pdf_title_image/miner_pdf/seal_test.py

import os
import base64
import requests
import json
import time

# img dir
image_dir = "/home/stf/miner_pdf/test_img"
# access token
access_token = "24.6bbe9987c6bd19ba65e4402917811657.2592000.1724573148.282335-86574608"
# request url
request_url = f"https://aip.baidubce.com/rest/2.0/ocr/v1/seal?access_token={access_token}"
# headers
headers = {'content-type': 'application/x-www-form-urlencoded'}
# seal save path
seal_save_path = "/home/stf/miner_pdf/seal.json"

data = {}

# 图片文件
for img_name in os.listdir(image_dir):
    img_path = os.path.join(image_dir, img_name)
    print(f'processing {img_path} ...')
    f = open(img_path, 'rb')
    img = base64.b64encode(f.read())
    params = {"image":img}
    #印章检测
    response = requests.post(request_url, data=params, headers=headers)
    if response:
        print(response.json())
        data[img_name] = response.json()

    time.sleep(3)

with open(seal_save_path, 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=4)