noteparse 1.0.1__tar.gz

noteparse-1.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+ 
+Copyright (c) [2024] [maoyuyan]
+ 
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+ 
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+ 
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

noteparse-1.0.1/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.1
+Name: noteparse
+Version: 1.0.1
+Summary: a package for parse html to noteinfo
+Author: maoyuyan
+Author-email: 294567571@qq.com
+License: MIT
+Platform: all
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Natural Language :: Chinese (Simplified)
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+一个项目

noteparse-1.0.1/README.md

@@ -0,0 +1 @@
+一个项目

noteparse-1.0.1/noteparse.egg-info/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.1
+Name: noteparse
+Version: 1.0.1
+Summary: a package for parse html to noteinfo
+Author: maoyuyan
+Author-email: 294567571@qq.com
+License: MIT
+Platform: all
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Natural Language :: Chinese (Simplified)
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+一个项目

noteparse-1.0.1/noteparse.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+setup.cfg
+setup.py
+noteparse.egg-info/PKG-INFO
+noteparse.egg-info/SOURCES.txt
+noteparse.egg-info/dependency_links.txt
+noteparse.egg-info/entry_points.txt
+noteparse.egg-info/requires.txt
+noteparse.egg-info/top_level.txt
+src/__init__.py
+src/dataHelper.py
+src/dbHelper.py
+src/parse.py
+src/parseService.py

noteparse-1.0.1/noteparse.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

noteparse-1.0.1/noteparse.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+noteparse = noteparse.__init__:init

noteparse-1.0.1/noteparse.egg-info/requires.txt

@@ -0,0 +1,6 @@
+requests>=2.32.3
+bs4>=0.0.2
+fastapi>=0.115.4
+pydantic>=2.7.3
+loguru>=0.7.2
+zhipuai>=2.1.5.20230904

noteparse-1.0.1/noteparse.egg-info/top_level.txt

@@ -0,0 +1 @@
+src

noteparse-1.0.1/setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+description-file = README.md
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

noteparse-1.0.1/setup.py

@@ -0,0 +1,47 @@
+import setuptools  # 导入setuptools打包工具
+
+# with open("README.md", "r", encoding="utf-8") as fh:
+#     long_description = fh.read()
+
+setuptools.setup(
+    name="noteparse",  # 用自己的名替换其中的YOUR_USERNAME_
+    version="1.0.1",  # 包版本号，便于维护版本,保证每次发布都是版本都是唯一的
+    author="maoyuyan",  # 作者，可以写自己的姓名
+    author_email="294567571@qq.com",  # 作者联系方式，可写自己的邮箱地址
+    description="a package for parse html to noteinfo",  # 包的简述
+    long_description=open("README.md", "r", encoding="utf-8").read(),  # 包的详细介绍，一般在README.md文件内
+    long_description_content_type="text/markdown",
+    platforms=["all"],
+    # url="https://github.com/m294567571/noteparse.git",  # 自己项目地址，比如github的项目地址
+    # http://gitlab.uniview.com/mkt_uic/uic-spider.git
+    packages=setuptools.find_packages(),
+    entry_points={
+        "console_scripts" : ['noteparse = noteparse.__init__:init']
+    }, #安装成功后，在命令行输入mwjApiTest 就相当于执行了mwjApiTest.manage.py中的run了
+    install_requires=[
+        'requests>=2.32.3',
+        'bs4>=0.0.2',
+        'fastapi>=0.115.4',
+        'pydantic>=2.7.3',
+        'loguru>=0.7.2',
+        'zhipuai>=2.1.5.20230904',
+    ],
+    classifiers=[
+        # 发展时期,常见的如下
+        #   3 - Alpha
+        #   4 - Beta
+        #   5 - Production/Stable
+        'Development Status :: 4 - Beta',
+        # 开发的目标用户
+        'Intended Audience :: Developers',
+        # 许可证信息
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: Microsoft :: Windows',
+        'Natural Language :: Chinese (Simplified)',
+        # 目标 Python 版本
+        'Programming Language :: Python :: 3',
+        # 属于什么类型
+        'Topic :: Software Development :: Libraries :: Python Modules'
+    ],
+    license='MIT'
+)

noteparse-1.0.1/src/__init__.py

@@ -0,0 +1,5 @@
+from dbHelper import create_connection
+
+def init(host,port,user,password,db):
+#     create_connection(host,port,user,password,db)
+    create_connection()

