test_script/HR_OCR/tools/convert_json.py

from pathlib import Path

import requests
import json
import base64
from itertools import chain

url = 'http://aihubpre-idc.digitalyili.com/aiSquare/openApi/reasoning-services/hrocr'
imgs_path = '/Users/zeke/Downloads/户口本测试样本1011-常住人口页'


def send_request(img_path):
    with open(img_path, 'rb') as f:
        img_str: str = base64.encodebytes(f.read()).decode('utf-8')
        data = {
            'image': img_str
        }
        idc_header = {
            'Content-Type': 'application/json',
            'Authorization': 'Bearer 4e00c444-620b-4d3c-85f4-777e64276f0e'
        }
        r = requests.post(f'{url}/hkbsbtest/regbook', json=data, headers=idc_header)
        # r = requests.post(f'{url}/hkbsbtest/regbook', json=data)
        print(r.json())
        return r.json()


def _parse_result(r):
    if r['status'] == '000':
        r = r['result']
        if r:
            del r['confidence']
        return {k: v['text'] if isinstance(v, dict) else v for k, v in r.items()}
    elif r['status'] == '101':
        return "101"


if __name__ == '__main__':

    # 0
    # img_paths = chain(*[Path(root / imgs_path).rglob(f'*.{ext}') for ext in ['jpeg', 'jpg', 'png', 'JPG', 'PNG']])
    img_paths = chain(*[Path(imgs_path).rglob(f'*.{ext}') for ext in ['jpg']])
    for img_path in img_paths:
        print(img_path)
        r = send_request(img_path)
        res = _parse_result(r)
        print(res)
        img_path: Path = img_path
        d = img_path.parent
        fn = f'{img_path.stem}.json'

        with (d / fn).open('w', encoding='utf-8') as f:
            json.dump(res, f, ensure_ascii=False, indent=4)