arbitration_system_V20/application_extractor/demo/PP-StructureV3/PP-StructureV3_1.0.py

import os
import re
import base64
import requests
import config


API_URL = "https://q2z8becfm967o4y7.aistudio-app.com/layout-parsing"
TOKEN = "16455708d55afac2f074f4ae5a88fc6c7bae7920"

file_path = "E:\\project\\arbitration_system\\appplication_extractor\\test\\刘正新\\刘正新-申请书.png"
input_filename = os.path.splitext(os.path.basename(file_path))[0]

with open(file_path, "rb") as file:
    file_bytes = file.read()
    file_data = base64.b64encode(file_bytes).decode("ascii")

headers = {
    "Authorization": f"token {TOKEN}",
    "Content-Type": "application/json"
}

required_payload = {
    "file": file_data,
    "fileType": 1,
}

optional_payload = {
    "useDocOrientationClassify": False,
    "useDocUnwarping": False,
    "useTextlineOrientation": False,
}

payload = {**required_payload, **optional_payload}

response = requests.post(API_URL, json=payload, headers=headers)

assert response.status_code == 200
result = response.json()["result"]

os.makedirs("../PP-OCRv5/output", exist_ok=True)

# 如果需要处理多个页面
for i, res in enumerate(result.get("ocrResults", [])):
    if "prunedResult" in res:
        pruned_result = res["prunedResult"]
        if "rec_texts" in pruned_result:
            print(f"\n=== 页面 {i + 1} 的识别文本 ===")
            result_text = ""
            for j, text in enumerate(pruned_result["rec_texts"]):
                result_text = result_text+"\n"+text
            print(result_text)