noteparse-1.0.1/src/dataHelper.py

@@ -0,0 +1,268 @@
+# -*- coding: UTF-8 -*-
+"""
+@File    ：dataHelper.py
+@Author  ：VerSion/08398
+@Date    ：2023/12/07 14:29 
+@Corp    ：Uniview
+"""
+import json
+import os
+import time
+
+import pymysql
+import requests
+
+db_config = {
+    'host': '10.220.6.138',
+    'port': 3306,
+    'user': 'root',
+    'password': '*Ab123456',
+    'db': 'unvbasicx_khgz'
+}
+
+
+def write_log(announce_list, province_key):
+    print('正在写入日志...')
+    # 记录日志
+    try:
+        # 获取当前脚本所在的目录
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        # 创建log文件夹
+        log_folder = os.path.join(current_dir, 'log')
+        if not os.path.exists(log_folder):
+            os.makedirs(log_folder)
+        # 获取当前时间
+        current_time = time.strftime("%Y-%m-%d", time.localtime())
+        # 导出JSON到文件
+        file_name = f"{current_time}_{province_key}.json"
+        file_path = os.path.join(log_folder, file_name)
+        announce_dict = [item.__json__() for item in announce_list]
+        with open(file_path, 'a', encoding='utf-8') as file:
+            json.dump(announce_dict, file, ensure_ascii=False)
+        print(f"JSON已成功导出到文件: {file_path}")
+    except Exception as log_ex:
+        print('日志写入异常：' + str(log_ex))
+        raise Exception('日志写入异常：' + str(log_ex))
+    return file_path
+
+
+def upload_datas(announce_list, province_key):
+    upload_msg = ''
+    # 上传数据
+    try:
+        upload_url = 'http://10.220.6.138/api/khgz/project'
+        headers = {
+            'Content-Type': 'application/json'
+        }
+
+        upload_response = requests.post(upload_url, headers=headers,
+                                        data=json.dumps([item.__json__() for item in announce_list],
+                                                        ensure_ascii=False).encode('utf-8'))
+
+        if upload_response.status_code == 200:
+            upload_result = json.loads(upload_response.text)
+            if upload_result['ok']:
+                upload_msg = f'\033[1;33;42m数据上传成功\033[0m'
+            else:
+                upload_msg = f'\033[1;31;40m数据上传失败，详细信息：{upload_result["msg"]}\033[0m'
+        else:
+            upload_msg = f'数据上传失败，错误码：{upload_response.status_code}'
+    except Exception as upload_ex:
+        upload_msg = '数据上传异常：' + str(upload_ex)
+        raise Exception('数据上传异常：' + str(upload_ex))
+    finally:
+        # 获取当前脚本所在的目录
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        # 创建log文件夹
+        log_folder = os.path.join(current_dir, 'log')
+        if not os.path.exists(log_folder):
+            os.makedirs(log_folder)
+        # 获取当前时间
+        current_time = time.strftime("%Y-%m-%d", time.localtime())
+        # 导出JSON到文件
+        file_name = f"{current_time}_数据上传.json"
+        file_path = os.path.join(log_folder, file_name)
+        with open(file_path, 'a', encoding='utf-8') as file:
+            file.write(f'\n[{province_key}]数据上传日志 => ' + upload_msg)
+            print(upload_msg)
+
+
+def excute_sql(sql_str):
+    # 连接数据库
+    conn = pymysql.connect(host=db_config.get('host', ''), port=db_config.get('port', ''),
+                           user=db_config.get('user', ''), password=db_config.get('password', ''),
+                           db=db_config.get('db', ''))
+    # 创建游标对象
+    with conn.cursor() as cursor:
+        # 执行SQL语句
+        cursor.execute(sql_str)
+    # 提交更改
+    conn.commit()
+
+
+def execute_sql_query(sql_query):
+    # 建立数据库连接
+    conn = pymysql.connect(host=db_config.get('host', ''), port=db_config.get('port', ''),
+                           user=db_config.get('user', ''), password=db_config.get('password', ''),
+                           db=db_config.get('db', ''))
+    # 创建游标对象
+    cursor = conn.cursor(pymysql.cursors.DictCursor)
+    try:
+        # 执行 SQL 查询
+        cursor.execute(sql_query)
+        # 获取查询结果
+        result = cursor.fetchall()
+
+        return result
+
+    except Exception as e:
+        # 如果发生异常，回滚事务
+        conn.rollback()
+        raise Exception('数据库查询异常：' + str(e))
+
+    finally:
+        # 关闭游标和连接
+        cursor.close()
+        conn.close()
+
+
+def insert_engineering_datas(engineering_list):
+    print('正在写入数据...')
+    template_sql = "INSERT INTO tbl_engineering_project (project_name, project_number, publish_date, version_type, project_stage, province_id, city_id, area_id, origin_location, address, construction_period, investment_amount, total_investment, engineering_type, client_type, industry, building_area, land_occupation_area,decoration_situation, foreign_investment, topic, project_scale, installed_capacity, industry_level, project_overview, construction_desc, procures_equipment, client_infos, designer_infos, epcs_infos, contractor_infos, subcontractor_infos, project_link,special_name, data_source, data_source_id) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s);"
+    data = []
+    for item in engineering_list:
+        data.append((item.project_name,
+                     item.project_number,
+                     item.publish_date,
+                     item.version_type,
+                     item.project_stage,
+                     item.province_id,
+                     item.city_id,
+                     item.area_id,
+                     item.origin_location,
+                     item.address,
+                     item.construction_period,
+                     item.investment_amount,
+                     item.total_investment,
+                     item.engineering_type,
+                     item.client_type,
+                     item.industry,
+                     item.building_area,
+                     item.land_occupation_area,
+                     item.decoration_situation,
+                     item.foreign_investment,
+                     item.topic,
+                     item.project_scale,
+                     item.installed_capacity,
+                     item.industry_level,
+                     item.project_overview,
+                     item.construction_desc,
+                     item.procures_equipment,
+                     item.client_infos,
+                     item.designer_infos,
+                     item.epcs_infos,
+                     item.contractor_infos,
+                     item.subcontractor_infos,
+                     item.project_link,
+                     item.special_name,
+                     item.data_source,
+                     item.data_source_id))
+
+    err_msg = ''
+    try:
+        # 连接数据库
+        conn = pymysql.connect(host='10.220.6.138', port=3306, user='root', password='*Ab123456', db='unvbasicx_khgz')
+        # 创建游标对象
+        with conn.cursor() as cursor:
+            # 执行SQL语句
+            cursor.executemany(template_sql, data)
+        # 提交更改
+        conn.commit()
+
+        err_msg = f'写入数据成功！本次写入 {len(engineering_list)} 条数据。'
+        print(f'写入数据成功！本次写入 {len(engineering_list)} 条数据。')
+    except Exception as sql_ex:
+        err_msg = '数据写入数据库异常：' + str(sql_ex)
+        raise Exception('数据写入数据库异常：' + str(sql_ex))
+    finally:
+        # 获取当前脚本所在的目录
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        # 创建log文件夹
+        log_folder = os.path.join(current_dir, 'log')
+        if not os.path.exists(log_folder):
+            os.makedirs(log_folder)
+        # 获取当前时间
+        current_time = time.strftime("%Y-%m-%d", time.localtime())
+        # 导出JSON到文件
+        file_name = f"{current_time}_数据上传.json"
+        file_path = os.path.join(log_folder, file_name)
+        with open(file_path, 'a', encoding='utf-8') as file:
+            file.write(json.dumps([item.__json__() for item in engineering_list]) + '\r\n')
+            file.write(err_msg + '\r\n')
+            file.write('################################################################\r\n')
+
+
+def redis_set(key, value, expire=30, time_type=1):
+    """
+    在redis中设置数据
+    :param key: 键
+    :param value: 值
+    :param expire: 超时时间
+    :param time_type: 时间类型（1-分钟,2-小时,3-天）
+    :return:
+    """
+    # 如果没有传入key，则抛出异常
+    if key is None or len(key) == 0:
+        raise Exception('未传入键')
+    try:
+        upload_url = 'http://10.220.6.63:8090/api/khgz/redis/saveCache'
+        headers = {
+            'Content-Type': 'application/json'
+        }
+        payload = {
+            "key": key,
+            "value": value,
+            "timeout": expire,
+            "type": time_type
+        }
+        redis_response = requests.post(upload_url, headers=headers, data=json.dumps(payload).encode('utf-8'))
+        if redis_response.status_code == 200:
+            redis_result = json.loads(redis_response.text)
+            if redis_result['ok']:
+                print(f'Redis设置成功')
+            else:
+                raise Exception(f'Redis设置失败，详细信息：{redis_result["msg"]}')
+        else:
+            raise Exception('接口调用失败，错误码：' + str(redis_response.status_code))
+    except Exception as redis_ex:
+        print('Redis设置异常：' + str(redis_ex))
+        raise Exception('Redis设置异常：' + str(redis_ex))
+
+
+def redis_get(key):
+    """
+    从redis中获取数据
+    :param key: 键
+    :return:
+    """
+    # 如果没有传入key，则抛出异常
+    if key is None or len(key) == 0:
+        raise Exception('未传入键')
+    try:
+        upload_url = 'http://10.220.6.138/api/khgz/redis/getCache'
+        headers = {
+            'Content-Type': 'application/x-www-form-urlencoded'
+        }
+        redis_response = requests.get(upload_url, headers=headers, params={"key": key})
+        if redis_response.status_code == 200:
+            redis_result = json.loads(redis_response.text)
+            if redis_result['ok']:
+                return str(redis_result['data'])
+            else:
+                raise Exception(f'Redis获取失败，详细信息：{redis_result["msg"]}')
+        else:
+            raise Exception('接口调用失败，错误码：' + str(redis_response.status_code))
+
+    except Exception as redis_ex:
+        print('Redis获取异常：' + str(redis_ex))
+        raise Exception('Redis获取异常：' + str(redis_ex))

