tesserocr与pytesseract模块的使用方法解析

#从文件识别图像字符In [7]: tesserocr.file_to_text('image.png')Out[7]: 'Python3WebSpider/n/n'#查看tesseract已安装的语言包In [8]: tesserocr.get_languages()Out[8]: ('/usr/share/tesseract/tessdata/', ['eng'])#从图片数据识别图像字符In [9]: tesserocr.image_to_text(im)Out[9]: 'Python3WebSpider/n/n'#查看版本信息In [10]: tesserocr.tesseract_version()Out[10]: 'tesseract 3.04.00/n leptonica-1.72/n libgif 4.1.6(?) : libjpeg 6b (libjpeg-turbo 1.2.90) : libpng 1.5.13 : libtiff 4.0.3 : zlib 1.2.7 : libwebp 0.3.0/n'

from PIL import Imageimport pytesseract#如果PATH中没有tesseract可执行文件，请指定tesseract路径pytesseract.pytesseract.tesseract_cmd='C:/Program Files (x86)/Tesseract-OCR//tesseract.exe'#打印识别的图像的字符串print(pytesseract.image_to_string(Image.open('test.png')))#指定语言识别图像字符串,eng为英语print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='eng'))#获取图像边界框print(pytesseract.image_to_boxes(Image.open('test.png')))#获取包含边界框，置信度，行和页码的详细数据print(pytesseract.image_to_data(Image.open('test.png')))#获取方向和脚本检测print(pytesseract.image_to_osd(Image.open('test.png'))

from PIL import Imageimport pytesseractim = Image.open('66.png')#二值化图像传入图像和阈值def erzhihua(image,threshold):  ''':type image:Image.Image'''  image=image.convert('L')  table=[]  for i in range(256):    if i < threshold:      table.append(0)    else:      table.append(1)  return image.point(table,'1')image=erzhihua(im,127)image.show()result=pytesseract.image_to_string(image,lang='eng')print(result)

#!/usr/bin/env python# -*- coding: utf-8 -*-# @Time  : 2018/7/13 8:58# @Author : Py.qi# @File  : login.py# @Software: PyCharmfrom selenium import webdriverfrom selenium.common.exceptions import TimeoutException,WebDriverExceptionfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.common.keys import Keysfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.remote.webelement import WebElementfrom io import BytesIOfrom PIL import Imageimport pytesseractimport timeuser='zhang'password='123'url='http://10.0.0.200'driver=webdriver.Chrome()wait=WebDriverWait(driver,10)#识别验证码def acker(content):  im_erzhihua=erzhihua(content,127)  result=pytesseract.image_to_string(im_erzhihua,lang='eng')  return result#验证码二值化def erzhihua(image,threshold):  ''':type image:Image.Image'''  image=image.convert('L')  table=[]  for i in range(256):    if i < threshold:      table.append(0)    else:      table.append(1)  return image.point(table,'1')#自动登陆def login():  try:    driver.get(url)    #获取用户输入框    input=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#loginname'))) #type:WebElement    input.clear()    #发送用户名    input.send_keys(user)    #获取密码框    inpass=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#password'))) #type:WebElement    inpass.clear()    #发送密码    inpass.send_keys(password)    #获取验证输入框    yanzheng=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#code'))) #type:WebElement    #获取验证码在画布中的位置    codeimg=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#codeImg'))) #type:WebElement    image_location = codeimg.location    #截取页面图像并截取掩码码区域图像    image=driver.get_screenshot_as_png()    im=Image.open(BytesIO(image))    imag_code=im.crop((image_location['x'],image_location['y'],488,473))    #输入验证码并登陆    yanzheng.clear()    yanzheng.send_keys(acker(imag_code))    time.sleep(2)    yanzheng.send_keys(Keys.ENTER)  except TimeoutException as e:    print('timeout:',e)  except WebDriverException as e:    print('webdriver error:',e)if __name__ == '__main__':  login()