智联招聘刷新简历

最新推荐文章于 2018-04-08 20:53:00 发布

吓人的鸟

最新推荐文章于 2018-04-08 20:53:00 发布

阅读量5k

点赞数

分类专栏：编程语言-python 代码库/程序片段文章标签： casperjs python

本文链接：https://blog.csdn.net/XIARENDENIAO/article/details/8673417

版权

编程语言-python 同时被 2 个专栏收录

30 篇文章 0 订阅

订阅专栏

代码库/程序片段

24 篇文章 0 订阅

订阅专栏

应一同学要求，写了个刷新智联简历的脚本，省得他一边奔波于面试还要一边刷简历。

主要工具还是神器casperjs！

1.capserjs程序：

1>访问自制的一个iframe组合页(验证码识别页+智联登录页)

2>把智联页的验证码截图并写入验证码识别页并提交

3>把验证码识别页返回的字符填入智联页的验证码框、用户名密码也填入相应位置，点击登录按钮

4>等待页面跳转并点击刷新按钮

5>循环点击刷新按钮

[dongsong@localhost js_study]$ cat zhilian.js 
var logPrint = true;
var icDir = '/tmp/raw_codes/';

function GUID ()
{
    var S4 = function ()
    {
        return Math.floor(
                Math.random() * 0x10000 /* 65536 */
            ).toString(16);
    };

    return (
            S4() + S4() + "-" +
            S4() + "-" +
            S4() + "-" +
            S4() + "-" +
            S4() + S4() + S4()
        );
}

function debug(st) {
        require('utils').dump(st);
}

function check_arg(casper, fileName)
{
        if (!casper.cli.has("username") || !casper.cli.has("passwd") || !casper.cli.has("starturl")) {
                console.log("\nUsage:\n\tcasperjs " + fileName + " --starturl=http://www.centos6.com:9000/mainapp/customized_iframe --username=xx --passwd=xx\n");
                casper.exit();
        }
}

function refresh()
{
        this.wait(10000,
                function() {
                        this.click('a[title="简历刷新"]');
                        this.log('refreshed my resume');
                }
        );
        this.run(refresh);
}

function main_navigation()
{
        //创建casper对象
        var casper = require("casper").create({
                verbose: logPrint,
                logLevel: "debug",
                onError: function(self,m){
                                this.capture("error.png");
                                console.log("FATAL:" + m);
                                self.exit();
                },
                onTimeout:function(self) { this.log('entire casper navigation timeout', 'error'); },
                timeout:86400 //整个脚本执行时间不能超过一天
        });

        //检查参数
        check_arg(casper, "zhilian.js");
        var starturl = casper.cli.get("starturl");
        var userName = casper.cli.get("username");
        var passWd = casper.cli.get("passwd");
        var icFile = null;


        //请求智联页面和验证码识别页面的iframe组合
        casper.start(starturl+'?aimUrl='+encodeURIComponent("http://my.zhaopin.com/myzhaopin/resume_index.asp"), 
                function then() {this.page.switchToChildFrame(0);} 
        );

        //等待验证码
        casper.waitFor(function check(){
                        if (this.visible('img[id="vimg"]')) {
                                this.log('identifying code appears');
                                icFile = icDir + GUID() + '.png';
                                //bounds = this.getElementBounds('img[node-type="pincode"]');
                                //this.capture('whole_for_render_completed.png');
                                //this.capture('code_for_render_completed.png', {top:bounds['top'],left:bounds['left'],width:bounds['width'],height:bounds['height']});
                                //this.capture(icFile, {top:bounds['top']+7,left:bounds['left']+7,width:bounds['width'],height:bounds['height']}); //加上了校准
                                this.captureSelector(icFile, 'img[id="vimg"]');
                                this.page.switchToParentFrame();
                                this.page.switchToChildFrame(1);
                                this.fill('form#icform', {'picfile':icFile}, true);
                                return true;
                        }
                        else {
                                this.log('identifying code does not appear')
                                return false;
                        }
                },
                function then() {},
                function onTimeout() { this.log('timeout: oauth form still exists and identifying code does not appear', 'error'); },
                timeout = 30000
        );

