以前公司业务人员手动操作，一天也只能获取1000来条数据，通过程序获得了非常大的改观。程序目的是自动验证登录并查询获取相关信息，对验证码上每个字显示的宽度有要求，需要事先预设好，因为需要将验证码图片上的字分别裁剪单独分析。当然一般一个网站的验证码宽度都相对固定。
1
package com.xiaohang.readcode;
2
3import java.awt.*;
4import java.awt.image.BufferedImage;
5import java.io.*;
6import java.net.URL;
7import javax.imageio.*;
8
9
public class ImageCode 
{
10
BufferedImage imd; // 待识别图像
11
12 private int iw, ih; // 图像宽和高
13
14 //public final static String path = "E:\\codeimages\\1.bmp";
15
16
public static void main(String []args){
17
18 try{
19
20 ImageCode app = new ImageCode();
21
22 //String s = app.getImageNum("http://*****.cjn.cn/gcode.act");
23 String s = app.getImageNum("E:\\codeimages\\1.bmp");
24 System.out.println("result is : " + s);
25
26
}catch(Exception ex)
27 {
28 ex.printStackTrace();
29 }
30 }
31
32 public String getImageNum(String file) {
33
34 StringBuffer sb = new StringBuffer("");
35 try {
36 // imd = ImageIO.read(new URL(file)); // 用ImageIO的静态方法读取图像
37 imd = ImageIO.read(new File(file));
38 BufferedImage newim[] = new BufferedImage[4];
39 int[] x = new int[4];
40 // 将图像分成4块，因为要处理的文件都有四个数字
41 newim[0] = imd.getSubimage(5, 0, 10, 15);
42 newim[1] = imd.getSubimage(18, 0, 10, 15);
43 newim[2] = imd.getSubimage(31, 0, 10, 15);
44 newim[3] = imd.getSubimage(44, 0, 10, 15);
45
46 for (int k = 0; k < 4; k++) {
47 x[k] = 0;
48 // ImageIO.write(newim[k], "JPEG", new File("E:\\codeimages\\"+k+".jpeg"));
49 this.iw = newim[k].getWidth(null);
50 this.ih = newim[k].getHeight(null);
51 int[] pix = new int[iw * ih];
52 // 二进制图像，将像数读取出来，转换成0、1图像数组
53
54 for (int i = 0; i < ih; i++) {
55 for (int j = 0; j < iw; j++) {
56 pix[i * (iw) + j] = newim[k].getRGB(j, i);
57 String code = String.valueOf(pix[i * (iw) + j]);
58 if (code.length() >= 8)
59 pix[i * (iw) + j] = 1;
60 else
61 pix[i * (iw) + j] = 0;
62
63 x[k] = x[k] + pix[i * (iw) + j];
64 }
65 }
66
67 // 得到匹配的数字
68 int r = this.getMatchNum(pix);
69 sb.append(r);
70 // System.out.println("x=" + x[k]);
71 }
72
73 } catch (Exception ex) {
74 ex.printStackTrace();
75 }
76 return sb.toString();
77 }
78
79 static int[][] value = {
80 // 0
81 {
82 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
83 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
84 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
85 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
86 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
87 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
88 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
89 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
90 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
91 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
92 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
93 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
94 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
95 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
96 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
97 },
98 // 1
99 {
100 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
101 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
102 0, 0, 0, 0, 1, 1, 1, 0, 0, 0,
103 0, 0, 0, 0, 1, 1, 1, 0, 0, 0,
104 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
105 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
106 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
107 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
108 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
109 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
110 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
111 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
112 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
113 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
114 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
115 },
116 // 2
117 {
118 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
119 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
120 0, 0, 0, 1, 1, 1, 0, 0, 0, 0,
121 0, 0, 1, 1, 1, 1, 1, 0, 0, 0,
122 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
123 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
124 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
125 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
126 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
127 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,
128 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,
129 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
130 0, 1, 1, 1, 1, 1, 1, 1, 0, 0,
131 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
132 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
133 },
134
135
136 // 3
137 {
138 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
139 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
140 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
141 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
142 0, 0, 1, 0, 0, 0, 1, 1, 0, 0,
143 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
144 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
145 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
146 0, 0, 0, 0, 1, 1, 1, 1, 0, 0,
147 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
148 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
149 0, 0, 1, 1, 1, 1, 1, 0, 0, 0,
150 0, 0, 1, 1, 1, 1, 0, 0, 0, 0,
151 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
152 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
153 },
154 // 4
155 {
156 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
157 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
158 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,
159 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
160 0, 0, 0, 0, 1, 1, 1, 0, 0, 0,
161 0, 0, 0, 0, 1, 1, 1, 0, 0, 0,
162 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
163 0, 0, 1, 1, 0, 1, 1, 0, 0, 0,
164 0, 1, 1, 1, 1, 1, 1, 1, 0, 0,
165 0, 1, 1, 1, 1, 1, 1, 1, 0, 0,
166 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
167 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
168 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
169 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
170 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
171 },
172 // 5
173 {
174 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
175 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
176 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
177 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
178 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,
179 0, 0, 1, 1, 1, 1, 0, 0, 0, 0,
180 0, 0, 1, 0, 1, 1, 1, 0, 0, 0,
181 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
182 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
183 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
184 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,
185 0, 0, 1, 1, 1, 1, 1, 0, 0, 0,
186 0, 0, 1, 1, 1, 1, 0, 0, 0, 0,
187 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
188 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
189 },
190 // 6
191 {
192 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
193 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
194 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
195 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
196 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,
197 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,
198 0, 0, 1, 1, 1, 1, 0, 0, 0, 0,
199 0, 0, 1, 1, 1, 1, 1, 0, 0, 0,
200 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
201 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
202 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
203 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
204 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
205 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
206 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
207 },
208 // 7
209 {
210 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
211 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
212 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
213 0, 1, 1, 1, 1, 1, 1, 1, 0, 0,
214 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
215 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
216 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
217 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
218 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
219 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
220 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
221 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,
222 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,
223 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,
224 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
225 },
226 // 8
227 {
228 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
229 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
230 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
231 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
232 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
233 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
234 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
235 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
236 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
237 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
238 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,
239 0, 0, 1, 1, 1, 1, 1, 1, 0, 0,
240 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,
241 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
242 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
243 },
244 // 9
245 {
246 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
247 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
248 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
249 0, 0, 0, 1, 0, 0, 1, 0, 0, 0,
250 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
251 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
252 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
253 0, 0, 0, 1, 0, 0, 1, 1, 0, 0,
254 0, 0, 0, 0, 1, 1, 0, 1, 0, 0,
255 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,
256 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,
257 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,
258 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,
259 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
260 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
261 } };
262
263 // 图像像素相减去最小绝对值得到最接近结果
264 public int getMatchNum(int[] pix){
265
266 int result = -1;
267 int temp = 100;
268 int x;
269 for(int k = 0 ; k < 10 ; k++){
270
271 x = 0 ;
272 for(int i = 0 ; i < 150 ; i++){ // lenght=120
273 x = x+Math.abs(pix[i] - value[k][i]); // 取绝对值
274 }
275
276 if(x < temp){
277 temp = x;
278 result = k;
279 }
280 }
281 return result;
282 }
283
284
285
}
286
原创文章，转载请注明出处。
http://www.blogjava.net/beijing2008/articles/285556.html
posted on 2009-07-05 15:28
.Sun 阅读(848)
评论(1) 编辑 收藏