Arch-03-10-自动投票机器人
由于生活中需要对网站上的某张图片投票决定排名，无可避免地想起了做个自动投票机器人。经过一天的尝试，三种方案：
（1）保存投票页面到本地，分析代码，直接用 js 和 ajax 循环提交，每次循环中间随机休眠几秒。一开始居然有效，不过好景不长，第二天就被网站改了页面，不能直接提交了。
<html><head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> <title> 自动投票机器人一 </title> <link rel="stylesheet" href="style.css" type="text/css"media="screen"> <script type="text/javascript">var counters=0;var xmlHttp;function S_xmlhttprequest(){if(window.ActiveXObject){xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");} else if(window.XMLHttpRequest){xmlHttp = new XMLHttpRequest();}}function vote(){url =1;//idS_xmlhttprequest();xmlHttp.open("GET","http://www.xxxx.com/work/vote.php?id="+url+"&"+Math.random(),true);xmlHttp.send(null);alert(' 投票成功！\n 谢谢您的支持！'); counters++; document.getElementById("counter").innerText=counters; setTimeout("vote()",nextTime());} function Workspace_OnLoad() { setTimeout("vote()",1000); } function nextTime(){ var vNum=1000;vNum = Math.random();vNum = Math.round(vNum*60000);return vNum; } </script> </head> <body class="bgcolor" > <div align="center"> <table class="bgjpg" align="center" border="0" cellpadding="0" cellspacing="0" width="100%"> <tbody> <tr height="10"> <td> </td> </tr> <tr> <td height="30"> </td> </tr> </tbody> </table> </div> </body></html>
（2）发现需要提交表单到服务器，而不是直接发送GET请求，并且有 cookie 检查校验码，尝试用 java 编程，好象没成功，但理论上可行。
[*]获取校验码图片
[*]tesseract OCR 解析校验码图片
[*]尝试提交模拟表单
[*]需要的 jar 包和 Tesseract OCR在网上搜。
package A;import java.io.ByteArrayInputStream;import java.io.ByteArrayOutputStream;import java.io.DataOutputStream;import java.io.File;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStream;import javax.servlet.RequestDispatcher;import javax.servlet.ServletException;import javax.servlet.http.HttpServletRequest;import javax.servlet.http.HttpServletResponse;import org.apache.commons.httpclient.Header;import org.apache.commons.httpclient.HttpClient;import org.apache.commons.httpclient.HttpException;import org.apache.commons.httpclient.HttpStatus;import org.apache.commons.httpclient.NameValuePair;import org.apache.commons.httpclient.methods.PostMethod;import com.overseas.ocr.ImageFilter;import com.overseas.ocr.ImageIOHelper;import com.overseas.sys.InitEnv;import com.overseas.util.PicUtil;import net.sourceforge.tess4j.*;public class TesseractExample {public int success=0;public static void main(String[] args) {//File imageFile = new File("eurotext.tif");//Tesseract instance = Tesseract.getInstance(); // JNA Interface Mapping// Tesseract1 instance = new Tesseract1(); // JNA Direct Mappingtry {TesseractExample t =new TesseractExample();t.doit() ;//String result = instance.doOCR(imageFile);//System.out.println(result);} catch (Exception e) {System.err.println(e.getMessage());}}private void doit() {int counter =1000000;for(int i=0;i<counter;i++){try{Thread.sleep((int)(Math.random()*50000));}catch(Exception e){e.printStackTrace();}String decodeText =decode();System.out.println("Start excute..."+i+"====="+decodeText);if(decodeText==null || decodeText.trim().length()<4 ){continue;//next times}decodeText =decodeText.trim();if(decodeText.length()>4)decodeText =decodeText.substring(0,4);try{int code =Integer.parseInt(decodeText);// submit votevote(code);System.out.println("call vote..."+code);}catch(Exception e){continue;}}}private void vote(int code) {HttpClient httpClient = new HttpClient();String url = "http://www.xxxx.com/work/chick.php?id=1";PostMethod postMethod = new PostMethod(url);// 填入各个表单域的值NameValuePair[] data = { new NameValuePair("numtext", Integer.toString(code)), new NameValuePair("submit", "确认"),};// 将表单的值放入postMethod中postMethod.setRequestBody(data);// 执行postMethodint statusCode = 0;try { statusCode = httpClient.executeMethod(postMethod);} catch (HttpException e) { // TODO Auto-generated catch block e.printStackTrace();} catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace();}// HttpClient对于要求接受后继服务的请求，象POST和PUT等不能自动处理转发// 301或者302if (statusCode == HttpStatus.SC_MOVED_PERMANENTLY || statusCode == HttpStatus.SC_MOVED_TEMPORARILY){ // 从头中取出转向的地址 Header locationHeader = postMethod.getResponseHeader("location"); String location = null; if (locationHeader != null) { location = locationHeader.getValue(); System.out.println("The page was redirected to:" + location); } else { System.err.println("Location field value is null."); } return;}else{ System.out.println(postMethod.getStatusLine()); String str = ""; try { str = postMethod.getResponseBodyAsString(); System.out.println("Success! ooooooooooooooooo"+success++); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } System.out.println("======================================================"); System.out.println(utf8Togb2312(str));}postMethod.releaseConnection(); return ;}private String decode() {String url = "http://www.xxxx.com/work/che.php?"+Math.random();InputStream instream = InitEnv.class.getResourceAsStream(InitEnv.CERTPATH);ByteArrayOutputStream outputStream = new ByteArrayOutputStream();String protocol = "http";byte[] b = null;try {if (url.startsWith("https")) {protocol = "https";}PicUtil.getPic(protocol, url, 80, "", instream,outputStream);b = outputStream.toByteArray();ImageFilter imageFilter = new ImageFilter(new ByteArrayInputStream(b));outputStream.close();ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();ImageIOHelper.createImage(imageFilter.changeGrey(),byteArrayOutputStream);File file = new File("C:\\temp\\ocr.tiff ");if (!file.exists()) {file.createNewFile();}DataOutputStream to = new DataOutputStream(new FileOutputStream(file));byteArrayOutputStream.writeTo(to);byteArrayOutputStream.close();Tesseract instance = Tesseract.getInstance();String result = instance.doOCR(file);return result;} catch (Exception e) {e.printStackTrace();return null;}}private String utf8Togb2312(String str){ StringBuffer sb = new StringBuffer(); for(int i=0; i<str.length(); i++) { char c = str.charAt(i); switch (c) { case '+': sb.append(' '); break; case '%': try { sb.append((char)Integer.parseInt( str.substring(i+1,i+3),16)); } catch (NumberFormatException e) { throw new IllegalArgumentException(); } i += 2; break; default: sb.append(c); break; } } // Undo conversion to external encoding String result = sb.toString(); String res=null; try{ byte[] inputBytes = result.getBytes("8859_1"); res= new String(inputBytes,"UTF-8"); } catch(Exception e){} return res;}}
（3）既然前面两种方法都没办法成功，尝试用第三种方法吧，比较复杂，但理论上一定可用（做出来后才发现，投票时间已经结束，无法验证）
[*]greasemonkey
[*]ajax 取得图片
[*]上传到图片解析服务器（需要搭建专门 OCR 解析服务器）
[*]从解析服务器返回解析后的校验码
[*]填充表单校验码，提交
// ==UserScript==// @name AutoVote// @namespace autovote// @include http://www.xxxx.com/work/workshow.php?id=1// @include http://www.xxxx.com/work/index.php// @include http://www.xxxx.com/work/show.php// ==/UserScript==var VOTE_URL='http://www.xxxx.com/work/workshow.php?id=1';var IMG_URL ='http://www.xxxx.com/work/che.php?';var DECODE_SERVER_URL ='http://localhost/decode/image';var MAX_COUNT =10;var counter =0;function start(){// 1. direct to vote pageif(counter>MAX_COUNT) return;if(document.location.href!=VOTE_URL){document.location.href =VOTE_URL;} document.getElementById('title').style.display="block";// 2. get code from PLUS_VOTE_SERVER load_image();// 3. full code value// 4. submit// 5. open new window// 6. close current windows}function load_image(){if(counter>MAX_COUNT) return;counter++;alert("2. get code from PLUS_VOTE_SERVER");var imageSrc = IMG_URL+Math.random(1); GM_xmlhttpRequest({method: 'GET', url: imageSrc, overrideMimeType: 'text/plain; charset=x-user-defined', onload: function(response) { decode_image(response.responseText); } }); }function decode_image(data){ var textbox = document.getElementById('numtext'); textbox.value = 'working...'; upload(data);}function upload(data) {var darray=data_array(data);GM_xmlhttpRequest({ method: 'POST', headers:{'Content-type':'application/x-www-form-urlencoded'}, url: DECODE_SERVER_URL, data: 'data='+darray, onload: function(response) { submit_form(response.responseText); }});}function submit_form(data){if(data==-1){load_image();} var textbox = document.getElementById('numtext'); textbox.value = data; var form1 = document.forms; //alert("submit ..."); form1.submit();}function data_array(data){ var data_array = []; for (var i = 0; i < data.length; i++) data_array.push(data.charCodeAt(0) & 0xff); return data_array;}start();
页:
[1]