        //获取验证码字符
        casper.waitFor(function check(){
                                if (this.exists('h')) {
                                        recognizedCode = this.fetchText('h');
                                        this.log('result code is ' + recognizedCode);
                                        this.page.switchToParentFrame();
                                        this.page.switchToChildFrame(0);
                                        this.fill('form[name="frmLogin"]', {'loginname':userName}, false);
                                        this.fill('form[name="frmLogin"]', {'password':passWd}, false);
                                        this.fill('form[name="frmLogin"]', {'Validate':recognizedCode}, false);
                                        this.click('input[id="loginbutton"]');
                                        return true;
                                } else {
                                        this.log('waiting for recognized string', 'debug');
                                        return false;
                                }
                        },
                function then() {this.capture('filled.png');},
                function onTimeout() { this.log('timeout: waiting for recognized string', 'error'); },
                timeout = 1000000
        );

        //等到页面跳转并点击刷新按钮
        casper.waitForSelector('a[title="简历刷新"]', function() {
                                this.capture('to_click.png');
                                this.click('a[title="简历刷新"]');
                        },
                function onTimeout() { this.log('wait form failed', 'error'); },
                timeout = 10000
        );

        //loop:隔一段时间就刷新一次简历(用waitFor和wait实现循环，貌似不靠谱儿！)
        /*
        casper.waitFor(function check(){
                        this.wait(10000,
                                function() {
                                        this.click('a[title="简历刷新"]');
                                        this.log('refreshed my resume');
                                }
                        );
                        return false;
                },
                function then() {},
                function onTimeout() {this.log('timeout: refresh loop competed.', 'error');},
                timeout = 120000
        );*/

        //launch the navigation 
        casper.run(refresh);
}

main_navigation();

