javascript - 使用 phantomjs 和 Jquery 登录网页

Question

一般来说，我是 phantomjs、Java 脚本和 WebScraping 的新手。我想做的是基本的 http 身份验证，然后访问另一个 URL 以获取一些信息。这是我到目前为止所拥有的。请告诉我我做错了什么。

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

page.onConsoleMessage = function(msg) {
   console.log(msg);
};

page.onAlert = function(msg) {
   console.log('alert!!>' + msg);
};

page.settings.userName = "foo";
page.settings.password = "bar";

page.open("http://localhost/login", function(status) {
    console.log(status);
    var retval = page.evaluate(function() {
       return "test";
    });
    console.log(retval);

    page.open("http://localhost/ticket/" + system.args[1], function(status) {
        if ( status === "success" ) {
            page.injectJs("jquery.min.js");
            var k = page.evaluate(function () {
                var a = $("div.description > h3 + p");

                if (a.length == 2) {
                    console.log(a.slice(-1).text())
                } 
                else {
                    console.log(a.slice(-2).text())
                }
            //return document.getElementById('addfiles');
            });

        }
    });
    phantom.exit();
});

我正在向该文件传递一个参数:一个附加到第二个 URL 的票号。

Answer 1

我会推荐 CasperJS对此高度评价。

CasperJS is an open source navigation scripting & testing utility written in Javascript and based on PhantomJS — the scriptable headless WebKit engine. It eases the process of defining a full navigation scenario and provides useful high-level functions, methods & syntactic sugar for doing common tasks such as:

• defining & ordering browsing navigation steps
• filling & submitting forms
• clicking & following links
• capturing screenshots of a page (or part of it)
• testing remote DOM
• logging events
• downloading resources, including binary ones
• writing functional test suites, saving results as JUnit XML
• scraping Web contents

(来自 CasperJS 网站)

我最近花了一天时间尝试让 PhantomJS 自己完成一些事情，比如填写登录表单并导航到下一页。

CasperJS 也有一个很好的为表单构建的 API:

http://docs.casperjs.org/en/latest/modules/casper.html#fill

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

casper.start('http://some.tld/contact.form', function() {
    this.fill('form#contact-form', {
        'subject':    'I am watching you',
        'content':    'So be careful.',
        'civility':   'Mr',
        'name':       'Chuck Norris',
        'email':      'chuck@norris.com',
        'cc':         true,
        'attachment': '/Users/chuck/roundhousekick.doc'
    }, true);
});

casper.then(function() {
    this.evaluateOrDie(function() {
        return /message sent/.test(document.body.innerText);
    }, 'sending message failed');
});

casper.run(function() {
    this.echo('message sent').exit();
});