match_spider/gys/aliyun.py

# -*- coding: utf-8 -*-
"""
Created on 2024-11-01 
---------
@summary:  
---------
@author: Dzr
"""

from base64 import b64encode

import requests


def file_extract(path):
    b64_str = b64encode(path.read_bytes()).decode('utf8')
    data = {"input": {"image": b64_str}}
    url = 'http://1228910937799386.cn-hangzhou.pai-eas.aliyuncs.com/api/predict/ms_eas_c38f0a8d_f314_463b_875d_581a/invoke'
    headers = {
        'Content-Type': 'application/json',
        'Authorization': 'ZDljNTk5ZTU3M2U3NzQzOGI5NzJhY2Y2OTI1M2I0NWI5NmVhZjljZA=='
    }
    # print(b64_str)
    # data = {"input":{"image":"http://modelscope.oss-cn-beijing.aliyuncs.com/demo/images/image_ocr_recognition.jpg"}}

    response = requests.post(url, headers=headers, json=data, timeout=10)
    r_json = response.json()
    print(r_json)
    return r_json['Data']['text'][0] if r_json and 'Data' in r_json else ''