404 lines
18 KiB
Python
404 lines
18 KiB
Python
|
|
from pathlib import Path
|
|
import astrbot.core.message.components as Comp
|
|
import datetime
|
|
import json
|
|
from astrbot.api.event import filter, AstrMessageEvent,MessageChain
|
|
from astrbot.api.star import Context, Star, register, StarTools
|
|
from astrbot.api import logger, AstrBotConfig
|
|
from astrbot.api.message_components import Node, Plain,Video,Image,Nodes,File
|
|
from astrbot.core.utils.session_waiter import (
|
|
session_waiter,
|
|
SessionController,
|
|
)
|
|
from typing import List
|
|
import imaplib
|
|
# 导入email库用于解析邮件内容
|
|
import email
|
|
# 导入os库用于文件和目录操作
|
|
import os
|
|
# 从datetime导入datetime用于日期时间处理
|
|
from datetime import datetime
|
|
# 导入email.utils用于邮件日期解析
|
|
import email.utils
|
|
# 导入email.header用于解码邮件头
|
|
import email.header
|
|
from lxml import html
|
|
import re
|
|
import zipfile
|
|
from pyzipper import AESZipFile
|
|
import pandas as pd
|
|
import requests
|
|
from urllib.parse import urlparse
|
|
import numpy as np
|
|
import sqlite3
|
|
@register("astrbot_bdzxb_bill", "bd_bill", "账单统计", "1.0.0")
|
|
class MyPlugin(Star):
|
|
def __init__(self, context: Context, config: AstrBotConfig):
|
|
super().__init__(context)
|
|
self.ceshi = None
|
|
self.email_usr = None
|
|
self.emcil_paswd = None
|
|
self.emcil_imap = None
|
|
self.message_target = None
|
|
self.no_file = None
|
|
self.emcil_white = None
|
|
self.file_path = "data/plugins/astrbot_bdzxb_bill"
|
|
self.config = config
|
|
self.chatid = None
|
|
self.data_path = None
|
|
self.sqllitaa = None
|
|
async def initialize(self):
|
|
"""可选择实现异步的插件初始化方法，当实例化该插件类之后会自动调用该方法。"""
|
|
# 读取配置信息
|
|
self.email_usr = self.config.email_usr
|
|
self.emcil_paswd = self.config.emcil_paswd
|
|
self.emcil_imap = self.config.emcil_imap
|
|
self.emcil_white = self.config.emcil_white
|
|
self.no_file = self.config.no_file
|
|
self.data_path = StarTools.get_data_dir("astrbot_bdzxb_bill")
|
|
file_list = os.listdir(f"{self.data_path}")
|
|
|
|
if "zhangdan.db" not in file_list:
|
|
self.sqllitaa = sqlite3.connect(f"{self.data_path}/zhangdan.db")
|
|
# 创建游标对象
|
|
cursor = self.sqllitaa.cursor()
|
|
# 创建表
|
|
# id:流水号,payid:账单号,paytype:交易类型,paydate:交易时间,payname:交易名称,payto:收入/支出,paysize:交易金额
|
|
# paystu:交易状态,paybox:收支方式,payqd:记录渠道
|
|
try:
|
|
cursor.execute(
|
|
'''
|
|
create table if not exists zhangdan(
|
|
id int primary key ,
|
|
payid text not null,
|
|
paytype text not null,
|
|
paydate text not null,
|
|
payname text not null,
|
|
payto text not null,
|
|
paysize text not null,
|
|
paystu text not null,
|
|
paybox text not null,
|
|
payqd text not null
|
|
|
|
)
|
|
'''
|
|
)
|
|
self.sqllitaa.commit()
|
|
cursor.close()
|
|
self.sqllitaa.close()
|
|
except Exception as e:
|
|
logger.info(f"{e}")
|
|
self.sqllitaa.commit()
|
|
cursor.close()
|
|
self.sqllitaa.close()
|
|
else:
|
|
self.sqllitaa = sqlite3.connect(f"{self.data_path}/zhangdan.db")
|
|
# 登录邮箱 下载文件
|
|
def emaillog(self):
|
|
logger.info(f" 开始执行 登录邮箱 {self.email_usr} 命令 ")
|
|
# 邮箱登录用户名
|
|
email_user = self.email_usr
|
|
# 邮箱授权码(非登录密码)，用于IMAP协议认证
|
|
email_password = self.emcil_paswd
|
|
# IMAP服务器地址，Foxmail使用QQ邮箱的IMAP服务器
|
|
