Integrate with webpages using CasperJS (built on top of PhantomJS)

PhantomJS is a headless and scriptable WebKit runtime (aka browser) with JavaScript API.

Usage

in script.js

Login and delete spare movie tags on Douban.

var casper = require('casper').create({
  pageSettings: {
    loadImages: true,
    loadPlugins: false
  },
  logLevel: 'debug',
  verbose: true
});

// save session cookies
var fs = require('fs');
var page = require('webpage').create();

var cookieFile = 'cookies.json';

var saveSessionCookie = function() {
  try {
    fs.statSync(cookieFile);
  } catch (e) {
    fs.write(cookieFile, JSON.stringify(phantom.cookies), 'w');
  }
}

if (fs.isFile(cookieFile)) {
  Array.prototype.forEach.call(JSON.parse(fs.read(cookieFile)), function(x) {
    phantom.addCookie(x);
  });
}

// script
var loginUrl = 'https://accounts.douban.com/login';
var startUrl = 'https://movie.douban.com/people/vinta/all';

var tags_do_not_delete = [
  '丹麦', '新西兰', '新加坡', '以色列', '印度', '意大利', '瑞典', '墨西哥', '俄罗斯', '西班牙', '比利时'
];

casper.start(loginUrl, function() {
  this.echo(this.getCurrentUrl());
  this.echo(this.getTitle());

  this.capture('login.png');

  var data = {
    form_email: 'xxx',
    form_password: 'xxx'
  };

  // 可能會被豆瓣要求輸入驗證碼
  // 可以用 casperjs script.js --remote-debugger-port=9000
  // 先打開 login.png 看驗證碼是什麼
  // 到 http://127.0.0.1:9000/ 的 console 手動輸入驗證碼
  // data['captcha-solution'] = '123';

  this.waitForSelector('form#lzform');
  this.fill('form#lzform', data, true);
});

casper.then(function() {
  this.echo(this.getCurrentUrl());
  this.echo(this.getTitle());

  saveSessionCookie();

  this.capture('all.png');

  this.open(startUrl).then(function() {
    this.waitForSelector('#open_tags', function() {
      this.click('#open_tags');
    });

    this.waitWhileSelector('#open_tags');
  });
});

casper.then(function() {
  this.echo(this.getCurrentUrl());
  this.echo(this.getTitle());

  var links = this.evaluate(function() {
    var tagList = document.querySelectorAll('ul.tag-list li a');
    var theLinks = Array.prototype.map.call(tagList, function(elem) {
        return {
          tag: elem.textContent.trim(),
          href: elem.getAttribute('href'),
          count: parseInt(elem.nextElementSibling.textContent, 10)
        };
    });

    return theLinks;
  });

  var filteredLinks = links.filter(function(link) {
    if (link.count < 5 && tags_do_not_delete.indexOf(link.tag) == -1) {
      return true;
    }
    return false;
  });

  this.each(filteredLinks, function(self, link) {
    this.echo(link.tag + ', ' + link.count);

    self.thenOpen(link.href, function() {
      this.echo(this.getCurrentUrl());
      this.echo(this.getTitle());

      this.waitForSelector('#tag-del', function() {
        this.click('#tag-del');
      });

      this.waitForSelector('input[name="del_submit"]', function() {
        this.click('input[name="del_submit"]');
      });
    });
  });
});

casper.run();

To evaluate JavaScript code in the context of the webpage, you must use evaluate() function. The context is a sandbox.

ref:
http://docs.casperjs.org/en/latest/modules/index.html

ref:
https://github.com/vinta/playground/blob/master/casperjs/script.js

Save session cookies

--cookies-file=xxx.txt only store non-session cookies (which remain your logged-in or authenticated status). You have to save every cookie manually.

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

// save session cookies
var fs = require('fs');
var page = require('webpage').create();

var cookieFile = 'cookies.json';

var saveSessionCookie = function() {
  try {
    fs.statSync(cookieFile);
  } catch (e) {
    fs.write(cookieFile, JSON.stringify(phantom.cookies), 'w');
  }
}

if (fs.isFile(cookieFile)) {
  Array.prototype.forEach.call(JSON.parse(fs.read(cookieFile)), function(x) {
    phantom.addCookie(x);
  });
}

casper.start('yourUrl', function() {
  // do your shit
});

ref:
http://stackoverflow.com/questions/18739354/how-can-i-use-persisted-cookies-from-a-file-using-phantomjs

Run

$ docker run --rm -v `pwd`:/data vinta/casperjs:1.1.3 script.js

# or

$ brew install casperjs
$ casperjs script.js --disk-cache=true

ref:
https://hub.docker.com/r/vinta/casperjs/
https://hub.docker.com/r/zopanix/casperjs/

ref:
http://phantomjs.org/api/command-line.html

Run in debugging mode

$ casperjs script.js --remote-debugger-port=9000
$ open http://127.0.0.1:9000/
  • Click the first link (something like "file:///usr/local/Cellar/xxx").
  • In Sources tab, press "Enable Debugging" button.
  • In Console tab, type "__run();" to start.
  • Once breakpoints worked, you could go to Console tab to debug.

ref:
http://phantomjs.org/troubleshooting.html