noteparse-1.0.1/src/dbHelper.py

@@ -0,0 +1,116 @@
+import pymysql
+from datetime import datetime
+import traceback
+
+
+db_config = {
+    'host': '10.220.6.63',
+    'port': 3306,
+    'user': 'root',
+    'password': '*Ab123456',
+    'db': 'unvbasicx_khgz'
+}
+
+# 创建数据库连接
+def create_connection():
+    try:
+        print(datetime.now(),'开启数据库链接')
+        # 连接数据库
+        connection = pymysql.connect(host=db_config.get('host', ''), port=db_config.get('port', ''),
+                        user=db_config.get('user', ''), password=db_config.get('password', ''),
+                        db=db_config.get('db', ''))
+        print(datetime.now(),'数据库链接成功')
+        
+    except pymysql.MySQLError as e:
+        print(datetime.now(),'数据库链接失败',e)
+    return connection
+
+# # 创建数据库连接
+# def create_connection(host,port,user,password,db):
+#     try:
+#         print(datetime.now(),'开启数据库链接')
+#         # 连接数据库
+#         connection = pymysql.connect(host=host, port=port,
+#                         user=user, password=password,
+#                         db=db)
+#         print(datetime.now(),'数据库链接成功')
+        
+#     except pymysql.MySQLError as e:
+#         print(datetime.now(),'数据库链接失败',e)
+#     return connection
+
+# 确保在程序退出时关闭数据库连接
+def close_connection(connection):
+    if connection and connection.open:
+        print(datetime.now(),'关闭SQL连接')
+        connection.close()
+
+connection = create_connection()
+
+# 通过城市名称查询城市信息
+def queryCityInfo(cityName):
+    query = f'''
+    (SELECT 
+        a.areaid,
+        a.area,
+        c.cityid,
+        c.city,
+        p.provinceid,
+        p.province
+    FROM 
+        unvbasicx_khgz.areas a
+    JOIN 
+        unvbasicx_khgz.cities c ON a.cityid = c.cityid
+    JOIN 
+        unvbasicx_khgz.provinces p ON c.provinceid = p.provinceid
+    WHERE 
+        a.area like '%{cityName}%')
+    UNION ALL
+    (SELECT 
+        '' AS areaid,
+        '' AS area,
+        c.cityid,
+        c.city,
+        p.provinceid,
+        p.province
+    FROM 
+        unvbasicx_khgz.cities c
+    JOIN 
+        unvbasicx_khgz.provinces p ON c.provinceid = p.provinceid
+    WHERE 
+        c.city like '%{cityName}%'
+        AND NOT EXISTS (
+            SELECT 1 FROM unvbasicx_khgz.areas WHERE area like '%{cityName}%'
+        )
+    )
+    UNION ALL
+    (SELECT 
+        '' AS areaid,
+        '' AS area,
+        '' AS cityid,
+        '' AS city,
+        p.provinceid,
+        p.province
+    FROM 
+        unvbasicx_khgz.provinces p
+    WHERE 
+        p.province like '%{cityName}%'
+        AND NOT EXISTS (
+            SELECT 1 FROM unvbasicx_khgz.cities WHERE city like '%{cityName}%'
+        )
+        AND NOT EXISTS (
+            SELECT 1 FROM unvbasicx_khgz.areas WHERE area like '%{cityName}%'
+        )
+    )
+    LIMIT 1
+    '''
+    if connection == None:
+        create_connection()
+    try:
+        with connection.cursor() as cursor:
+            cursor.execute(query)
+            result = cursor.fetchall()  # 获取所有查询结果
+            return result
+    except Exception as e:
+        print(datetime.now(),'通过城市名查询城市信息异常',e)
+        traceback.print_exc()