imap_server = self.emcil_imap
|
|
mail = imaplib.IMAP4_SSL(imap_server)
|
|
# 使用用户名和授权码登录邮箱
|
|
# try:
|
|
mail.login(email_user, email_password)
|
|
# 查询收件箱 只读模式
|
|
mail.select("inbox",readonly=True)
|
|
# 设定查询条件
|
|
for emlname in self.emcil_white:
|
|
from_clause = " OR ".join([f'FROM "{sender}"' for sender in emlname])
|
|
# 获取今天的日期，格式化为IMAP要求的格式(如"21-Jul-2025")
|
|
today = datetime.now().strftime("%d-%b-%Y")
|
|
search_criteria = f'({from_clause} SINCE "{today.encode('utf-8')}" HAS attachment)'
|
|
logger.info(f"严格模式: 只处理今天({today})收到的邮件")
|
|
logger.info(f"发件人白名单: {self.emcil_white}")
|
|
logger.info(f"搜索条件: {search_criteria}")
|
|
|
|
# 执行IMAP搜索命令
|
|
status, messages = mail.search(None, search_criteria)
|
|
if status != "OK": # 检查搜索是否成功
|
|
raise Exception("邮件搜索失败")
|
|
|
|
# 获取邮件ID列表并只取最后20个（最新的20封）
|
|
mail_ids = messages[0].split()[-20:]
|
|
logger.info(f"获取到邮件数量: {len(messages)}")
|
|
filenames = ""
|
|
for mail_id in reversed(mail_ids):
|
|
# 获取邮件完整内容(RFC822格式)
|
|
status, msg_data = mail.fetch(mail_id, "(RFC822)")
|
|
if status != "OK": # 如果获取失败则跳过
|
|
continue
|
|
# 解析邮件内容为Message对象
|
|
email_message = email.message_from_bytes(msg_data[0][1])
|
|
# 验证发件人是否在白名单中
|
|
# ========================
|
|
from_header = email.utils.parseaddr(email_message['From'])[1] # 解析发件人邮箱
|
|
logger.info(f"邮件发件人: {from_header}")
|
|
if from_header not in self.emcil_white: # 严格检查白名单
|
|
logger.info(f"跳过非白名单发件人: {from_header}")
|
|
continue
|
|
|
|
# 遍历邮件各部分
|
|
# =============
|
|
for part in email_message.walk(): # 递归遍历邮件所有部分
|
|
if part.get_content_maintype() == "multipart": # 跳过multipart容器部分
|
|
continue
|
|
|
|
# 检查是否为.zip附件
|
|
# ==================
|
|
filename = part.get_filename() # 获取附件文件名
|
|
# 获取正文
|
|
maildata = part.get_payload(decode=True)
|
|
# 微信导出文件需要点击链接下载 检测正文中是否包含链接
|
|
etree = html.etree
|
|
tree = etree.HTML(maildata)
|
|
# logger.info(f"邮件正文{maildata}")
|
|
a_tags = tree.xpath('//a')
|
|
mail_date = email.utils.parsedate_to_datetime(email_message['Date']) if email_message['Date'] else None
|
|
mail_date = re.sub(r"[^\u4e00-\u9fa5a-zA-Z0-9]", "", str(mail_date))
|
|
for a_tag in a_tags:
|
|
# 获取到url后下载url
|
|
urlt = a_tag.get("href")
|
|
if urlt:
|
|
try:
|
|
filenames += self.download_file(urlt=urlt,filenamett=f"{from_header}{mail_date}")
|
|
except Exception as e:
|
|
logger.debug(f"URl 文件下载失败：{e}")
|
|
content_type = part.get_content_type() # 获取内容类型
|
|
# 判断条件：
|
|
# 1. 文件名以.zip结尾，或
|
|
# 2. 内容类型是Excel文件
|
|
# if (filename and filename.lower().endswith(".zip")) or \
|
|
# (content_type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"):
|
|
|
|
|
|
|
|
# 处理无文件名的情况
|
|
# ================
|
|
if not filename: # 如果附件没有文件名
|
|
# 按日期发件人生成附件名
|
|
|
|
filename = f"{from_header}{mail_date}.zip"
|
|
|
|
# 文件名处理
|
|
# =========
|
|
# 解码邮件头中的文件名
|
|
try:
|
|
decoded_name = email.header.decode_header(filename)[0][0]
|
|
if isinstance(decoded_name, bytes):
|
|
decoded_name = decoded_name.decode()
|
|
except Exception as e:
|
|
logger.info(f"{e} \n解析文件名称失败{email.header.decode_header(filename)[0][0]}")
|
|
decoded_name = f"{from_header}{datetime.now().strftime("%d-%b-%Y")}.zip"
|
|
filename = f"{from_header}{mail_date}.zip"
|
|
|
|
|
|