结果：

[dongsong@localhost js_study]$ casperjs zhilian.js --username="xxx@gmail.com" --passwd="xxxx" --starturl="http://localhost:9000/mainapp/customized_iframe"
[info] [phantom] Starting...
[info] [phantom] Execution timeout set to 86400000ms
[info] [phantom] Running suite: 5 steps
[debug] [phantom] opening url: http://localhost:9000/mainapp/customized_iframe?aimUrl=http%3A%2F%2Fmy.zhaopin.com%2Fmyzhaopin%2Fresume_index.asp, HTTP GET
[debug] [phantom] Navigation requested: url=http://localhost:9000/mainapp/customized_iframe?aimUrl=http://my.zhaopin.com/myzhaopin/resume_index.asp, type=Other, lock=true, isMainFrame=true
[debug] [phantom] url changed to "http://localhost:9000/mainapp/customized_iframe?aimUrl=http://my.zhaopin.com/myzhaopin/resume_index.asp"
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/myzhaopin/resume_index.asp, type=Other, lock=true, isMainFrame=false
[debug] [phantom] Navigation requested: url=http://localhost:9000/mainapp/fileform, type=Other, lock=true, isMainFrame=false
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/loginmgr/login.asp?BkUrl=/myzhaopin/resume_index.asp?, type=Other, lock=true, isMainFrame=false
[debug] [phantom] Successfully injected Casper client-side utilities
[info] [phantom] Step 2/5 http://localhost:9000/mainapp/customized_iframe?aimUrl=http://my.zhaopin.com/myzhaopin/resume_index.asp (HTTP 200)
[info] [phantom] Step 2/5: done in 9751ms.
[debug] [phantom] Successfully injected Casper client-side utilities
[info] [phantom] Step 3/5 http://my.zhaopin.com/loginmgr/login.asp?BkUrl=/myzhaopin/resume_index.asp? (HTTP 200)
[info] [phantom] Step 3/5: done in 9853ms.
[debug] [phantom] identifying code appears
[debug] [phantom] Capturing page to /home/dongsong/js_study/whole_for_render_completed.png
[info] [phantom] Capture saved to /home/dongsong/js_study/whole_for_render_completed.png
[debug] [phantom] Capturing page to /tmp/raw_codes/81358a65-119e-c715-53e5-617fdbf31c9.png with clipRect {"height":27,"left":941,"top":223,"width":72}
[info] [phantom] Capture saved to /tmp/raw_codes/81358a65-119e-c715-53e5-617fdbf31c9.png
[debug] [phantom] Successfully injected Casper client-side utilities
[info] [remote] attempting to fetch form element from selector: 'form#icform'
[debug] [remote] Set "picfile" field value to /tmp/raw_codes/81358a65-119e-c715-53e5-617fdbf31c9.png
[info] [remote] submitting form to /mainapp/recognize, HTTP POST
[info] [phantom] waitFor() finished in 352ms.
[debug] [phantom] Navigation requested: url=http://localhost:9000/mainapp/recognize, type=FormSubmitted, lock=true, isMainFrame=false
[debug] [phantom] Successfully injected Casper client-side utilities
[info] [phantom] Step 4/6 http://localhost:9000/mainapp/recognize (HTTP 200)
[info] [phantom] Step 4/6: done in 62320ms.
[info] [phantom] Step 5/6 http://localhost:9000/mainapp/recognize (HTTP 200)
[info] [phantom] Step 5/6: done in 62418ms.
[debug] [phantom] result code is dl5k
[info] [remote] attempting to fetch form element from selector: 'form[name="frmLogin"]'
[debug] [remote] Set "loginname" field value to dongsong.xu@gmail.com
[info] [remote] attempting to fetch form element from selector: 'form[name="frmLogin"]'
[debug] [remote] Set "password" field value to ********
[info] [remote] attempting to fetch form element from selector: 'form[name="frmLogin"]'
[debug] [remote] Set "Validate" field value to dl5k
[debug] [phantom] Mouse event 'click' on selector: input[id="loginbutton"]
[info] [phantom] waitFor() finished in 201ms.
[info] [phantom] Step 6/7 http://my.zhaopin.com/loginmgr/login.asp?BkUrl=/myzhaopin/resume_index.asp? (HTTP 200)
[debug] [phantom] Capturing page to /home/dongsong/js_study/filled.png
[info] [phantom] Capture saved to /home/dongsong/js_study/filled.png
[info] [phantom] Step 6/7: done in 62941ms.
[info] [phantom] Step 7/7 http://my.zhaopin.com/loginmgr/login.asp?BkUrl=/myzhaopin/resume_index.asp? (HTTP 200)
[info] [phantom] Step 7/7: done in 62946ms.
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/loginmgr/loginproc.asp, type=FormSubmitted, lock=true, isMainFrame=false
[debug] [phantom] Successfully injected Casper client-side utilities
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/myzhaopin/resume_index.asp?, type=Other, lock=true, isMainFrame=false
[debug] [phantom] Successfully injected Casper client-side utilities
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/MYZHAOPIN/new_register_tracking.asp, type=Other, lock=true, isMainFrame=false
[info] [phantom] waitFor() finished in 6367ms.
[info] [phantom] Step 8/8 http://my.zhaopin.com/myzhaopin/resume_index.asp? (HTTP 200)
[debug] [phantom] Capturing page to /home/dongsong/js_study/to_click.png
[info] [phantom] Capture saved to /home/dongsong/js_study/to_click.png
[debug] [phantom] Mouse event 'click' on selector: a[title="简历刷新"]
[debug] [phantom] Navigation requested: url=http://my.zhaopin.com/myzhaopin/resume_index.asp?#, type=LinkClicked, lock=true, isMainFrame=false
[info] [phantom] Step 8/8: done in 72774ms.
[info] [phantom] Done 8 steps in 72774ms
[info] [phantom] Running suite: 9 steps
[info] [phantom] Step 9/9 http://my.zhaopin.com/myzhaopin/resume_index.asp?# (HTTP 200)
[info] [phantom] Step 9/9: done in 72876ms.
[info] [phantom] wait() finished waiting for 10000ms.
[debug] [phantom] Mouse event 'click' on selector: a[title="简历刷新"]
[debug] [phantom] refreshed my resume
[info] [phantom] Done 9 steps in 82898ms
[info] [phantom] Running suite: 10 steps
[info] [phantom] Step 10/10 http://my.zhaopin.com/myzhaopin/resume_index.asp?# (HTTP 200)
[info] [phantom] Step 10/10: done in 83000ms.
[info] [phantom] wait() finished waiting for 10000ms.
[debug] [phantom] Mouse event 'click' on selector: a[title="简历刷新"]
[debug] [phantom] refreshed my resume
[info] [phantom] Done 10 steps in 93041ms
[info] [phantom] Running suite: 11 steps
[info] [phantom] Step 11/11 http://my.zhaopin.com/myzhaopin/resume_index.asp?# (HTTP 200)
[info] [phantom] Step 11/11: done in 93144ms.
^C

2.后台验证码识别程序1

提供前述的iframe组合页面

提供验证码提交的页面：收到post来的图片文件后通过邮件发送到目标邮箱并扫描数据库该图片对应的破解字符，扫描到字符就返回给浏览器

3.后台验证码识别程序2

登录发送验证码的邮箱，定时(30s)扫描新邮件，并把验证码的破解字符更新到数据库

4.验证码的破解：需要人为读取邮件中的验证码图片，并用普通字符回复邮件

2和3的程序涉及文件比较多就不贴出来了，按照上述思想自己写是没多大难度的。

贴一个刷新的效果图：