noteparse-1.0.1/src/parseService.py

@@ -0,0 +1,734 @@
+from datetime import datetime
+import re
+import requests
+import json
+from bs4 import BeautifulSoup
+import traceback
+import dbHelper
+# from fastapi import FastAPI,HTTPException, Request,Depends
+# from fastapi.responses import JSONResponse
+# import uvicorn
+from pydantic import BaseModel, ValidationError
+from typing import List, Literal, Optional, Union
+from loguru import logger
+from zhipuai import ZhipuAI
+# from flask import Flask, request, jsonify
+
+# 金额正则
+pattern = r'(\d+\.?\d*\s*(亿元|万元|元))'
+
+# 项目编号正则
+proejctNumPattern = r'(?:编号|代码|编码|标号)：([A-Za-z0-9-]+)'
+# 字段对应关键字的set，有另外的直接加
+keySet = {
+    'bidUnit' : [
+    '采购人：','招标人单位：','建设单位（招标人）：',
+    '比选人：',
+    '发布单位：',
+    '单位名称：',
+    '招标人：',
+    '招募人：',
+    '业主单位：',
+    '建设单位：',
+    '项目单位：',
+    '项目业主名称：',
+    '法人单位：','招标人名称：','联系人（采购人）：','采购单位：','建设单位(招标人)：','建设单位(或招标人)：','招标（采购）人名称：'
+    ],
+    'proxyUnit' : ['采购代理机构：','代理机构：','招标代理机构：','招募代理机构：','招标机构：','招标代理名称：','招标代理机构名称：','联系人（代理机构）：','招标代理：','代理机构单位：',],
+    'contact' :  ['联系人：','项目法人：','申请人：',],
+    'address' : ['地址：','建设地点：','项目所在地：'],
+    'phone' : ['联系方式：','电话：','联系电话：'],
+    'publishTime' : ['发布时间：','发布日期：','成交时间：'],
+    'winBidUnit': ['成交供应商：','中标人：','中标候选人名称：','供应商名称：','中标候选人单位名称：','中标单位名称：','中标供应商名称：','中标（成交）单位名称：','第一中标（成交）候选人名称：'],
+    'bidAmount': ['预算金额：','预算金额（元）：'],
+    'winBidAmount': ['成交金额/成交下浮率：','中标价（费率或单价等）：','中标总价（元）/费率：','中标金额：','中标（成交）金额：','中标金额：','预期中标价/元：','成交金额：','投标价格：'],
+    'bidContact': ['招标人联系人：','采购经办人：'],
+    'bidPhone': ['招标人联系方式：','采购人电话：'],
+    'proxyContact': ['招标代理联系人：','代理机构经办人：'],
+    'proxyPhone': ['招标代理联系方式：','代理机构电话：']
+}
+
+
+# content--正文html; noteInfo--调接口的入参对象，其他如name、publishTime字段可以解析前就设定好noteInfo对象，以下解析是往里面加的
+def parseContent(content,noteInfo):
+    contentDiv = BeautifulSoup(content,'html.parser')
+    screenStr = []
+    # 第一种是最普通的p标签分行
+    pList = contentDiv.find_all('p')
+    # print('--------len(plist)',pList)
+    if pList and len(pList)>1:
+        for p in pList:
+            # 如果有br,每个br间隔都是一行
+            contains_br = any(child.name == 'br' for child in p.children)
+            if contains_br:
+                text_and_tag = p.contents
+                current_paragraph = ''
+                for item in text_and_tag:
+                    if isinstance(item,str):
+                        current_paragraph += item
+                    elif item.name == 'br':
+                        screenStr.append(current_paragraph.strip())
+                        current_paragraph = ''
+                if current_paragraph:
+                    screenStr.append(current_paragraph.strip())
+            # 如果一行多个信息,多是用空格分割,如:联系人：黄工/汪工 联系电话：0572-********
+            elif  ' ' in p.text and p.text.count('：')>1:
+                strList = p.text.split(' ')
+                screenStr.extend(strList)
+            else:
+                screenStr.append(p.text)
+    # 如果没有P标签，或者p标签只有一个，尝试获取span标签，这类的公告可能用span标签取代p标签，但是span标签较细小，多是包在div、p标签内，所以不单独处理，否则screenStr内容会非常混乱，解析准确度更差
+    else:
+        spanList = contentDiv.find_all('span')
+        for span in spanList:
+            if ' ' in span.text and span.text.count('：')>1:
+                strList = span.text.split(' ')
+                screenStr.extend(strList)
+            else:
+                screenStr.append(span.text)
+
+    # 第二种是table表格格式,按th和td的数量匹配分段的规则,进行标题和内容拼接
+    tableList = contentDiv.find_all('table')
+    for table in tableList:
+        if table:
+            trList = table.find_all('tr')
+            if trList:
+                if len(trList) == 2:
+                    # 先查看标题是不是用th标签
+                    thList = trList[0].find_all('th')
+                    tdList = trList[1].find_all('td')
+                    if len(thList) == len(tdList):
+                        # 只有两个tr,一个tr全是th,另一个全是td,则是成排的
+                        for index,th in enumerate(thList):
+                            screenStr.append(th.text+'：'+tdList[index].text)
+                    elif len(thList) == 0:
+                        # 如果没有th标签，查看第一个tr内是不是也是用的td标签
+                        firstTdList = trList[0].find_all('td')
+                        if len(firstTdList) == len(tdList):
+                            for index,firstTd in enumerate(firstTdList):
+                                screenStr.append(firstTd.text+'：'+tdList[index].text)
+                for index,tr in enumerate(trList):
+                    tdList = tr.find_all('td')
+                    thList = tr.find_all('th')
+                    # 表格里只有td标签的，一般是双数，一个标签td对一个值td
+                    if len(thList)==0 and len(tdList) > 0:
+                        if len(tdList) == 1:
+                            screenStr.append(tdList[0].text)
+                        elif len(tdList) % 2 == 0:
+                            for i in range(0,int(len(tdList)),2) :
+                                if '：' in tdList[i].text:
+                                    screenStr.append(tdList[i].text + tdList[i+1].text )
+                                elif ':' in tdList[i].text:
+                                    screenStr.append(tdList[i].text.replace(':','：') + tdList[i+1].text )
+                                else:
+                                    screenStr.append(tdList[i].text + '：' +tdList[i+1].text )
+
+                        # elif len(tdList) >1:
+                        #     if '：' in tdList[0].text:
+                        #         screenStr.append(tdList[0].text + tdList[1].text )
+                        #     elif ':' in tdList[0].text:
+                        #         screenStr.append(tdList[0].text.replace(':','：') + tdList[1].text)
+                        #     else:
+                        #         screenStr.append(tdList[0].text + '：' +tdList[1].text )
+
+                        # elif len(tdList) == 4:
+                        #     if '：' in tdList[0].text:
+                        #         screenStr.append(tdList[0].text + tdList[1].text )
+                        #     elif ':' in tdList[0].text:
+                        #         screenStr.append(tdList[0].text.replace(':','：') + tdList[1].text )
+                        #     else:
+                        #         screenStr.append(tdList[0].text + '：' +tdList[1].text )
+
+                        #     if '：' in tdList[2].text:
+                        #         screenStr.append(tdList[2].text + tdList[3].text )
+                        #     elif ':' in tdList[2].text:
+                        #         screenStr.append(tdList[2].text.replace(':','：') + tdList[3].text )
+                        #     else:
+                        #         screenStr.append(tdList[2].text + '：' +tdList[3].text )
+                    # 表格里一个th和一个td的，一般是一个th标签对一个td标签
+                    elif len(thList) == 1 and len(tdList) == 1:
