如何在zombie.js中保存可下载文件链接

Question

I am scrapping a website using node.js and zombie.js. I am facing an issue where in a file I have an anchor which holds the link to download a pdf file. If I click it using browser.clickLink() function, the result that I get in console is beyond my understanding. Is there a way to save this pdf file and have its link like in php? I want to save it for further processing. Here is my test js code

 var http = require('http'); var browser = require('zombie'); var assert = require('assert'); const hostname = '127.0.0.1'; const port = 3000; const server = http.createServer((req, res) => { res.statusCode = 200; //res.setHeader('Content-Type', 'text/plain'); //res.end('Hello World\\n'); }); server.listen(port, hostname, () => { console.log(`Server running at http://${hostname}:${port}/`); }); var url = 'http://localhost/Node/HM_LandRegistry/downloadPdf.html' browser.visit(url, function(error,browser) { //browser.dump(); //console.log('browser.text (".link")', browser.text(".link")); browser.clickLink("a.link"); browser.wait().then(function(){ console.log(browser.text()); browser.dump(); }); }); 

Answer 1

Here is something I found on google groups. It has solved my problem.

function getLinks(browser) {
 var links = browser.querySelectorAll('.link');
 return Array.prototype.map.call(links, function(e) {
 return e.getAttribute('href'); // returns an array. Use .toString() to get string only
});
}

Save the link