OCR识别-讯飞接口

OCR识别-讯飞接口

我只是个搬运工，参考：https://zhuanlan.zhihu.com/p/402226006
也可以使用utools里面的截图ocr

# -*- coding: utf-8 -*-
import base64
import hashlib
import time
import keyboard as keyboard
import pyperclip
import requests
#获取剪切板内容
from PIL import ImageGrab

# OCR手写文字识别接口地址
URL = "http://webapi.xfyun.cn/v1/service/v1/ocr/handwriting"
# 应用APPID(必须为webapi类型应用,并开通手写文字识别服务,参考帖子如何创建一个webapi应用：http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=36481)
APPID = "xxx"
# 接口密钥(webapi类型应用开通手写文字识别后，控制台--我的应用---手写文字识别---相应服务的apikey)
API_KEY = "xxx"



def getHeader():
    curTime = str(int(time.time()))
    param = "{\"language\":\""+language+"\",\"location\":\""+location+"\"}"
    paramBase64 = base64.b64encode(param.encode('utf-8'))

    m2 = hashlib.md5()
    str1 = API_KEY + curTime + str(paramBase64, 'utf-8')
    m2.update(str1.encode('utf-8'))
    checkSum = m2.hexdigest()
    # 组装http请求头
    header = {
        'X-CurTime': curTime,
        'X-Param': paramBase64,
        'X-Appid': APPID,
        'X-CheckSum': checkSum,
        'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
    }
    return header

#图片转换为base编码
def getBody(filepath):
    with open(filepath, 'rb') as f:
        imgfile = f.read()
    data = {'image': str(base64.b64encode(imgfile), 'utf-8')}
    return data

#英文判断
def isEnglish(keyword):
    #return keyword.isalpha()  #判断纯单词 是否是英文
    return all(ord(c) < 128 for c in keyword)

# 写入到剪切板
def settext(aString):
    # importing the module
    # copies all the data the user has copied
    pyperclip.copy(aString)

    # paste the copied data from clipboard
    pyperclip.paste()

#保存剪切板数据图片
def get_pic():
    # 按ctrl+后才执行下面的语句
    #keyboard.wait(hotkey='ctrl+alt+a')
    # ctrl+c保存截图至剪切板， ImageGrab从剪切板读取图片
    img1 = ImageGrab.grabclipboard()
    #print(type(img1))
    # 文件保存的名字
    # img_path = str(int(time.time()))+"ocr_temp"+".png"
    img_path = "./ocr_temp" + ".png"
    img1.save(img_path)
    return img_path

# 语种设置
language = "cn|en"
# 是否返回文本位置信息
location = "true"
r = requests.post(URL, headers=getHeader(), data=getBody(get_pic()))
resp=r.json()
if resp['code'] != '0':
    print (resp['desc'])
# print(resp)
result=""#每一行的数据
content="" #每一行某个数据 某个文字/某个单词
for i in range(0,len(resp["data"]["block"][0]["line"])):
    for j in range(0,len(resp["data"]["block"][0]["line"][i]["word"])):
        content=resp["data"]["block"][0]["line"][i]["word"][j]["content"]
        if isEnglish(content):
            result+=content+" "  #英文单词 需要  空格
        else:
            result+=content
    result+="\n" #换行

#添加到剪切板
settext(result)
print(result)