+                            if '：' in thList[0].text:
+                                screenStr.append(thList[0].text + tdList[0].text )
+                            elif ':' in thList[0].text:
+                                screenStr.append(thList[0].text.replace(':','：') + tdList[0].text )
+                            else:
+                                screenStr.append(thList[0].text + '：' +tdList[0].text )
+                    elif len(tdList) == 0 and len(thList)>0:
+                        if index < len(trList)-1:
+                            nextThList = trList[index+1].find_all('th')
+                            for index2,th in enumerate(thList):
+                                if '中标候选人名称' == th.text or '投标报价（元）' == th.text:
+                                    screenStr.append(th.text+'：'+nextThList[index2].text)
+                            
+    
+    # 第三种是div标签分段的,目前抽样到有br标签分行
+    # if len(pList) == 0:
+    divList = contentDiv.find_all('div')
+    for divItem in divList:
+        # 如果有br,每个br间隔都是一行
+        contains_br = any(child.name == 'br' for child in divItem.children)
+        if contains_br:
+            text_and_tag = divItem.contents
+            current_paragraph = ''
+            for item in text_and_tag:
+                if isinstance(item,str):
+                    current_paragraph += item
+                elif item.name == 'br':
+                    screenStr.append(current_paragraph.strip())
+                    current_paragraph = ''
+                # 第四种是只有span标签的，这类的因为span标签太细小，大多都会包在div标签、p标签内，所以这类公告不单独分析，否则文本列表会非常混乱
+                elif item.name == 'span':
+                    screenStr.append(item.text.strip())
+                    current_paragraph = ''
+            if current_paragraph:
+                screenStr.append(current_paragraph.strip())
+        # 没有Br的，只保存只有一个：的段落，有些公告内使用div标签分行
+        else:
+            if divItem.text.count('：') == 1:
+                screenStr.append(divItem.text)
+
+
+
+
+
+    amountStr = ''
+    ddlTimeStr = ''
+    for pStr in screenStr:
+        text = re.sub('\s+','',pStr.replace(u'\xa0','').strip().replace('\n','').replace(':','：'))
+        projectNum = re.search(proejctNumPattern,text)
+        if 'projectNum' not in noteInfo and projectNum:
+            noteInfo.projectNum = projectNum.group(1)
+        # 直接把包含元的内容全给GPT,让GPT识别
+        if '元' in text:
+            amountStr += text.replace(',','')
+        if '截止时间' in text:
+            ddlTimeStr += text
+        # 如果文本中包含多个:,则不处理,因为无法判断需要的内容在第几个分号分割
+        if text.count('：') > 1:
+            continue
+        # 因为有很多会有1.2采购人:xxx这种格式,所以只能用in,不能用startwith
+        # 匹配上其中一个关键字之后就不用继续匹配了，优化效率
+        hasMatched = False
+        for keyword, field in keySet.items():
+            if hasMatched:
+                break
+            for key in field:
+                if key in text:
+                    val = text.split('：')[1]
+                    # 所有字段长度理论上都是大于1的，正好可以用来处理单位名称：空这类的情况
+                    if val and len(val)>1:
+                        if keyword == 'bidUnit' and 'bidUnit' not in noteInfo:
+                            print('--------match bidunit-----',val)
+                            noteInfo.bidUnit = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'proxyUnit' and '公章' not in val:
+                            noteInfo.proxyUnit = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'winBidUnit' and 'winBidUnit' not in noteInfo:
+                            noteInfo.winBidUnit = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'bidContact' and 'bidContact' not in noteInfo:
+                            noteInfo.bidContact = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'bidPhone' and 'bidPhone' not in noteInfo:
+                            noteInfo.bidPhone = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'proxyContact' and 'proxyContact' not in noteInfo:
+                            noteInfo.proxyContact = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'proxyPhone' and 'proxyPhone' not in noteInfo:
+                            noteInfo.proxyPhone = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'address' and 'address' not in noteInfo:
+                            noteInfo.address = val
+                            hasMatched = True
+                            break
+                        elif keyword == 'contact':
+                            if 'bidContact' not in noteInfo:
+                                noteInfo.bidContact = val
+                            elif 'proxyContact' not in noteInfo:
+                                noteInfo.proxyContact = val
+                            
+                            hasMatched = True
+                            break
+                        
+                        elif keyword == 'phone':
+                            phone = val.replace('拨打','')
+                            if len(phone) > 25:
+                                print(datetime.now(),'电话获取错误跳过',phone)
+                                continue
+                            if 'bidPhone' not in noteInfo:
+                                noteInfo.bidPhone = phone
+                            elif 'proxyPhone' not in noteInfo:
+                                noteInfo.proxyPhone = phone                                       
+                            hasMatched = True
+                            break
+                        elif keyword == 'winBidAmount':
+                            try:
+                                winBidAmount = val.replace(',','')
+                                if winBidAmount.endswith('万元'):
+                                    amount = float(winBidAmount.replace('万元','')) * 10000
+                                    noteInfo.winBidAmount = amount
+                                elif winBidAmount.endswith('元'):
+                                    amount = float(winBidAmount.replace('元',''))
+                                    noteInfo.winBidAmount = amount
+                                else:
+                                    noteInfo.winBidAmount = float(amount)
+                            except Exception as parse_amount_err:
+                                print(datetime.now(),'中标金额转换失败',winBidAmount,parse_amount_err)
+                        elif keyword == 'bidAmount':
+                            match = re.search(pattern, val.replace(',',''))
+                            if match: 
+                                tender_number = match.group(1)
+                                if '万元' in tender_number:
+                                    amountstr = tender_number.replace('万元','')
+                                    amount = float(amountstr) * 10000
+                                    noteInfo.bidAmount = amount
+                                elif '元' in tender_number:
+                                    amount = float(tender_number.replace('元',''))
+                                    noteInfo.bidAmount = amount
+
+        # 名称这个词太宽泛,所以用startswith,以上词相对精准,可以用in匹配
+        if text.startswith('名称：') or text.startswith('单位名称：'):
+            if 'bidUnit' not in noteInfo:
+                noteInfo.bidUnit = text.split('：')[1]
+            elif 'proxyUnit' not in noteInfo:
+                noteInfo.proxyUnit = text.split('：')[1]
+        elif text.startswith('发布时间：') or text.startswith('发布日期：'):
+            publishTime = parsePublishTime(text.split('：')[1])
+            noteInfo.publishTime = publishTime
+
+    if amountStr != '':
+        # 最多传1000字
+        if 'bidAmount' not in noteInfo and noteInfo.noticeType != 1:
+            amount = getAmountByZhiPu(amountStr[:1000])
+            print(datetime.now(),'amount',amount)
+            if amount != None and amount != 2330000.0:
+                noteInfo.bidAmount = amount
+        elif 'winBidAmount' not in noteInfo and noteInfo.noticeType == 1:
+            amount = getAmountByZhiPu(amountStr[:1000])
+            print(datetime.now(),'amount',amount)
+
+            if amount != None and amount != 2330000.0:
+                noteInfo.winBidAmount = amount  
+
+    if ddlTimeStr != '':
+        ddlDate = getBidDdlTimeByZhiPu(ddlTimeStr)
+        if ddlDate != None:
+            noteInfo.bidDdlTime = ddlDate.strftime('%Y-%m-%d %H:%M:%S')          
+    print('----解析完毕---')
+    # noteInfo['content'] = ''
+    # 尝试获取地市信息，如果报错，不影响其他字段插入
+    try:
+        if 'cityId' not in noteInfo and 'address' in noteInfo:
+            # 优先使用公告标题查询公告所属地市
+            noteInfo = parseCityId(noteInfo.address,noteInfo)
+            # 如果通过公告名称无法提取地市名称，则通过采购单位名称查询
+            if 'cityId' not in noteInfo and 'bidUnit' in noteInfo:
+                noteInfo = parseCityId(noteInfo.bidUnit,noteInfo)
+                # 如果通过公告名称无法提取地市名称，则通过采购单位名称查询
+                if 'cityId' not in noteInfo:
+                    noteInfo = parseCityId(noteInfo.name,noteInfo)
+    except Exception as get_city_info_err:
+        print(datetime.now(),'通过文本查询地市信息异常',get_city_info_err)
+
+
+    # 验证截止时间和发布时间,如果截止时间在发布时间之前,那这个时间错误,置为空
+    if 'publishTime' in noteInfo and 'bidDdlTime' in noteInfo:
+        publishTime = datetime.strptime(noteInfo.publishTime,'%Y-%m-%d %H:%M:%S')             
+        bidDdlTime = datetime.strptime(noteInfo.bidDdlTime,'%Y-%m-%d %H:%M:%S')
+        if bidDdlTime < publishTime:
+            noteInfo.bidDdlTime = ''            
+    # print('----noteInfo:',noteInfo)       
+    return noteInfo
+
+def parseCityId(cityParseStr,noteInfo):
+    cityName = getCityInfoByZhiPu(cityParseStr)
+    if cityName:
+        cityInfoList = dbHelper.queryCityInfo(cityName)
+        print(datetime.now(),'查询到公告所属省市区为',cityInfoList)
+        if len(cityInfoList)>0:
+            cityInfo = cityInfoList[0]
+            if '' != cityInfo[4]:
+                # 如果noteInfo已经定位了省份，则验证省份ID是否正确，正确则添加cityId或areaId,如果不正确，则地区匹配错误不作更新
+                if 'provinceId' in noteInfo:
+                    if noteInfo.provinceId == cityInfo[4]:
+                        if '' != cityInfo[0]:
+                            noteInfo.areaId = cityInfo[0]
+                        if '' != cityInfo[2]:
+                            noteInfo.cityId = cityInfo[2]
+                    else:
+                        print(datetime.now(),'获取到地市信息与当前provinceId不符，数据抛弃')
+                else:
+                # 如果noteInfo没有定位省份，则直接添加provinceId，cityId和areaId
+                    noteInfo.provinceId = cityInfo[4]
+                    if '' != cityInfo[0]:
+                        noteInfo.areaId = cityInfo[0]
+                    if '' != cityInfo[2]:
+                        noteInfo.cityId = cityInfo[2]
+    return noteInfo
+
+
+def getBidDdlTimeByZhiPu(ddlTimeStr):
+    try:
+        client = ZhipuAI(api_key="9ece6c42cdca139afa262b16c93814d5.qVKFvLXWFfwuaHgp") # 填写您自己的APIKey
+        response = client.chat.completions.create(
+            model="glm-4-flash",  # 填写需要调用的模型编码
+            messages=[
+                {"role": "system", "content": "# 角色：您是项目信息提取专家，专注于从项目公告的片段中提取投标文件的截止时间等## 技能：截止时间提取## 约束条件###1、时间来自用户输入原文###2、仅保留一个结果###3、结果按截止时间：XXXX-XX-XX XX:XX:XX的格式返回，且不要有其他描述，只显示一个截止时间即可###4、若结果没有秒数，则默认补充秒数为00###5、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：凡有意参加投标者，请于2024年10月16日00时00分至2024年10月23日23时59分（北京时间，下同），登录全国公共资源交易平台，通过数字证书免费下载招标文件（含招标文件的澄清、修改，通知等内容）。6.1 投标文件递交的截止时间（投标截止时间，下同）为2024年11月6日9时30分，投标人应在截止时间前通过登录全国- **处理步骤**：  1. 按分号；分割用户输入的内容  2. 遍历每一段内容并理解用户输入  3. 拆分出各个金额及金额对应的意思 4. 按照截止时间：XXXX-XX-XX XX:XX:XX的格式设定输出结果 -**输出结果案例**：截止时间：2024-11-06 09:30:00 "},
+                {"role": "user", "content": "请提取下文中的截止时间，只需回答截止时间即可，不要有其他描述，文本如下：%s" % (ddlTimeStr)}
+            ],
+        )
+        resContent = response.choices[0].message.content
+        ddlRes = resContent.split('：')[1]
+        ddlTime = datetime.strptime(ddlRes,'%Y-%m-%d %H:%M:%S')
+        return ddlTime
+    except Exception as parse_ddl_err:
+        return None
+
+
+def getbidDdlTime(ddlTimeStr):
+    url = 'http://10.220.6.180:17860/v1/chat/completions'
+    # url = 'http://223.76.195.4:18012/api/v1/chat/completions'
+    param ={
+            "model": "chatglm3",
+            "messages": [
+                    {
+                            "role": "system",
+                            "content": "# 角色：您是项目信息提取专家，专注于从项目公告的片段中提取投标文件的截止时间等## 技能：截止时间提取## 约束条件###1、时间来自用户输入原文###2、仅保留一个结果###3、结果按截止时间：XXXX年XX月XX日 XX时XX分的格式返回，且不要有其他描述，只显示一个截止时间即可###4、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：凡有意参加投标者，请于2024年10月16日00时00分至2024年10月23日23时59分（北京时间，下同），登录全国公共资源交易平台（贵州省·六盘水市），网址http://ggzy.gzlps.gov.cn，通过数字证书免费下载招标文件（含招标文件的澄清、修改，通知等内容）。6.1 投标文件递交的截止时间（投标截止时间，下同）为2024年11月6日9时30分，投标人应在截止时间前通过登录全国- **处理步骤**：  1. 按分号；分割用户输入的内容  2. 遍历每一段内容并理解用户输入  3. 拆分出各个金额及金额对应的意思 4. 按照截止时间：XXXX年XX月XX日 XX时XX分的格式设定输出结果 -**输出结果案例**：截止时间：2024年11月6日 9时30分 "
+                    },
+                    {
+                            "role": "user",
+                            "content": "请提取下文中的截止时间，只需回答截止时间即可，不要有其他描述，文本如下：%s" % (ddlTimeStr)
+                    }
+            ],
+            "stream": False,
+            "temperature": 0,
+            "top-p": 0
+    }
+    header = {
+        'Content-Type':'application/json',
+        'Authorization':  'Bearer sk-n0voW3LMMrDGaRtG75F34330EbF94d3bA8606c6d9910F0E8'
+        # 'Authorization':  'Bearer fastgpt-78cMEaF8hoZVndBjsr0nSPexYrPuDiEtcDhx2egnNteN5sWhNqHYFvvhj5ySvuZ2h'      
+    }
+    try:
+        print(datetime.now(),'请求GPT获取截标时间:',ddlTimeStr)
+        response = requests.post(url=url,data=json.dumps(param),headers=header,timeout=30)
+        print(datetime.now(),'get ddlTime response:',response.text)
+        res = json.loads(response.text)
+        resContent = res['choices'][0]['message']['content']
+        if '：':  
