使用python，基于aksk，调用推理服务

如果输入数据是json字符串

请直接参考

https://support.huaweicloud.com/devg-apig/apig-dev-180307016.html

如果输入的数据是一张图片,下面的例子程序假设图片保存在image/rose1.jpg中

首先从下面链接下载apig sdk

https://obs.cn-north-1.myhuaweicloud.com/apig-sdk/ApiGateway-python-sdk.zip

解压后对于main.py进行如下修改

修改后的全量代码如下

# coding=utf-8
import requests
from apig_sdk import signer

if __name__ == '__main__':
    sig = signer.Signer()
    sig.Key = "<YOUR-AK>"
    sig.Secret = "<YOUR-SK>"
    data_type = 'images'
    input_img_path = 'image/rose1.jpg'
    predict_file = {data_type: open(input_img_path, 'rb')}
    predict_body, content_type = requests.models.RequestEncodingMixin._encode_files(predict_file, {})
    predict_file[data_type].close()
    r = signer.HttpRequest("POST",
                           "<YOUR-INFER-URL>",
                           {"x-stage": "RELEASE", 'content-type': content_type},
                           predict_body)
    sig.Sign(r)
    print(r.headers["X-Sdk-Date"])
    print(r.headers["Authorization"])
    resp = requests.request(r.method, r.scheme + "://" + r.host + r.uri, headers=r.headers, data=r.body, verify=False)
    print(resp.status_code, resp.reason)

    print(resp.content)

对于apig_sdk目录下面的signer.py进行如下修改

        if sys.version_info.major >= 3 and isinstance(body, str):
            self.body = body.encode("utf-8")
        else:
            self.body = body