python middleware_Python Django Middleware中间件限制IP访问频率及判断搜索引擎爬虫

1、中间件代码import time

from django.utils.deprecation import MiddlewareMixin

MAX_REQUEST_PER_SECOND=2 #每秒访问次数

class RequestBlockingMiddleware(MiddlewareMixin):

def process_request(self,request):

now=time.time()

request_queue = request.session.get('request_queue',[])

if len(request_queue) < MAX_REQUEST_PER_SECOND:

request_queue.append(now)

request.session['request_queue']=request_queue

else:

time0=request_queue[0]

if (now-time0)<1:

time.sleep(5)

request_queue.append(time.time())

request.session['request_queue']=request_queue[1:]

2、settings.py配置app.middleware.RequestBlockingMiddleware中间件#启用RequestBlocking中间件

IDDLEWARE = [

'django.middleware.security.SecurityMiddleware',

'django.contrib.sessions.middleware.SessionMiddleware',

'django.middleware.common.CommonMiddleware',

'django.middleware.csrf.CsrfViewMiddleware',

'app.middleware.RequestBlockingMiddleware', #在sessions之后，auth之前

'django.contrib.auth.middleware.AuthenticationMiddleware',

'django.contrib.messages.middleware.MessageMiddleware',

'django.middleware.clickjacking.XFrameOptionsMiddleware',

]

3、判断IP是否是搜索引擎import socket

def getHost(ip):

try:

result=socket.gethostbyaddr(ip)

if result:

return result[0]

return None

except socket.herror as e:

pass

return None

>>>getHost("203.208.60.11")

'crawl-203-208-60-11.googlebot.com'

#根据返回的结果就可以判断是否为搜索引擎

注意：python2 和 python3 处理 except 子句的语法有点不同，需要注意；

1)Python2try:

print (1/0)

except ZeroDivisionError, err:　　　　　　# , 加原因参数名称

print ('Exception: ', err)

2)Python3try:

print (1/0)

except ZeroDivisionError as err: # as 加原因参数名称

print ('Exception: ', err)