today_str = datetime.now().strftime("%Y%m%d") # 获取当前日期字符串
|
|
base_name, ext = os.path.splitext(decoded_name) # 拆分文件名和扩展名
|
|
# 生成新文件名格式：YYYYMMDD-原文件名.zip
|
|
new_filename = f"{today_str}-{base_name}{ext}"
|
|
if filename:
|
|
new_filename = filename
|
|
# 拼接完整的文件保存路径
|
|
filepath = os.path.join(StarTools.get_data_dir("astrbot_bdzxb_bill"), new_filename)
|
|
|
|
if new_filename not in self.no_file:
|
|
# 附件保存处理
|
|
# ===========
|
|
if not os.path.exists(filepath): # 检查文件是否已存在
|
|
# 以二进制模式保存附件
|
|
with open(filepath, "wb") as f:
|
|
f.write(part.get_payload(decode=True)) # 解码并写入附件内容
|
|
logger.info(f"下载附件: {filename} -> {new_filename}")
|
|
filenames += new_filename+"\n"
|
|
else: # 文件已存在则跳过
|
|
with open(filepath, "wb") as f:
|
|
f.write(part.get_payload(decode=True)) # 解码并写入附件内容
|
|
logger.info(f"附件已存在，覆盖: {new_filename}")
|
|
|
|
|
|
|
|
return "获取成功:"+filenames
|
|
# 查看白名单邮件
|
|
# if from_header not in self.emcil_white: # 严格检查白名单
|
|
# logger.debug(f"跳过非白名单发件人: {from_header}")
|
|
# except Exception as e:
|
|
# logger.error(f" 邮箱登陆失败 抛出异常：{e}")
|
|
# return "邮件搜索失败"
|
|
|
|
|
|
# 帮助
|
|
@filter.command("zdhelp")
|
|
async def mchelp(self, event: AstrMessageEvent):
|
|
logger.info(" 开始执行 zdhelp 命令 ")
|
|
helptxt = """ """
|
|
yield event.plain_result(f"{helptxt}")
|
|
# 获取解压密码冰进行下载解压
|
|
@filter.command("mm")
|
|
async def wxmm(self, event: AstrMessageEvent, wxmm: str,zfbmm: str):
|
|
# # 登录邮箱 下载文件
|
|
self.emaillog()
|
|
logger.info("开始解压文件")
|
|
# # 解压文件 self.data_path
|
|
file_list = os.listdir(self.data_path )
|
|
logger.info(f"{file_list}")
|
|
for aac in file_list:
|
|
self.jzip(filename=aac,mima=wxmm)
|
|
self.jzip(filename=aac,mima=zfbmm)
|
|
# 解析文件
|
|
file_list = os.listdir(f"{self.data_path}/zhangdan")
|
|
self.sqllitaa = sqlite3.connect(f"{self.data_path}/zhangdan.db")
|
|
cur = self.sqllitaa.cursor()
|
|
try:
|
|
for aaa in file_list:
|
|
for icc in self.exceltt(filename=str(self.data_path)+"/zhangdan/"+aaa):
|
|
# logger.info(f"执行语句：{icc}")
|
|
cur.execute(icc)
|
|
self.sqllitaa.commit()
|
|
cur.close()
|
|
self.sqllitaa.close()
|
|
yield event.plain_result("保存完成__使用/chazhang 查询最后10条记录")
|
|
except Exception as e:
|
|
logger.info(f"{e}")
|
|
cur.close()
|
|
self.sqllitaa.close()
|
|
|
|
# 查账
|
|
@filter.command("chazhang")
|
|
async def chazhang(self, event: AstrMessageEvent):
|
|
logger.info(" 开始执行 chazhang 命令 ")
|
|
self.sqllitaa = sqlite3.connect(f"{self.data_path}/zhangdan.db")
|
|
# 创建游标对象
|
|
cursor = self.sqllitaa.cursor()
|
|
try:
|
|
cursor.execute('SELECT * FROM zhangdan ORDER BY id DESC LIMIT 10;')
|
|
jieg =cursor.fetchall()
|
|
self.sqllitaa.commit()
|
|
cursor.close()
|
|
self.sqllitaa.close()
|
|
yield event.plain_result(f"{jieg}")
|
|
except Exception as e:
|
|
logger.info(f"查询失败{e}")
|
|
self.sqllitaa.commit()
|
|
cursor.close()
|
|
self.sqllitaa.close()
|
|
|
|
def exceltt(self,filename):
|
|
yuju = []
|
|
try:
|
|
if ".csv" in filename:
|
|
ata = pd.read_csv(filename, encoding='GB2312', on_bad_lines='skip',header=22)
|
|
# 读取表格数据
|
|
for biao in range(10):
|
|
# 暂存当行数据
|
|
shuju = []
|
|
for aac in ata.loc[biao]:
|
|
shuju.append(str(aac))
|
|
# id:流水号,payid:账单号,paytype:交易类型,paydate:交易时间,payname:交易名称,payto:收入/支出,paysize:交易金额
|
