python实现批量监控网站

时间:2022-09-07 14:39:17

最近又新上了一部分站点,随着站点的增多,管理复杂性也上来了,俗话说:人多了不好带,我发现站点多了也不好管,因为这些站点里有重要的也有不重要的,重要核心的站点当然就管理的多一些,像一些万年都不出一次问题的,慢慢就被自己都淡忘了,冷不丁那天出个问题,还的手忙脚乱的去紧急处理,所以规范的去管理这些站点是很有必要的,今天我们就做第一步,不管大站小站,先统一把监控做起来,先不说业务情况,最起码那个站点不能访问了,要第一时间报出来,别等着业务方给你反馈,就显得我们不够专业了,那接下来我们看看如果用python实现多网站的可用性监控,脚本如下:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
#!/usr/bin/env python
 
 
import pickle, os, sys, logging
from httplib import HTTPConnection, socket
from smtplib import SMTP
 
def email_alert(message, status):
  fromaddr = 'xxx@163.com'
  toaddrs = 'xxxx@qq.com'
  
  server = SMTP('smtp.163.com:25')
  server.starttls()
  server.login('xxxxx', 'xxxx')
  server.sendmail(fromaddr, toaddrs, 'Subject: %s\r\n%s' % (status, message))
  server.quit()
 
def get_site_status(url):
  response = get_response(url)
  try:
    if getattr(response, 'status') == 200:
      return 'up'
  except AttributeError:
    pass
  return 'down'
    
def get_response(url):
  try:
    conn = HTTPConnection(url)
    conn.request('HEAD', '/')
    return conn.getresponse()
  except socket.error:
    return None
  except:
    logging.error('Bad URL:', url)
    exit(1)
    
def get_headers(url):
  response = get_response(url)
  try:
    return getattr(response, 'getheaders')()
  except AttributeError:
    return 'Headers unavailable'
 
def compare_site_status(prev_results):
  
  def is_status_changed(url):
    status = get_site_status(url)
    friendly_status = '%s is %s' % (url, status)
    print friendly_status
    if urlin prev_resultsand prev_results[url] != status:
      logging.warning(status)
      email_alert(str(get_headers(url)), friendly_status)
    prev_results[url] = status
 
  return is_status_changed
 
def is_internet_reachable():
  if get_site_status('www.baidu.com') == 'down' and get_site_status('www.sohu.com') == 'down':
    return False
  return True
  
def load_old_results(file_path):
  pickledata = {}
  if os.path.isfile(file_path):
    picklefile = open(file_path, 'rb')
    pickledata = pickle.load(picklefile)
    picklefile.close()
  return pickledata
  
def store_results(file_path, data):
  output = open(file_path, 'wb')
  pickle.dump(data, output)
  output.close()
  
def main(urls):
  logging.basicConfig(level=logging.WARNING, filename='checksites.log',
      format='%(asctime)s %(levelname)s: %(message)s',
      datefmt='%Y-%m-%d %H:%M:%S')
  
  pickle_file = 'data.pkl'
  pickledata = load_old_results(pickle_file)
  print pickledata
    
  if is_internet_reachable():
    status_checker = compare_site_status(pickledata)
    map(status_checker, urls)
  else:
    logging.error('Either the world ended or we are not connected to the net.')
    
  store_results(pickle_file, pickledata)
 
if __name__ == '__main__':
  main(sys.argv[1:])

脚本核心点解释:

1、getattr()是python的内置函数,接收一个对象,可以根据对象属性返回对象的值。

2、compare_site_status()函数是返回的是一个内部定义的函数。

3、map(),需要2个参数,一个是函数,一个是序列,功能就是将序列中的每个元素应用函数方法。