#!/usr/bin/env python3
import os
import sqlite3
import requests
import time
from requests.auth import HTTPBasicAuth
from requests.exceptions import RequestException
import logging

# Paperless 服务器信息
PAPERLESS_URL = "http://localhost:8000/api"
#AUTH = HTTPBasicAuth("admin", "admin")  # Basic Auth 认证， mac上用这个
AUTH = HTTPBasicAuth("admin", "paperless")  # Basic Auth 认证，NAS上用这个

# 日志配置
logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")

# 连接到 SQLite 数据库
DB_PATH = "/usr/src/paperless/data/db.sqlite3"
conn = sqlite3.connect(DB_PATH)
cursor = conn.cursor()

# API 请求封装（带重试）,支持GET，POST等
def api_request(method, url, data=None, retries=5):
    for attempt in range(retries):
        try:
            response = requests.request(method, url, json=data, auth=AUTH, timeout=5)

            if response.status_code in [200, 201, 204]:
                return response.json() if response.text else True
            elif response.status_code == 404:
                logging.warning(f"API 资源未找到: {method} {url}")
                return None
            else:
                logging.error(f"API 请求失败: {method} {url}, 状态码: {response.status_code}, 响应: {response.text}")

        except RequestException as e:
            logging.error(f"API 请求异常: {method} {url}, 错误: {e}")

        if attempt < retries - 1:
            logging.warning(f"请求失败，等待 2 秒后重试 ({attempt+1}/{retries})...")
            time.sleep(2)

    logging.error(f"API 请求最终失败: {method} {url}")
    return None

# 从数据库中获取 page_count <= 6 的文档 id
def get_documents_to_delete():
    try:
        cursor.execute("SELECT id FROM documents_document WHERE page_count <= 6 and (deleted_at IS NULL OR deleted_at = '') ")
        rows = cursor.fetchall()
        return [row[0] for row in rows]
    except sqlite3.Error as e:
        logging.error(f"Error querying data: {e}")
        return []

# 删除文档
def delete_documents(doc_ids):
    succ_count = 0
    for doc_id in doc_ids:
        url = f"{PAPERLESS_URL}/documents/{doc_id}/"
        result = api_request("DELETE", url)
        if result:
            logging.info(f"✅ 文档 {doc_id} 删除成功")
            succ_count += 1
        else:
            logging.error(f"❌ 文档 {doc_id} 删除失败")
    logging.info(f"\ntotal count: {len(doc_ids)}, deleted: {succ_count}")

if __name__ == "__main__":
    doc_ids = get_documents_to_delete()
    if doc_ids:
        delete_documents(doc_ids)
    else:
        logging.info("没有需要删除的文档")

    # 关闭数据库连接
    conn.close()