|
# paystu:交易状态,paybox:收支方式,payqd:记录渠道
|
|
# 插入数据
|
|
yuju.append(f"replace into zhangdan(id,payid,paytype,paydate,payname,payto,paysize,paystu,paybox,payqd) VALUES('{np.float64(shuju[9])}','{shuju[9]}','{shuju[1]}','{shuju[0]}','{shuju[2]+shuju[4]}','{shuju[5]}','{shuju[6]}','{shuju[8]}','{shuju[7]}',' 支付宝')")
|
|
|
|
elif ".xls" in filename:
|
|
ata = pd.read_excel(filename,header=17)
|
|
for biao in range(10):
|
|
# 暂存当行数据
|
|
shuju = []
|
|
for aac in ata.loc[biao]:
|
|
shuju.append(str(aac))
|
|
# id:流水号,payid:账单号,paytype:交易类型,paydate:交易时间,payname:交易名称,payto:收入/支出,paysize:交易金额
|
|
# paystu:交易状态,paybox:收支方式,payqd:记录渠道
|
|
# 插入数据
|
|
yuju.append(f"replace into zhangdan(id,payid,paytype,paydate,payname,payto,paysize,paystu,paybox,payqd) VALUES('{np.float64(shuju[8])}','{shuju[8]}','{shuju[1]}','{shuju[0]}','{shuju[2]+shuju[3]}','{shuju[4]}','{shuju[5]}','{shuju[7]}','{shuju[6]}','微信')")
|
|
# 读取xlsx文件
|
|
return yuju
|
|
|
|
except Exception as e:
|
|
logger.info(f"{e}")
|
|
return
|
|
|
|
|
|
# if "支付宝" in filename:
|
|
|
|
# elif "微信" in filename:
|
|
|
|
def jzip(self,filename,mima):
|
|
filename = self.data_path / f'{filename}'
|
|
# 输出目录
|
|
output_path = f'{self.data_path}/zhangdan'
|
|
try:
|
|
os.mkdir(output_path)
|
|
except Exception as e:
|
|
logger.info(f"文件夹已存在开始解压{filename}")
|
|
# try:
|
|
# # 使用AESZipFile打开加密的ZIP文件
|
|
# with AESZipFile(filename, 'r') as zf:
|
|
# # 列出ZIP文件中的所有文件和文件夹
|
|
# logger.info(f"本次解压文件{zf.namelist()}")
|
|
# # 解压所有文件到指定目录
|
|
# zf.extractall(path=output_path, pwd=mima.encode("bytes"))
|
|
# except Exception as e:
|
|
# logger.debug(f"解压失败：{e}")
|
|
|
|
try:
|
|
with AESZipFile(filename, 'r') as zf:
|
|
logger.info(f"本次解压文件{zf.namelist()}")
|
|
zf.extractall(path=output_path, pwd=mima.encode())
|
|
logger.info(f"解压成功，文件保存至：{output_path}")
|
|
except (RuntimeError, zipfile.BadZipFile) as e:
|
|
logger.error(f"解压失败，原因：{e}") # RuntimeError 常因密码错误触发
|
|
except Exception as e:
|
|
logger.error(f"解压过程中出现未知错误：{e}")
|
|
|
|
|
|
|
|
|
|
def download_file(self,urlt,filenamett):
|
|
try:
|
|
response = requests.get(urlt, stream=True)
|
|
response.raise_for_status()
|
|
|
|
download_dir = StarTools.get_data_dir("astrbot_bdzxb_bill")
|
|
os.makedirs(download_dir, exist_ok=True)
|
|
file_name = os.path.basename(urlparse(urlt).path)+filenamett
|
|
if "." not in file_name:
|
|
file_name += ".zip"
|
|
if file_name not in self.no_file:
|
|
logger.info(f"下载文件名是{file_name}")
|
|
file_path = os.path.join(download_dir, file_name)
|
|
logger.info(f"下载文件路径是{file_path}")
|
|
with open(file_path, 'wb') as file:
|
|
for chunk in response.iter_content(chunk_size=8192):
|
|
if chunk:
|
|
file.write(chunk)
|
|
return file_name
|
|
else:
|
|
return
|
|
except Exception as e:
|
|
return
|
|
|
|
|
|
#保存文件
|
|
def get_json_path(self, filename: str) -> Path:
|
|
"""
|
|
读取Jason文件
|
|
|
|
Args:
|
|
filename: 文件名称
|
|
|
|
Returns:
|
|
JSON文件的Path对象
|
|
"""
|
|
data_path = StarTools.get_data_dir("astrbot_bdzxb_bill")
|
|
json_path = data_path / f'{filename}.json'
|
|
json_path.parent.mkdir(parents=True, exist_ok=True)
|
|
return json_path
|
|
|
|
async def terminate(self):
|
|
"""可选择实现异步的插件销毁方法，当插件被卸载/停用时会调用。"""
|