python下调用pytesseract识别某网站验证码

一、pytesseract介绍

1、pytesseract说明

pytesseract最新版本0.1.6，网址：https://pypi.python.org/pypi/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.

翻译一下大意：

a、Python-tesseract是一个基于google's Tesseract-OCR的独立封装包；

b、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；

c、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；

2、pytesseract安装

INSTALLATION:

Prerequisites:
* Python-tesseract requires python 2.5 or later or python 3.
* You will need the Python Imaging Library (PIL). Under Debian/Ubuntu, this is
the package "python-imaging" or "python3-imaging" for python3.
* Install google tesseract-ocr from http://code.google.com/p/tesseract-ocr/ .
You must be able to invoke the tesseract command as "tesseract". If this
isn't the case, for example because tesseract isn't in your PATH, you will
have to change the "tesseract_cmd" variable at the top of 'tesseract.py'.
Under Debian/Ubuntu you can use the package "tesseract-ocr".

Installing via pip: 
See the [pytesseract package page](https://pypi.python.org/pypi/pytesseract) 
```
$> sudo pip install pytesseract 

 翻译一下：

a、Python-tesseract支持python2.5及更高版本；

b、Python-tesseract需要安装PIL（Python Imaging Library） ，来支持更多的图片格式；

c、Python-tesseract需要安装tesseract-ocr安装包，具体参看上一篇博文。

综上，Pytesseract原理：

1、上一篇博文中提到，执行命令行 tesseract.exe 1.png output -l eng ，可以识别1.png中文字，并把识别结果输出到output.txt中；

2、Pytesseract对上述过程进行了二次封装，自动调用tesseract.exe，并读取output.txt文件的内容，作为函数的返回值进行返回。

二、pytesseract使用

 USAGE:
```
> try:
> import Image
> except ImportError:
> from PIL import Image
> import pytesseract
> print(pytesseract.image_to_string(Image.open('test.png')))
> print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))

可以看到：

1、核心代码就是image_to_string函数，该函数还支持-l eng 参数，支持-psm 参数。

用法：
image_to_string(Image.open('test.png'),lang="eng" config="-psm 7")

2、pytesseract里调用了image，所以才需要PIL，其实tesseract.exe本身是支持jpeg、png等图片格式的。

实例代码，识别某公共网站的验证码(大家千万别干坏事啊，思虑再三，最后还是隐掉网站域名，大家去找别的网站试试吧……)：

#-*-coding=utf-8-*-
__author__='zhongtang'

import urllib
import urllib2
import cookielib
import math
import random
import time
import os
import htmltool
from pytesseract import *
from PIL import Image
from PIL import ImageEnhance
import re

class orclnypcg:
    def __init__(self):
        self.baseUrl='http://jbywcg.****.com.cn'
        self.ht=htmltool.htmltool()
        self.curPath=self.ht.getPyFileDir()
        self.authCode=''
        
    def initUrllib2(self):
        try:
            cookie = cookielib.CookieJar()
            cookieHandLer = urllib2.HTTPCookieProcessor(cookie)
            httpHandLer=urllib2.HTTPHandler(debuglevel=0)
            httpsHandLer=urllib2.HTTPSHandler(debuglevel=0)
        except:
            raise
        else:
             opener = urllib2.build_opener(cookieHandLer,httpHandLer,httpsHandLer)
             opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11')]
             urllib2.install_opener(opener)
             
    def urllib2Navigate(self,url,data={}):           #定义连接函数，有超时重连功能
        tryTimes = 0
        while True:
            if (tryTimes>20):
                print u"多次尝试仍无法链接网络，程序终止"
                break
            try:
                if (data=={}):
                    req = urllib2.Request(url)
                else:
                    req = urllib2.Request(url,urllib.urlencode(data))
                response =urllib2.urlopen(req)
                bodydata = response.read()
                headerdata = response.info()
                if headerdata.get('Content-Encoding')=='gzip':
                    rdata = StringIO.StringIO(bodydata)
                    gz = gzip.GzipFile(fileobj=rdata)
                    bodydata = gz.read()
                    gz.close()
                tryTimes = tryTimes +1
            except urllib2.HTTPError, e:
              print 'HTTPError[%s]
' %e.code                
            except urllib2.URLError, e:
              print 'URLError[%s]
' %e.reason    
            except socket.error:
                print u"连接失败，尝试重新连接"
            else:
                break
        return bodydata,headerdata
    
