在 Node.js / Express 中，我如何“下载”页面并获取其 HTML？

Question

Inside the code, I want to download "http://www.google.com" and store it in a string. I know how to do that in urllib in python. But how do you do it in Node.JS + Express?

Answer 1

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();

Answer 2

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

Answer 3

Simple short and efficient code :)

var request = require("request");

request(
    { uri: "http://www.sitepoint.com" },
    function(error, response, body) {
        console.log(body);
    }
);

doc link: https://github.com/request/request

Answer 4

Yo can try with axios

var axios = require('axios');

axios.get("http://www.sitepoint.com", {
  headers: {
    Referer: 'http://www.sitepoint.com',
    'X-Requested-With': 'XMLHttpRequest'
  }
}).then(function (response) {
    console.log(response.data);
  });