pyhton验证码识别

1、PIL 下载地址： PIL-1.1.7.win-amd64-py2.7.exe

2、tesseract-ocr下载地址： tesseract-ocr-setup-3.02.02.exe

3、pytesseract安装直接使用pip install pytesseract安装即可，或者使用easy_install pytesseract

下载链接：http://pan.baidu.com/s/1hrVRHYG

#!/usr/bin/env python
# -*- coding: utf-8 -*-
 
 
'''
 
try:
    import pytesseract
    from PIL import Image
except ImportError:
    print '模块导入错误,请使用pip安装,pytesseract依赖以下库：'
    print 'http://www.lfd.uci.edu/~gohlke/pythonlibs/#pil'
    print 'http://code.google.com/p/tesseract-ocr/'
    raise SystemExit
  
image = Image.open('vcode.png')
vcode = pytesseract.image_to_string(image)
print vcode
'''
 
import pytesseract
from PIL import Image
import requests
 
def Vercode():
    url = "http://www.xxxx"
    header = {"user_agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
    r =requests.get(url,headers=header,timeout=5)
    with open('vcode.jpg','wb') as pic:
        pic.write(r.content)
    im = pytesseract.image_to_string(Image.open('vcode.jpg'))
    im = im.replace(' ', '')
    if im != '':
        return im
    else:
        return Vercode()
print Vcode()