductos').attr('src');
_book.linkBook = $(book).find('.FProductos').attr('href');
_books.push(_book);
});
//En esta parte lo que yo busco es hacer click en el boton siguiente de la pagina y es lo que no me esta funcionando
//Lo que termina pasando es que nunca pasa de pagina. Entonces siempre me trae la info de los mismo 10 libros.
_page.evaluate(function() {
var evObj = document.createEvent('Events');
evObj.initEvent('click', true, false);
document.getElementById('catalogNext').dispatchEvent(evObj);
});
}
console.log(_books);
_page.close();
_instance.exit();
}).catch(e => console.log(e));
What I need is to be able to do click
in next and be able to bring me the books that are showing. If it is not with phantom-node
and cheerio
can be with another tool, the only thing I need is that it works in node
.