标签：function keyword linu hang tle word key 替换 oca
python有专门图片识别的库
我用的是pytesseract
Python-tesseract is a wrapper for google’s Tesseract-OCR
( http://code.google.com/p/tesseract-ocr/ ). It is also useful as a
stand-alone invocation script to tesseract, as it can read all image types
supported by the Python Imaging Library, including jpeg, png, gif, bmp, tiff,
and others, whereas tesseract-ocr by default only supports tiff and bmp.
Additionally, if used as a script, Python-tesseract will print the recognized
text in stead of writing it to a file. Support for confidence estimates and
bounding box data is planned for future releases.大意如下：
1.Python-tesseract是一个基于google’s Tesseract-OCR的独立封装包
2.Python-tesseract功能是识别图片文件中文字，并作为返回参数返回识别结果
3.Python-tesseract默认支持tiff、bmp格式图片，只有在安装PIL之后，才能支持jpeg、gif、png等其他图片格式
那么问题来了，PIL是什么？
PIL：Python Imaging Library，已经是Python平台事实上的图像处理标准库了。PIL功能非常强大，但API却非常简单易用。
在Debian/Ubuntu Linux下直接通过apt安装：
|
1
|
$ sudo apt-get install python-imaging
|
Mac和其他版本的Linux可以直接使用easy_install或pip安装，安装前需要把编译环境装好：
|
1
|
$ sudo easy_install PIL
|
如果安装失败，根据提示先把缺失的包（比如openjpeg）装上。
Windows平台就去PIL官方网站下载exe安装包。
直接安装pytesseract
|
1
|
$ sudo pip install pytesseract
|
ubuntu安装成功后
然后测试一下，随便找了个简单的验证码图片test.png放在同一目录下
|
1
2
3
4
5
6
7
8
9
|
# -*- coding:utf -8-*-
import pytesseract
from PIL import Image
image = Image.open(‘test.png‘)
code = pytesseract.image_to_string(image)
print (code)
|
出现了报错
OSError: [Errno 2] No such file or directory
黑人问号？？？
mmp,开始我以为是文件读不到
结果到网上查，是没有安装tesseract-ocr
然后安装下
|
1
|
apt-get install tesseract-ocr
|
可以，很完美
接着写我的脚本，发现验证码全是数字
于是要把一些容易读出字母的数字改过来
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
|
change={
‘O‘:‘0‘,
‘o‘:‘0‘,
‘I‘:‘1‘,
‘i‘:‘1‘,
‘L‘:‘1‘,
‘l‘:‘1‘,
‘Z‘:‘2‘,
‘z‘:‘2‘,
‘e‘:‘3‘,
‘a‘:‘4‘,
‘S‘:‘5‘,
‘s‘:‘5‘,
‘b‘:‘6‘,
‘T‘:‘7‘,
‘t‘:‘7‘,
‘q‘:‘9‘
};
|
替换的时候
|
1
2
|
for x in change:
text = text.replace(x,change[x])
|
把他们合起来
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
|
# -*-coding:utf-8-*-
import pytesseract
from PIL import Image
image = Image.open(‘test.png‘)
code = pytesseract.image_to_string(image)
change={
‘O‘:‘0‘,
‘o‘:‘0‘,
‘I‘:‘1‘,
‘i‘:‘1‘,
‘L‘:‘1‘,
‘l‘:‘1‘,
‘Z‘:‘2‘,
‘z‘:‘2‘,
‘e‘:‘3‘,
‘a‘:‘4‘,
‘S‘:‘5‘,
‘s‘:‘5‘,
‘b‘:‘6‘,
‘T‘:‘7‘,
‘t‘:‘7‘,
‘q‘:‘9‘
};
for x in change:
code = code.replace(x,change[x])
print code
|
python获取图片并写到本地的脚本如下
|
1
2
3
4
5
6
7
8
|
# -*- coding:utf-8 -*-
import requests
r = requests.get(url = "http://example/test.php")
data = r.content
f = file("captchatest.png","wb")
f.write(data)
f.close()
|
最后的登录脚本为
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
|
# -*- coding:utf-8 -*-
import requests
import pytesseract
from PIL import Image
s = requests.session()
def change_to_string():
image = Image.open(‘captchatest.png‘)
code = pytesseract.image_to_string(image)
change={
‘O‘:‘0‘,
‘o‘:‘0‘,
‘I‘:‘1‘,
‘i‘:‘1‘,
‘L‘:‘1‘,
‘l‘:‘1‘,
‘Z‘:‘2‘,
‘z‘:‘2‘,
‘e‘:‘3‘,
‘a‘:‘4‘,
‘S‘:‘5‘,
‘s‘:‘5‘,
‘b‘:‘6‘,
‘T‘:‘7‘,
‘t‘:‘7‘,
‘q‘:‘9‘
};
for x in change:
code = code.replace(x,change[x])
return code
r = s.get(url = "http://example/login.php")
data = r.content
f = file("captchatest.png","wb")
f.write(data)
f.close()
# print change_to_string()
rr = s.post(url = "http://example/login.php" , data = {‘username‘:‘c014‘,‘password‘:‘c014‘,‘captcha‘:change_to_string()})
print "---------------------"
print rr.content
|
标签：function keyword linu hang tle word key 替换 oca
原文地址：http://www.cnblogs.com/test404/p/6920363.html