+            ddlRes = resContent.split('：')[1]
+            try:
+                if '年' in ddlRes:
+                    try:
+                        date = datetime.strptime(ddlRes,'%Y年%m月%d日 %H时%M分')
+
+                    except Exception:
+                        date = datetime.strptime(ddlRes,'%Y年%m月%d日%H时%M分')
+
+                    # print(date.strftime('%Y-%m-%d %H:%M:%S'))
+                else:
+                    try:
+                        date = datetime.strptime(ddlRes,'%Y-%m-%d %H:%M')
+                    except Exception:
+                        date = datetime.strptime(ddlRes,'%Y-%m-%d %H:%M:%S')
+                return date
+            except Exception as err:
+                print(datetime.now(),err)
+                return None
+        else:
+            # print(type(resContent))
+            return None
+    except Exception as get_amount_err:
+        print('获取截止时间失败',get_amount_err)
+        return None
+
+def getAmountByZhiPu(amountStr):
+    client = ZhipuAI(api_key="9ece6c42cdca139afa262b16c93814d5.qVKFvLXWFfwuaHgp") # 填写您自己的APIKey
+    response = client.chat.completions.create(
+        model="glm-4-flash",  # 填写需要调用的模型编码
+        messages=[
+            {"role": "system", "content": "# 角色：您是项目金额提取专家，专注于从项目公告的片段中提取项目金额等## 技能：项目金额提取## 约束条件###1、所有项目金额全部来自用户输入原文###2、所有金额转换为XXX元###3、仅保留一个结果###4、缴纳材料费、注册资本不是招标金额###5、预算金额，中标金额，招标金额，合同金额，项目投资，施工合同估算价，工程造价这些词都是项目金额，如果没有这些描述，取意思最相近的金额。如果确实无法匹配项目金额，返回项目金额：0元###6、如果有多个金额都是项目金额的描述，取金额最大的一个数字返回###7、结果按项目金额：XXX元的格式返回，且不要有其他描述，只显示一个项目金额：xx元即可###8、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：预算金额（万元）：233.0000000；最高限价（如有）：2350000.00元；售价：0元- **处理步骤**：  1. 按分号；分割用户输入的内容  2. 遍历每一段内容并理解用户输入  3. 拆分出各个金额及金额对应的意思  4. 分辨拆分出的金额哪一个才是公告的项目金额，如果金额单位是万元，则直接返回万元单位的结果，如果金额单位是亿元，则直接返回亿元单位的结果 5. 按照项目金额：xxx元的格式设定输出结果    7. 输出结果-**输出结果案例**：项目金额：233.0000000万元"},
+            {"role": "user", "content": "请提取下文中的项目金额，只需回答项目金额：xx元或者项目金额：xx万元即可，不要有其他描述，文本如下：%s" % (amountStr)}
+        ],
+    )
+    answerStr = response.choices[0].message.content
+    match = re.search(pattern, answerStr.replace(',',''))  
+    if match:  
+        # 提取并打印招标编号  
+        tender_number = match.group(1)
+        if '万元' in tender_number:
+            amountstr = tender_number.replace('万元','')
+            amount = float(amountstr) * 10000
+            print(datetime.now(),'最终项目金额:',amount)
+            return amount
+        elif '亿元' in tender_number:
+            amountstr = tender_number.replace('亿元','')
+            amount = float(amountstr) * 100000000
+            print(datetime.now(),'最终项目金额:',amount)
+            return amount
+        elif '元' in tender_number:
+            amount = float(tender_number.replace('元',''))
+            print(datetime.now(),'最终项目金额:',amount)
+            return amount
+        else:
+            amount = float(tender_number)
+            print(datetime.now(),'最终项目金额:',amount)
+            return amount
+    else:
+        # print(type(resContent))
+        return None
+
+def getAmount(amountStr):
+    # 正则表达式匹配浮点数
+    parPattern = r'(\d+(\.\d+)?)(?=[^\d])'
+
+    # 定义一个函数来处理匹配到的数字
+    def format_number(match):
+        num_str = match.group(0)
+        num = float(num_str)
+        # 格式化数字，去掉小数点后的多余0，并保留至少一位小数
+        formatted_num = f"{num:.2f}"
+        return formatted_num
+
+    # 使用正则表达式替换文本中的数字
+    amountStr = re.sub(parPattern, format_number, amountStr)
+    url = 'http://10.220.6.180:17860/v1/chat/completions'
+    # url = 'http://223.76.195.4:18012/api/v1/chat/completions'
+    param ={
+    "model": "chatglm3",
+    "messages": [
+        {
+            "role": "system",
+            "content": "# 角色：您是项目金额提取专家，专注于从项目公告的片段中提取项目金额等## 技能：项目金额提取## 约束条件###1、所有项目金额全部来自用户输入原文###2、所有金额转换为XXX元###3、仅保留一个结果###4、缴纳材料费、注册资本不是招标金额###5、预算金额，中标金额，招标金额，合同金额，项目投资，施工合同估算价，工程造价这些词都是项目金额，如果没有这些描述，取意思最相近的金额。如果确实无法匹配项目金额，返回项目金额：0元###6、如果有多个金额都是项目金额的描述，取金额最大的一个数字返回###7、结果按项目金额：XXX元的格式返回，且不要有其他描述，只显示一个项目金额：xx元即可###8、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：预算金额（万元）：233.0000000；最高限价（如有）：2350000.00元；售价：0元- **处理步骤**：  1. 按分号；分割用户输入的内容  2. 遍历每一段内容并理解用户输入  3. 拆分出各个金额及金额对应的意思  4. 分辨拆分出的金额哪一个才是公告的项目金额，如果金额单位是万元，则直接返回万元单位的结果，如果金额单位是亿元，则直接返回亿元单位的结果 5. 按照项目金额：xxx元的格式设定输出结果    7. 输出结果-**输出结果案例**：项目金额：233.0000000万元"
+        },
+        {"role": "user", "content": "请提取下文中的项目金额，只需回答项目金额：xx元或者项目金额：xx万元即可，不要有其他描述，文本如下：%s" % (amountStr)}
+        ],
+    "stream": False,
+    "temperature": 0
+    }
+    header = {
+        'Content-Type':'application/json',
+        'Authorization':  'Bearer sk-n0voW3LMMrDGaRtG75F34330EbF94d3bA8606c6d9910F0E8'
+        # 'Authorization':  'Bearer fastgpt-78cMEaF8hoZVndBjsr0nSPexYrPuDiEtcDhx2egnNteN5sWhNqHYFvvhj5ySvuZ2h'      
+    }
+    try:
+        print(datetime.now(),'请求GPT获取金额:',amountStr)
+        response = requests.post(url=url,data=json.dumps(param),headers=header,timeout=30)
+        print(datetime.now(),'get amount response:',response.text)
+        res = json.loads(response.text)
+        resContent = res['choices'][0]['message']['content']
+        match = re.search(pattern, resContent.replace(',',''))  
+        if match:  
+            # 提取并打印招标编号  
+            tender_number = match.group(1)
+            if '万元' in tender_number:
+                amountstr = tender_number.replace('万元','')
+                amount = float(amountstr) * 10000
+                print(datetime.now(),'最终项目金额:',amount)
+                return amount
+            elif '亿元' in tender_number:
+                amountstr = tender_number.replace('亿元','')
+                amount = float(amountstr) * 100000000
+                print(datetime.now(),'最终项目金额:',amount)
+                return amount
+            elif '元' in tender_number:
+                amount = float(tender_number.replace('元',''))
+                print(datetime.now(),'最终项目金额:',amount)
+                return amount
+            else:
+                amount = float(tender_number)
+                print(datetime.now(),'最终项目金额:',amount)
+                return amount
+        else:
+            # print(type(resContent))
+            return None
+    except Exception as get_amount_err:
+        print('获取金额失败',get_amount_err)
+        return None
+
+
+def parsePublishTime(str):
+    publishTimeStr = str.replace('：',':').replace('/','-').strip()
+    try:
+        if '-' in publishTimeStr:
+            semCount = publishTimeStr.count(':')
+            if semCount == 0:
+                dateObj = datetime.strptime(publishTimeStr,'%Y-%m-%d')
+                # 如果时间是同一天，但是没有详细时间，返回当前的详细时间
+                if dateObj.date() == datetime.now().date():
+                    return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+                else:
+                    return dateObj.strftime('%Y-%m-%d %H:%M:%S')
+            elif semCount == 1:
+                dateObj = datetime.strptime(publishTimeStr,'%Y-%m-%d %H:%M')
