工作图像识别

配置环境

pip install baidu-aip
pip install pytesseract

from PIL import Image
import pytesseract
from aip import AipOcr
import pandas as pd
import os

代码

# -*- coding: utf-8 -*-
"""
Created on Sun May  3 12:44:16 2020

@author: 62669
"""
####################################################1简单识别
####################################################2借助百度
from PIL import Image
import pytesseract
from aip import AipOcr
import pandas as pd
import os

APP_ID = '19708344'
API_KEY = '7tRkWyg7YbFwP9u4qOCt41DF'
SECRET_KEY = 'EOBl6LZRprr6ydft7LflTLwfaRQWomnq'
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

#第一步创建流
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()
#第二步，读图片并且给字符串
def image2text(fileName):
    image = get_file_content(fileName)
    dic_result = client.basicGeneral(image)
    res = dic_result['words_result']
    result = ''
    for m in res:
        result = result + str(m['words'])
    return result
 
#result = image2text(r'F:\a_houdashi_work\bbb_python学习\其他\图片转文字\圈外总结\结构化61.jpg')

#print(result)
#第三步，合并字符串并且导出到txt


folder_path='D:/hzl/图片转文字/规则集输入'
savefile_path='D:/hzl/图片转文字/规则集输入'
savefile_name='a.csv'

os.chdir(folder_path)
file_list=os.listdir()
file_list.sort(reverse = True)
file_list


filestart=0
fileend=len(file_list)
end = ''
for i in range(filestart,fileend):
    name = folder_path +'/'+file_list[i]
    print(name)
    result = image2text(name)
    end = '\n'+ name + '\n' + result + end  +'\n' 
print(end)

with open(r"D:\hzl\图片转文字\a.txt", "w", encoding='utf-8') as f:
    f.write(str(end))
    f.close()