文章目录

• 法一： 使用easyocr模块
• 法二：通过pytesseract调用tesseract
• 法三：调用百度API
• • 方式一： 通过urllib直接调用，替换自己的api_key和secret_key即可
  • 方式二：通过HTTP-SDK模块进行调用

法一： 使用easyocr模块

easyocr是基于torch的深度学习模块
easyocr安装后调用过程中出现opencv版本不兼容问题，所以放弃此方案。

法二：通过pytesseract调用tesseract

优点：部署快，轻量级，离线可用，免费
缺点：自带的中文库识别率较低，需要自己建数据进行训练

法三：调用百度API

优点：使用方便，功能强大
缺点：大量使用需要收费
我自己采用的是调用百度API的方式，下面是我的步骤：
注册百度账号，创建OCR应用可以参考其他教程。
购买后使用python调用方法

方式一： 通过urllib直接调用，替换自己的api_key和secret_key即可

# coding=utf-8

import sys
import json
import base64


# 保证兼容python2以及python3
IS_PY3 = sys.version_info.major == 3
if IS_PY3:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.error import URLError
    from urllib.parse import urlencode
    from urllib.parse import quote_plus
else:
    import urllib2
    from urllib import quote_plus
    from urllib2 import urlopen
    from urllib2 import Request
    from urllib2 import URLError
    from urllib import urlencode

# 防止https证书校验不正确
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

API_KEY = 'YsZKG1wha34PlDOPYaIrIIKO'

SECRET_KEY = 'HPRZtdOHrdnnETVsZM2Nx7vbDkMfxrkD'


OCR_URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"


"""  TOKEN start """
TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'


"""
    获取token
"""
def fetch_token():
    params = {'grant_type': 'client_credentials',
              'client_id': API_KEY,
              'client_secret': SECRET_KEY}
    post_data = urlencode(params)
    if (IS_PY3):
        post_data = post_data.encode('utf-8')
    req = Request(TOKEN_URL, post_data)
    try:
        f = urlopen(req, timeout=5)
        result_str = f.read()
    except URLError as err:
        print(err)
    if (IS_PY3):
        result_str = result_str.decode()


    result = json.loads(result_str)

    if ('access_token' in result.keys() and 'scope' in result.keys()):
        if not 'brain_all_scope' in result['scope'].split(' '):
            print ('please ensure has check the  ability')
            exit()
        return result['access_token']
    else:
        print ('please overwrite the correct API_KEY and SECRET_KEY')
        exit()

"""
    读取文件
"""
def read_file(image_path):
    f = None
    try:
        f = open(image_path, 'rb')
        return f.read()
    except:
        print('read image file fail')
        return None
    finally:
        if f:
            f.close()


"""
    调用远程服务
"""
def request(url, data):
    req = Request(url, data.encode('utf-8'))
    has_error = False
    try:
        f = urlopen(req)
        result_str = f.read()
        if (IS_PY3):
            result_str = result_str.decode()
        return result_str
    except  URLError as err:
        print(err)

if __name__ == '__main__':

    # 获取access token
    token = fetch_token()

    # 拼接通用文字识别高精度url
    image_url = OCR_URL + "?access_token=" + token

    text = ""

    # 读取测试图片
    file_content = read_file('test.jpg')

    # 调用文字识别服务
    result = request(image_url, urlencode({'image': base64.b64encode(file_content)}))

    # 解析返回结果
    result_json = json.loads(result)
    print(result_json)
    for words_result in result_json["words_result"]:
        text = text + words_result["words"]

    # 打印文字
    print(text)

方式二：通过HTTP-SDK模块进行调用

from aip import AipOcr
APP_ID = '25**9878'
API_KEY = 'VGT8y***EBf2O8xNRxyHrPNr'
SECRET_KEY = 'ckDyzG*****N3t0MTgvyYaKUnSl6fSw'

client = AipOcr(APP_ID,API_KEY,SECRET_KEY)


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

image = get_file_content('test.jpg')
res = client.basicGeneral(image)
print(res)
#res = client.basicAccurate(image)
#print(res)

直接识别屏幕指定区域上的文字

from aip import AipOcr
APP_ID = '25**9878'
API_KEY = 'VGT8y***EBf2O8xNRxyHrPNr'
SECRET_KEY = 'ckDyzG*****N3t0MTgvyYaKUnSl6fSw'

client = AipOcr(APP_ID,API_KEY,SECRET_KEY)

from io import BytesIO
from PIL import ImageGrab
out_buffer = BytesIO()
img = ImageGrab.grab((100,200,300,400))
img.save(out_buffer,format='PNG')
res = client.basicGeneral(out_buffer.getvalue())
print(res)

标签：识别,python,token,API,result,KEY,print,import,OCR
来源： https://blog.csdn.net/qq_41082953/article/details/123228367