+                return dateObj.strftime('%Y-%m-%d %H:%M:%S')            
+            elif semCount == 2:
+                dateObj = datetime.strptime(publishTimeStr,'%Y-%m-%d %H:%M:%S')
+                return dateObj.strftime('%Y-%m-%d %H:%M:%S')
+        elif '年' in publishTimeStr:
+            semCount = publishTimeStr.count(':')
+            if semCount == 0:
+                dateObj = datetime.strptime(publishTimeStr,'%Y年%m月%d日')
+                return dateObj.strftime('%Y-%m-%d %H:%M:%S')
+            elif semCount == 1:
+                dateObj = datetime.strptime(publishTimeStr,'%Y年%m月%d日 %H:%M')
+                return dateObj.strftime('%Y-%m-%d %H:%M:%S')            
+            elif semCount == 2:
+                dateObj = datetime.strptime(publishTimeStr,'%Y年%m月%d日 %H:%M:%S')
+                return dateObj.strftime('%Y-%m-%d %H:%M:%S')
+        else:
+            return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+    except Exception as parse_date_err:
+        print(datetime.now(),'时间识别错误，发布时间默认为当前时间',str)
+        return datetime.now().strftime('%Y-%m-%d %H:%M:%S')  
+
+
+
+
+def remove_space(str):
+    return ' '.join(str.split())
+
+
+def getCityInfoByZhiPu(cityInfoStr):
+    client = ZhipuAI(api_key="9ece6c42cdca139afa262b16c93814d5.qVKFvLXWFfwuaHgp") # 填写您自己的APIKey
+    response = client.chat.completions.create(
+        model="glm-4-flash",  # 填写需要调用的模型编码
+        messages=[
+            {"role": "system", "content": "# 角色：您是项目所属地提取专家，专注于从项目公告中地名## 技能：项目金额提取## 约束条件###1、项目所属地名一定在用户输入的原文内，不要杜撰###2、如果项目名同时包含省、市、区，只返回区名###3、仅保留一个结果###3、结果按项目所属地：XXX的格式返回，且不要有其他描述，只显示一个项目所属地：xx市/区即可###4、如果文中没有明确写明所属地，则范围空值即可###8、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：陕西省渭南市秦岭北麓（东部）森林火灾高风险区综合治理工程建设项目招标公告 **处理步骤**：  1. 先提取出用户输入文本内包含的省市区地名，如陕西省、渭南市  2. 遍历提取出的地名，判断地名数量，地名是属于省还是地市还是地区  3. 按地区>地市>省份的优先级排序  4. 取最高优先级的地名拼凑结果    7. 输出结果-**输出结果案例**：项目所属地：渭南"},
+            {"role": "user", "content": "请提取下标题中的的项目所属地，只需回答项目所属地：xx即可，不要有其他描述，文本如下%s" % (cityInfoStr)}
+        ],
+    )
+    resContent = response.choices[0].message.content
+    if '项目所属地：'in resContent:  
+        # 提取并打印招标编号  
+        cityName = resContent.split('：')[1]
+        return cityName
+    else:
+        return None
+
+def getCityInfo(cityInfoStr):
+    url = 'http://10.220.6.180:17860/v1/chat/completions'
+    # url = 'http://223.76.195.4:18012/api/v1/chat/completions'
+    param ={
+        "model": "chatglm3",
+        "messages": [
+                {
+                        "role": "system",
+                        "content": "# 角色：您是项目所属地提取专家，专注于从项目公告中地名## 技能：项目金额提取## 约束条件###1、项目所属地名一定在用户输入的原文内，不要杜撰###2、如果项目名同时包含省、市、区，只返回区名###3、仅保留一个结果###3、结果按项目所属地：XXX的格式返回，且不要有其他描述，只显示一个项目所属地：xx市/区即可###4、如果文中没有明确写明所属地，则范围空值即可###8、输出结果之前验算一下约束条件### 示例互动流程- **用户询问**：陕西省渭南市秦岭北麓（东部）森林火灾高风险区综合治理工程建设项目招标公告 **处理步骤**：  1. 先提取出用户输入文本内包含的省市区地名，如陕西省、渭南市  2. 遍历提取出的地名，判断地名数量，地名是属于省还是地市还是地区  3. 按地区>地市>省份的优先级排序  4. 取最高优先级的地名拼凑结果    7. 输出结果-**输出结果案例**：项目所属地：渭南"
+                },
+                {
+                        "role": "user",
+                        "content": "请提取下标题中的的项目所属地，只需回答项目所属地：xx即可，不要有其他描述，文本如下%s" % (cityInfoStr)
+                }
+        ],
+        "stream": False,
+        "temperature": 0
+    }
+    header = {
+        'Content-Type':'application/json',
+        'Authorization':  'Bearer sk-n0voW3LMMrDGaRtG75F34330EbF94d3bA8606c6d9910F0E8'
+        # 'Authorization':  'Bearer fastgpt-78cMEaF8hoZVndBjsr0nSPexYrPuDiEtcDhx2egnNteN5sWhNqHYFvvhj5ySvuZ2h'      
+    }
+    try:
+        print(datetime.now(),'请求GPT提取地市名称:',cityInfoStr)
+        response = requests.post(url=url,data=json.dumps(param),headers=header,timeout=30)
+        print(datetime.now(),'get amount response:',response.text)
+        res = json.loads(response.text)
+        resContent = res['choices'][0]['message']['content']
+        if '项目所属地：'in resContent:  
+            # 提取并打印招标编号  
+            cityName = resContent.split('：')[1]
+            return cityName
+        else:
+            return None
+    except Exception as get_amount_err:
+        print('获取地市名称失败',get_amount_err)
+        return None
+
+
+
+
+# class NoteInfo(BaseModel):
+#     # 公告名称
+#     name: str 
+#     url: str # 原文链接
+#     dataSource: str # 数据源
+#     publishTime: Optional[str] = '' # 发布时间
+#     provinceId: Optional[str] = '' # 省份id
+#     cityId: Optional[str] = '' # 城市id
+#     areaId: Optional[str] = '' # 区id
+#     projectNum: Optional[str] = '' # 项目编码
+#     noticeType: Optional[int] = 0 # 公告类型
+#     bidUnit: Optional[str] = '' # 招标单位
+#     bidContact: Optional[str] = '' # 招标单位联系人
+#     bidPhone: Optional[str] = '' # 招标单位联系人电话
+#     bidAmount: Optional[float] = 0.0 # 招标金额
+#     proxyUnit: Optional[str] = '' # 代理公司名称
+#     proxyContact: Optional[str] = '' # 代理公司联系人
+#     proxyPhone: Optional[str] = '' # 代理公司联系人电话
+#     winBidUnit: Optional[str] = '' # 中标单位
+#     winBidAmount: Optional[float] = 0.0 # 中标金额
+#     address: Optional[str] = '' # 招标单位地址
+#     bidDdlTime: Optional[str] = '' # 投标截止时间
+#     content: Optional[str] = '' # 公告内容
+
+# class ParseResponse(BaseModel):
+#     code: int = 0
+#     msg: str
+#     data: Optional[NoteInfo] = None
+
+# app = FastAPI()
+
+
+
+# @app.post('/content/parse')
+# async def parsePost(noteInfo: NoteInfo ):
+#     # if not noteInfo.name or not noteInfo.url:
+#     #     print('缺少必填字段')
+#     #     raise HTTPException(status_code=400,detail="公告名称与路径必填")
+#     print(datetime.now(),f'=====开始解析{noteInfo.dataSource}--{noteInfo.name}--{noteInfo.url}')
+#     content = noteInfo.content
+#     if len(content) > 1:
+#         noteInfo = parseContent(content,noteInfo)
+#     #  # 返回响应，确保使用UTF-8编码
+#     # response = app.response_class(
+#     #     response=json.dumps(noteInfo, ensure_ascii=False),
+#     #     status=200,
+#     #     mimetype='application/json'
+#     # )
+#     # response.headers["Content-Type"] = "application/json; charset=utf-8"
+#     # return ParseResponse(code=0, msg='success', data=noteInfo)
+#     print(datetime.now(),f'=====解析完毕{noteInfo.dataSource}--{noteInfo.name}--{noteInfo.url}')
+#     return noteInfo
+
+    
+
+# 设定main函数,程序起点
+if __name__ == '__main__':
+    try:
+        # uvicorn.run(app, host='0.0.0.0', port=18881, workers=1)
+
+    # #    noteInfo = testMatch('电话：ABC公司')
+        pStr = '名 称：抚松县教育局局'
+    #     text = re.sub('\s+','',pStr.replace(u'\xa0','').strip().replace('\n','').replace(':','：'))
+    #     print('======text:',text)
+    #     a = remove_space(text)
+    #     print(a)
+    # #    a = ' 1.2852万元。收取对象：中标（成交）供应商。2.采购预算总金额：1,000,000.00元，最高限价：978,000.00元。地址：中国(四川)自由贸易试验区成都高新区益州大道中段722号3栋1单元603号中标（成交）金额：952,000.00元金额(元)：952,000.00'
+    # #    amount = getAmount(a[:1000])
+    # #    print('noteInfo',amount)
+
+    except Exception as err:
+        print(f'任务执行失败',err)
+        traceback.print_exc()
+        
+