[开箱即用] Python 使用 百度 OCR 试图

简介

首先先去 百度AI 的云平台注册一个账户，获取APP_ID、API_KEY、SECRET_KEY 填入代码中即可使用。

代码

# -*- coding:utf-8 -*-
import cv2
from aip import AipOcr

import tap

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

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)


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


# 分析file图片
def analysis_screenshot(fname='screenshot.png'):
    image = get_file_content(fname)
    try:
        results = client.general(image)["words_result"]
        return results
    except BaseException as e:
        print(e)
        return []


# 分析坐标
def analysis_screenshot_base(fname='screenshot.png'):
    image = get_file_content(fname)
    try:
        results = client.basicGeneral(image)["words_result"]
        return results
        # 只回复纯文字
    except BaseException as e:
        print(e)
        return []


# 调试用
def dev():
    fname = 'screenshot.png'
    image = get_file_content(fname)

    """ 调用通用文字识别, 图片参数为本地图片 """
    # 还可以使用身份证驾驶证模板，直接得到字典对应所需字段
    results = client.general(image)["words_result"]
    print(results)
    img = cv2.imread(fname)
    for result in results:
        text = result["words"]
        location = result['location']
        print(location)
        print(text)
        # 画矩形框
        cv2.rectangle(img, (location["left"], location["top"]),
                      (location["left"] + location["width"], location["top"] + location["height"]), (0, 255, 0), 2)

    cv2.imwrite("bd_api.jpg", img)


if __name__ == '__main__':
    print(analysis_screenshot_base('pic.jpg'))

更多资料

百度OCR文档：https://ai.baidu.com/ai-doc/OCR/9kibizye4