BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/test/testocr.py

# coding=utf-8

import sys
import json
import requests
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 = 'ssfyC49bEbp7QdGnG96GKdt2'

SECRET_KEY = 'YCQtiQVt1GvldNZzyfOpbVtNugj7S1Uw'


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()



def ocr():
    '''
    通用文字识别（高精度版）
    '''

    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"
    # 二进制方式打开图片文件
    f = open('20201111181124.png', 'rb')
    img = base64.b64encode(f.read())

    params = {"image":img}
    access_token = '24.f7a57ed7b887ac523c606fa6b09dac88.2592000.1607681571.282335-22744183'
    request_url = request_url + "?access_token=" + access_token
    headers = {'content-type': 'application/x-www-form-urlencoded'}
    response = requests.post(request_url, data=params, headers=headers)
    if response:
        print (response.json())

if __name__=="__main__":
    # print(fetch_token())
    ocr()