In Node.js / Express, how do I "download" a page and gets its HTML?
Using node.js you can just use the http.request method
http://nodejs.org/docs/v0.4.7/api/all.html#http.request
This method is built into node you just need to require http.
If you just want to do a GET, then you can use http.get
http://nodejs.org/docs/v0.4.7/api/all.html#http.get
var options = {
host: 'www.google.com',
port: 80,
path: '/index.html'
};
http.get(options, function(res) {
console.log("Got response: " + res.statusCode);
}).on('error', function(e) {
console.log("Got error: " + e.message);
});
(Example from node.js docs)
You could also use mikeal's request module
https://github.com/mikeal/request
var util = require("util"),
http = require("http");
var options = {
host: "www.google.com",
port: 80,
path: "/"
};
var content = "";
var req = http.request(options, function(res) {
res.setEncoding("utf8");
res.on("data", function (chunk) {
content += chunk;
});
res.on("end", function () {
util.log(content);
});
});
req.end();