Python 实现任意区域文字识别(OCR)操作

├── README.md
├── aip     //SDK目录
│ ├── __init__.py  //导出类
│ ├── base.py   //aip基类
│ ├── http.py   //http请求
│ └── ocr.py   //OCR
└── setup.py    //setuptools安装

import os # 操作系统相关
import sys # 系统相关
import time # 时间获取
import signal # 系统信号
import winsound # 提示音
from aip import AipOcr # 百度OCR API
from PIL import ImageGrab # 捕获剪切板中的图片
import win32clipboard as wc # WINDOWS 剪切板操作
import win32con # 这里用于获取 WINDOWS 剪贴板数据的标准格式

""" 你的 APPID AK SK """
APP_ID = 'xxx'
API_KEY = 'xxx'
SECRET_KEY = 'xxx'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

""" 读取图片 """
def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
  return fp.read()

""" 从API的返回字典中获取文字 """
def getOcrText(txt_dict):
 txt = ""
 if type(txt_dict) == dict:
 for i in txt_dict['words_result']:
 txt = txt + i["words"]
 if len(i["words"])  25: # 这里使用字符串长度决定了文本是否换行，读者可以根据自己的喜好控制回车符的输出，实现可控的文本显示形式
 txt = txt + "\n\n"
 return txt

""" 调用通用/高精度文字识别, 图片参数为本地图片 """
def BaiduOcr(imageName,Accurate=True):
 image = get_file_content(imageName)
 if Accurate:
 return getOcrText(client.basicGeneral(image))
 else:
 return getOcrText(client.basicAccurate(image))
 
""" 带参数调用通用文字识别, 图片参数为远程url图片 """
def BaiduOcrUrl(url): 
 return getOcrText(client.basicGeneralUrl(url))

""" 剪切板操作函数 """
def get_clipboard():
 wc.OpenClipboard()
 txt = wc.GetClipboardData(win32con.CF_UNICODETEXT)
 wc.CloseClipboard()
 return txt

def empty_clipboard():
 wc.OpenClipboard()
 wc.EmptyClipboard()
 wc.CloseClipboard()

def set_clipboard(txt):
 wc.OpenClipboard()
 wc.EmptyClipboard()
 wc.SetClipboardData(win32con.CF_UNICODETEXT, txt)
 wc.CloseClipboard()
 
""" 截图后,调用通用/高精度文字识别"""
def BaiduOcrScreenshots(Accurate=True,path="./",ifauto=False):
 if not os.path.exists(path):
 os.makedirs(path)
 image = ImageGrab.grabclipboard()
 if image != None:
 print("\rThe image has been obtained. Please wait a moment!",end=" ")
 filename = str(time.time_ns())
 image.save(path+filename+".png")
 if Accurate:
 txt = getOcrText(client.basicAccurate(get_file_content(path+filename+".png")))
 else: 
 txt = getOcrText(client.basicGeneral(get_file_content(path+filename+".png")))
 os.remove(path+filename+".png")
 # f = open(os.path.abspath(path)+"\\"+filename+".txt",'w')
 # f.write(txt)
 set_clipboard(txt)
 winsound.PlaySound('SystemAsterisk',winsound.SND_ASYNC)
 # os.startfile(os.path.abspath(path)+"\\"+filename+".txt")
 # empty_clipboard()
 return txt
 else :
 if not ifauto:
 print("Please get the screenshots by Shift+Win+S!  ",end="")
 return ""
 else:
 print("\rPlease get the screenshots by Shift+Win+S !  ",end="")

def sig_handler(signum, frame):
 sys.exit(0)
 
def removeTempFile(file = [".txt",".png"],path="./"):
 if not os.path.exists(path):
 os.makedirs(path)
 pathDir = os.listdir(path)
 for i in pathDir:
 for j in file:
 if j in i:
 os.remove(path+i)

def AutoOcrFile(path="./",filetype=[".png",".jpg",".bmp"]):
 if not os.path.exists(path):
 os.makedirs(path)
 pathDir = os.listdir(path)
 for i in pathDir:
 for j in filetype:
 if j in i:
 f = open(os.path.abspath(path)+"\\"+str(time.time_ns())+".txt",'w')
 f.write(BaiduOcr(path+i))
 break

def AutoOcrScreenshots():
 signal.signal(signal.SIGINT, sig_handler)
 signal.signal(signal.SIGTERM, sig_handler)
 print("Waiting For Ctrl+C to exit ater removing all picture files and txt files!")
 print("Please get the screenshots by Shift+Win+S !",end="")
 while(1):
 try:
 BaiduOcrScreenshots(ifauto=True)
 time.sleep(0.1)
 except SystemExit:
 removeTempFile()
 break
 else :
 pass
 finally:
 pass

if __name__ == '__main__':
 AutoOcrScreenshots()

brew install tesseract

pip install pytesseract

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import pytesseract
from PIL import Image

# open image
image = Image.open('test.png')
code = pytesseract.image_to_string(image, lang='chi_sim')
print(code)