python发送xml格式socket心跳告警

需求

• 1、行内,应用程序发送心跳,发送xml到socker.
• 2、通过ps获取程序是否存在,判断是否发送心跳.
• 3、使用xml.etree.ElementTree来格式化xml格式

实现

• 1、使用socket link来创建socket链接
• 2、使用xml.etree.ElementTree来格式化xml格式
• 3、根据需要监控process_name_list 列表来循环 判断是否发送心跳
• 4、根据发送socket返回信息判断是否发送socket是否成功
• 5、记录日志信息

代码

#!/usr/bin/python3

"""
需求：
  1、行内,应用程序发送心跳,发送xml到socker.
  2、通过ps获取程序是否存在,判断是否发送心跳.
"""

import xml.etree.ElementTree as ET
import socket,os,time,logging
from logging.handlers import RotatingFileHandler

def build_xml_message(heartbeat_interval, name, SystemName, AlarmRes):
  local_time1 = int(round(time.time() * 1000))
  local_time2 = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())

  root = ET.Element("ALARMSTART")
  name_element = ET.SubElement(root, "SystemName")
  name_element.text = SystemName
  age_element = ET.SubElement(root, "AlarmID")
  age_element.text = str(local_time1)
  city_element = ET.SubElement(root, "AlarmEquipment")
  city_element.text = name
  city_element = ET.SubElement(root, "AlarmRes")
  city_element.text = AlarmRes
  city_element = ET.SubElement(root, "EventTime")
  city_element.text = local_time2
  return ET.tostring(root, encoding="utf-8", method="xml").decode("utf-8")

def send_heartbeat(xml_message, server_address):
  sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
  sock.settimeout(10)
  try:
      # print(xml_message.encode("utf-8"))
      sock.connect(server_address)
      sock.sendall(xml_message.encode("utf-8"))
      response = sock.recv(1024)
      local_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
      if "flag=true" in str(response):
        log_info = str(local_time) + " info send info ok ,return info: " +  str(response)
        logger.debug(log_info)
        # write_data_to_file_append(log_file_path, log_info)
      else:
        log_info = str(local_time) + " error send info fail ,return info: " +  str(response)
        logger.debug(log_info)
        #write_data_to_file_app/end(log_file_path, log_info)
  except Exception as e:
      logger.error("Failed to send heartbeat to " + str(server_address) +  " "  + str(e))
  finally:
      sock.close()

def write_data_to_file_append(file_path, data):
   with open(file_path, "a") as f:
       f.write(data)

def is_process_running(ps_out,process_name):
   # 遍历所有进程，查找具有给定名称的进程
   for line in ps_out.splitlines():
       if process_name in line:
           return True
   return False


if __name__ == "__main__":
  #需要链接soket 服务端
  server_address = ("localhost", 10000)
#   log_file_path = "send_socket.log"
  heartbeat_interval = 5
  #需要监控的程序名
  process_name_list = ["nginx","mysqld","cdesk_nginx1"]
  #xml名称定义
  SystemName = "ccc-test-001"
  AlarmRes = "定制接口服务器"

  ##### logger #####
  log_file = "./log/heratbeat.log"
  shell = "mkdir -p " + log_file.split("heratbeat.log")[0]
  os.popen(shell)

  # 创建日志记录器
  logger = logging.getLogger("my_logger")
  logger.setLevel(logging.DEBUG)

  # 创建RotatingFileHandler对象
  max_log_size = 100 * 1024 * 1024  # 100 MB
  backup_count = 50
  handler = RotatingFileHandler(log_file, maxBytes=max_log_size, backupCount=backup_count)

  # 定义日志格式
  formatter = logging.Formatter("%(asctime)s %(thread)d %(filename)s:%(lineno)d %(levelname)s %(message)s")
  handler.setFormatter(formatter)

  # 将处理程序添加到日志记录器
  logger.addHandler(handler)

  while True:
      #使用os.popen执行ps命令，获取所有进程
      ps_output = os.popen("ps aux").read()
      # ps_output = os.popen("ps -e").read()
      for process_name in process_name_list:
        if is_process_running(ps_output,process_name):
          xml_message = build_xml_message(heartbeat_interval, process_name, SystemName, AlarmRes)
          print(xml_message)
          logger.debug(process_name + " is running.")
          send_heartbeat(xml_message, server_address)
        else:
          logger.error(process_name + " is not running.")
      time.sleep(heartbeat_interval)
  # 程序结束时关闭处理程序
  logger.removeHandler(handler)
  handler.close()

解决运行情况

• 心跳监控运行状态

2023-09-19 10:32:49,369 140176451651392 heratbeat.py:103 DEBUG nginx is running.
2023-09-19 10:32:49,370 140176451651392 heratbeat.py:45 DEBUG 2023-09-19 10:32:49 error send info fail ,return info: b'<ALARMSTART><SystemName>ccc-test-001</SystemName><AlarmID>1695090769369</AlarmID><AlarmEquipment>nginx</AlarmEquipment><AlarmRes>\xe5\xae\x9a\xe5\x88\xb6\xe6\x8e\xa5\xe5\x8f\xa3\xe6\x9c\x8d\xe5\x8a\xa1\xe5\x99\xa8</AlarmRes><EventTime>2023-09-19 10:32:49</EventTime></ALARMSTART>'
2023-09-19 10:32:49,370 140176451651392 heratbeat.py:103 DEBUG mysqld is running.
2023-09-19 10:32:49,371 140176451651392 heratbeat.py:45 DEBUG 2023-09-19 10:32:49 error send info fail ,return info: b'<ALARMSTART><SystemName>ccc-test-001</SystemName><AlarmID>1695090769370</AlarmID><AlarmEquipment>mysqld</AlarmEquipment><AlarmRes>\xe5\xae\x9a\xe5\x88\xb6\xe6\x8e\xa5\xe5\x8f\xa3\xe6\x9c\x8d\xe5\x8a\xa1\xe5\x99\xa8</AlarmRes><EventTime>2023-09-19 10:32:49</EventTime></ALARMSTART>'
2023-09-19 10:32:49,371 140176451651392 heratbeat.py:106 ERROR cdesk_nginx1 is not running.

• socket 接收消息

[devops@my-dev ABC]$ ./sock.py 
服务器已启动，等待客户端连接...
客户端 ('127.0.0.1', 41400) 已连接
收到来自 ('127.0.0.1', 41400) 的数据： <ALARMSTART><SystemName>ccc-test-001</SystemName><AlarmID>1695090684048</AlarmID><AlarmEquipment>nginx</AlarmEquipment><AlarmRes>定制接口服务器</AlarmRes><EventTime>2023-09-19 10:31:24</EventTime></ALARMSTART>
客户端 ('127.0.0.1', 41402) 已连接
收到来自 ('127.0.0.1', 41402) 的数据： <ALARMSTART><SystemName>ccc-test-001</SystemName><AlarmID>1695090684049</AlarmID><AlarmEquipment>mysqld</AlarmEquipment><AlarmRes>定制接口服务器</AlarmRes><EventTime>2023-09-19 10:31:24</EventTime></ALARMSTART>