參考：
http://blog.csdn.net/lanphaday/archive/2007/10/28/1852726.aspx
http://www.zhuaxia.com/item/852269537
在web抓取，有些網站會判斷過度讀取會有驗證碼輸入：
java
package Main;
import java.awt.image.BufferedImage;
import java.net.URL;
import javax.imageio.ImageIO;
public class Test {
public static void main(String[] args) throws Exception {
BufferedImage img = ImageIO.read(new URL("file:/C:/src/python/gve/22.jpeg"));
int imgWith = img.getWidth();
int imgHeight = img.getHeight();
int bgint = img.getRGB(0, 0);
for (int y = 0; y < imgHeight; y++) {
System.out.println();
for (int x = 0; x < imgWith; x++) {
System.out.print(getBit(img, x, y,bgint));
}
}
}
private static char getBit(BufferedImage img, int x, int y,int bgint) {
int intCurtColor;
intCurtColor = img.getRGB(x, y);
return (intCurtColor == bgint) ? '0' : ' ';
}
}
000 000 0 0 00 0 0 0 0
0 000 00 0 0 0 0 0
00 00 0 0 00 0 00 0 00 0
0000 0 0 0 0 0 0 00 0 0
00 0 0 0 00 0
00 0 00 0 0 00 0
0 0 0 0 0 0 00 0
00 00 0 0 0 0 0 00 0
0 0 0 00 0 0 0 0
0 00 0 0 0 00
0 0 00 0 0 00
00 0 0 00 0 0 0 0
00 0 0 0 00 0 0 0 0 0
0 0 00 0 0 00 0000
python
#encoding=utf-8
import Image,ImageEnhance,ImageFilter
import sys
image_name = "./22.jpeg"
#去處 干擾點
im = Image.open(image_name)
im = im.filter(ImageFilter.MedianFilter())
enhancer = ImageEnhance.Contrast(im)
im = enhancer.enhance(2)
im = im.convert('1')
#im.show() #測試查看
s = 12 #啟始 切割點 x
t = 2 #啟始 切割點 y
w = 10 #切割 寬 +y
h = 15 #切割 長 +x
im_new = []
for i in range(4): #驗證碼切割
im1 = im.crop((s+w*i+i*2,t,s+w*(i+1)+i*2,h))
im_new.append(im1)
#im_new[0].show()#測試查看
xsize, ysize = im_new[0].size
gd = []
for i in range(ysize):
tmp=[]
for j in range(xsize):
if( im_new[0].getpixel((j,i)) == 255 ):
tmp.append(1)
else:
tmp.append(0)
gd.append(tmp)
#看效果
for i in range(ysize):
print gd[i]
比如 "0"
[ 1, 1, 0, 0, 0, 0, 1, 1, 1, 1]
[0, 0, 0, 0, 0, 0, 0, 1, 1, 1]
[0, 0, 0, 1, 1, 0, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 1, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 0, 1, 1, 1, 0, 0, 0, 1]
[0, 0, 0, 1, 1, 0, 0, 0, 0, 1]
[ 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
[ 1, 1, 0, 0, 0, 0, 0, 1, 1, 1]
有時間 在學習下 匹配。
整理 m.tkk7.com/Good-Game
|