    def randomCodeOcr(self,filename):
        image = Image.open(filename)
        #使用ImageEnhance可以增强图片的识别率
        #enhancer = ImageEnhance.Contrast(image)
        #enhancer = enhancer.enhance(4)
        image = image.convert('L')
        ltext = ''
        ltext= image_to_string(image)
        #去掉非法字符，只保留字母数字
        ltext=re.sub("W", "", ltext)
        print u'[%s]识别到验证码:[%s]!!!' %(filename,ltext)
        image.save(filename)
        #print ltext
        return ltext

    def getRandomCode(self):
        #开始获取验证码
        #http://jbywcg.****.com.cn/CommonPage/Code.aspx?0.9409255818463862
        i = 0 
        while ( i<=100):
            i += 1 
            #拼接验证码Url
            randomUrlNew='%s/CommonPage/Code.aspx?%s' %(self.baseUrl,random.random())
            #拼接验证码本地文件名
            filename= '%s.png' %(i)
            filename=  os.path.join(self.curPath,filename)
            jpgdata,jpgheader = self.urllib2Navigate(randomUrlNew)
            if len(jpgdata)<= 0 :
                print u'获取验证码出错！
'
                return False
            f = open(filename, 'wb')
            f.write(jpgdata)
            #print u"保存图片:",fileName
            f.close()
            self.authCode = self.randomCodeOcr(filename)


#主程序开始
orcln=orclnypcg()
orcln.initUrllib2()
orcln.getRandomCode()

三、pytesseract代码优化

上述程序在windows平台运行时，会发现有黑色的控制台窗口一闪而过的画面，不太友好。

略微修改了pytesseract.py（C:Python27Libsite-packagespytesseract目录下），把上述过程进行了隐藏。

# modified by zhongtang hide console window
# new code
IS_WIN32 = 'win32' in str(sys.platform).lower()
if IS_WIN32:
   startupinfo = subprocess.STARTUPINFO()
   startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
   startupinfo.wShowWindow = subprocess.SW_HIDE
   proc = subprocess.Popen(command,
        stderr=subprocess.PIPE,startupinfo=startupinfo)
'''
# old code
proc = subprocess.Popen(command,
   stderr=subprocess.PIPE)
'''
# modified end

为了方便初学者，把pytesseract.py也贴出来，高手自行忽略。

#!/usr/bin/env python
'''
Python-tesseract is an optical character recognition (OCR) tool for python.
That is, it will recognize and "read" the text embedded in images.

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.


USAGE:
```
 > try:
 >     import Image
 > except ImportError:
 >     from PIL import Image
 > import pytesseract
 > print(pytesseract.image_to_string(Image.open('test.png')))
 > print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))
```

INSTALLATION:

Prerequisites:
* Python-tesseract requires python 2.5 or later or python 3.
* You will need the Python Imaging Library (PIL).  Under Debian/Ubuntu, this is
  the package "python-imaging" or "python3-imaging" for python3.
* Install google tesseract-ocr from http://code.google.com/p/tesseract-ocr/ .
  You must be able to invoke the tesseract command as "tesseract". If this
  isn't the case, for example because tesseract isn't in your PATH, you will
  have to change the "tesseract_cmd" variable at the top of 'tesseract.py'.
  Under Debian/Ubuntu you can use the package "tesseract-ocr".
  
Installing via pip:   
See the [pytesseract package page](https://pypi.python.org/pypi/pytesseract)     
$> sudo pip install pytesseract   

Installing from source:   
$> git clone git@github.com:madmaze/pytesseract.git   
$> sudo python setup.py install    


LICENSE:
Python-tesseract is released under the GPL v3.

