一区二区三区在线-一区二区三区亚洲视频-一区二区三区亚洲-一区二区三区午夜-一区二区三区四区在线视频-一区二区三区四区在线免费观看

腳本之家，腳本語言編程技術及教程分享平臺！
分類導航

Python|VBS|Ruby|Lua|perl|VBA|Golang|PowerShell|Erlang|autoit|Dos|bat|

服務器之家 - 腳本之家 - Python - python下調用pytesseract識別某網站驗證碼的實現方法

python下調用pytesseract識別某網站驗證碼的實現方法

2020-08-25 09:52腳本之家 Python

下面小編就為大家帶來一篇python下調用pytesseract識別某網站驗證碼的實現方法。小編覺得挺不錯的，現在就分享給大家，也給大家做個參考。一起跟隨小編過來看看吧

一、pytesseract介紹

1、pytesseract說明

pytesseract最新版本0.1.6，網址：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.

翻譯一下大意：

a、Python-tesseract是一個基于google's Tesseract-OCR的獨立封裝包；

b、Python-tesseract功能是識別圖片文件中文字，并作為返回參數返回識別結果；

c、Python-tesseract默認支持tiff、bmp格式圖片，只有在安裝PIL之后，才能支持jpeg、gif、png等其他圖片格式；

2、pytesseract安裝

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

翻譯一下：

a、Python-tesseract支持python2.5及更高版本；

b、Python-tesseract需要安裝PIL（Python Imaging Library） ，來支持更多的圖片格式；

c、Python-tesseract需要安裝tesseract-ocr安裝包。

綜上，Pytesseract原理：

1、上一篇博文中提到，執行命令行 tesseract.exe 1.png output -l eng ，可以識別1.png中文字，并把識別結果輸出到output.txt中；

2、Pytesseract對上述過程進行了二次封裝，自動調用tesseract.exe，并讀取output.txt文件的內容，作為函數的返回值進行返回。

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、核心代碼就是image_to_string函數，該函數還支持-l eng 參數，支持-psm 參數。

用法：

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

2、pytesseract里調用了image，所以才需要PIL，其實tesseract.exe本身是支持jpeg、png等圖片格式的。

實例代碼，識別某公共網站的驗證碼(大家千萬別干壞事啊，思慮再三，最后還是隱掉網站域名，大家去找別的網站試試吧……)：

?
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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
#-*-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={}):      #定義連接函數，有超時重連功能
    tryTimes = 0
    while True:
      if (tryTimes>20):
        print u"多次嘗試仍無法鏈接網絡，程序終止"
        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]\n' %e.code       
      except urllib2.URLError, e:
       print 'URLError[%s]\n' %e.reason 
      except socket.error:
        print u"連接失敗，嘗試重新連接"
      else:
        break
    return bodydata,headerdata
  
  def randomCodeOcr(self,filename):
    image = Image.open(filename)
    #使用ImageEnhance可以增強圖片的識別率
    #enhancer = ImageEnhance.Contrast(image)
    #enhancer = enhancer.enhance(4)
    image = image.convert('L')
    ltext = ''
    ltext= image_to_string(image)
    #去掉非法字符，只保留字母數字
    ltext=re.sub("\W", "", ltext)
    print u'[%s]識別到驗證碼:[%s]!!!' %(filename,ltext)
    image.save(filename)
    #print ltext
    return ltext
 
  def getRandomCode(self):
    #開始獲取驗證碼
    #http://jbywcg.****.com.cn/CommonPage/Code.aspx?0.9409255818463862
    i = 0
    while ( i<=100):
      i += 1
      #拼接驗證碼Url
      randomUrlNew='%s/CommonPage/Code.aspx?%s' %(self.baseUrl,random.random())
      #拼接驗證碼本地文件名
      filename= '%s.png' %(i)
      filename= os.path.join(self.curPath,filename)
      jpgdata,jpgheader = self.urllib2Navigate(randomUrlNew)
      if len(jpgdata)<= 0 :
        print u'獲取驗證碼出錯！\n'
        return False
      f = open(filename, 'wb')
      f.write(jpgdata)
      #print u"保存圖片:",fileName
      f.close()
      self.authCode = self.randomCodeOcr(filename)
 
 
#主程序開始
orcln=orclnypcg()
orcln.initUrllib2()
orcln.getRandomCode()

三、pytesseract代碼優化

上述程序在windows平臺運行時，會發現有黑色的控制臺窗口一閃而過的畫面，不太友好。

略微修改了pytesseract.py（C:\Python27\Lib\site-packages\pytesseract目錄下），把上述過程進行了隱藏。

# 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

為了方便初學者，把pytesseract.py也貼出來，高手自行忽略。

?
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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
#!/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 [email protected]: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 '\n'.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"\n' % 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"\n' % filename)
      exit(1)
    print(image_to_string(image, lang=lang))
  else:
    sys.stderr.write('Usage: python pytesseract.py [-l language] input_file\n')
    exit(2)
 
if __name__ == '__main__':
  main()

以上……

以上這篇python下調用pytesseract識別某網站驗證碼的實現方法就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持服務器之家。

延伸 · 閱讀

精彩推薦
主站蜘蛛池模板： yy6080久久国产伦理 | 国产趴着打光屁股sp抽打 | 四虎精品永久在线网址 | 久久综久久美利坚合众国 | 色婷丁香 | 被强迫调教的高辣小说 | 精品午夜中文字幕熟女人妻在线 | 国产成人精品一区二区 | 国产精品原创巨作无遮挡 | 亚欧国产| 久久精品中文闷骚内射 | 久久成人精品免费播放 | 国产偷窥女洗浴在线观看亚洲 | 海派甜心完整版在线观看 | 男人狂躁女人gif动态图 | 日本又大又硬又粗的视频 | 全彩孕交漫画福利啪啪吧 | 波多野结衣亚洲一区 | 2020年新四虎免费 | 小小水蜜桃视频高清在线观看免费 | 四虎国产精品免费久久麻豆 | 亚洲七七久久综合桃花 | 免费特黄一区二区三区视频一 | 免费黄色片网站 | 91精品国产麻豆国产自产在线 | 亚洲日本视频在线 | 精品乱lun小说 | 8x8x极品国产在线 | 骚虎最新网址 | ova巨公主催眠1在线观看 | 午夜影院免费体验 | 无限国产资源 | 日韩一区视频在线 | 日韩理论在线观看 | 欧美第十页 | 嗯啊在线观看免费影院 | 成人网久久 | sss亚洲国产欧美一区二区 | 国产精品香蕉 | 操大姨子逼 | 15一16japanese破|