Get generated HTML after JS manipulates the DOM and pass request headers

问题

I need to get the generated HTML source of the page after JS DOM manipulation has all been done. I was using Phantomas https://github.com/macbre/phantomas for this purpose, but unfortunately it does not provide a way to pass in request headers.

Is there a library out there that will allow to pass request headers and then get the generated HTML source code.

Any pointers would be greatly helpful

回答1:

You can use "PhantomJS WebKit scriptable".

Specify customHeaders and get the page.content:

var webPage = require('webpage');
var page = webPage.create();

page.customHeaders = {
  "X-Test": "foo",
  "DNT": "1"
};

page.open('http://phantomjs.org', function (status) {
  var content = page.content;
  console.log('Content: ' + content);
  phantom.exit();
});

Save it to test.js and run:

phantomjs test.js

回答2:

You can use casperjs.

Pass headers in a settings object to the open() function and use getPageContent() to get the HTML source of the page:

var casper = require('casper').create();

var headers = {
    'Accept-Language': 'en-US,en;q=0.8',
    'HEADER-XYZ': 'HEADER-XYZ-DATA'
};

casper.start().then(function () {
    this.open("http://casperjs.org", {
        method: 'get',
        headers: headers
    });
});

casper.then(function() {
    console.log(this.getPageContent());
});

casper.run(function() {
    this.exit();
});

来源：https://stackoverflow.com/questions/27596852/get-generated-html-after-js-manipulates-the-dom-and-pass-request-headers