CONTRIBUTERS:
- Originally written by [Samuel Hoffstaetter](https://github.com/hoffstaetter) 
- [Juarez Bochi](https://github.com/jbochi)
- [Matthias Lee](https://github.com/madmaze)
- [Lars Kistner](https://github.com/Sr4l)

'''

# CHANGE THIS IF TESSERACT IS NOT IN YOUR PATH, OR IS NAMED DIFFERENTLY
tesseract_cmd = 'tesseract'

try:
    import Image
except ImportError:
    from PIL import Image
import subprocess
import sys
import tempfile
import os
import shlex

__all__ = ['image_to_string']

def run_tesseract(input_filename, output_filename_base, lang=None, boxes=False, config=None):
    '''
    runs the command:
        `tesseract_cmd` `input_filename` `output_filename_base`
    
    returns the exit status of tesseract, as well as tesseract's stderr output

    '''
    command = [tesseract_cmd, input_filename, output_filename_base]
    
    if lang is not None:
        command += ['-l', lang]

    if boxes:
        command += ['batch.nochop', 'makebox']
        
    if config:
        command += shlex.split(config)
        
    # modified by zhongtang  hide console window
    # new code
    IS_WIN32 = 'win32' in str(sys.platform).lower()
    if IS_WIN32:
        startupinfo = subprocess.STARTUPINFO()
        startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
        startupinfo.wShowWindow = subprocess.SW_HIDE
    proc = subprocess.Popen(command,
            stderr=subprocess.PIPE,startupinfo=startupinfo)
    '''
    # old code
    proc = subprocess.Popen(command,
            stderr=subprocess.PIPE)
    '''
    # modified end
    
    return (proc.wait(), proc.stderr.read())

def cleanup(filename):
    ''' tries to remove the given filename. Ignores non-existent files '''
    try:
        os.remove(filename)
    except OSError:
        pass

def get_errors(error_string):
    '''
    returns all lines in the error_string that start with the string "error"

    '''

    lines = error_string.splitlines()
    error_lines = tuple(line for line in lines if line.find('Error') >= 0)
    if len(error_lines) > 0:
        return '
'.join(error_lines)
    else:
        return error_string.strip()

def tempnam():
    ''' returns a temporary file-name '''
    tmpfile = tempfile.NamedTemporaryFile(prefix="tess_")
    return tmpfile.name

class TesseractError(Exception):
    def __init__(self, status, message):
        self.status = status
        self.message = message
        self.args = (status, message)

def image_to_string(image, lang=None, boxes=False, config=None):
    '''
    Runs tesseract on the specified image. First, the image is written to disk,
    and then the tesseract command is run on the image. Resseract's result is
    read, and the temporary files are erased.
    
    also supports boxes and config.
    
    if boxes=True
        "batch.nochop makebox" gets added to the tesseract call
    if config is set, the config gets appended to the command.
        ex: config="-psm 6"

    '''

    if len(image.split()) == 4:
        # In case we have 4 channels, lets discard the Alpha.
        # Kind of a hack, should fix in the future some time.
        r, g, b, a = image.split()
        image = Image.merge("RGB", (r, g, b))
    
    input_file_name = '%s.bmp' % tempnam()
    output_file_name_base = tempnam()
    if not boxes:
        output_file_name = '%s.txt' % output_file_name_base
    else:
        output_file_name = '%s.box' % output_file_name_base
    try:
        image.save(input_file_name)
        status, error_string = run_tesseract(input_file_name,
                                             output_file_name_base,
                                             lang=lang,
                                             boxes=boxes,
                                             config=config)
        if status:
            #print 'test' , status,error_string
            errors = get_errors(error_string)
            raise TesseractError(status, errors)
        f = open(output_file_name)
        try:
            return f.read().strip()
        finally:
            f.close()
    finally:
        cleanup(input_file_name)
        cleanup(output_file_name)

def main():
    if len(sys.argv) == 2:
        filename = sys.argv[1]
        try:
            image = Image.open(filename)
            if len(image.split()) == 4:
                # In case we have 4 channels, lets discard the Alpha.
                # Kind of a hack, should fix in the future some time.
                r, g, b, a = image.split()
                image = Image.merge("RGB", (r, g, b))
        except IOError:
            sys.stderr.write('ERROR: Could not open file "%s"
' % filename)
            exit(1)
        print(image_to_string(image))
    elif len(sys.argv) == 4 and sys.argv[1] == '-l':
        lang = sys.argv[2]
        filename = sys.argv[3]
        try:
            image = Image.open(filename)
        except IOError:
            sys.stderr.write('ERROR: Could not open file "%s"
' % filename)
            exit(1)
        print(image_to_string(image, lang=lang))
    else:
        sys.stderr.write('Usage: python pytesseract.py [-l language] input_file
')
        exit(2)

if __name__ == '__main__':
    main()

以上……