scrapy 避免被ban

1、settings.py

COOKIES_ENABLED = False

DOWNLOAD_DELAY = 3

ROBOTSTXT_OBEY = False

ip代理池设置

IPPOOL = [{'ipadder':'1.1.1.1'},
        {'ipadder':'2.1.1.1'},
        {'ipadder': '1.3.1.1'},
        {'ipadder': '1.1.1.4'},
        ]

DOWNLOADER_MIDDLEWARES = {
   #'Autopjt.middlewares.MyCustomDownloaderMiddleware': 543,
   'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware':123,
   'Autopjt.middlewares.IPPOOLS':125,
}

2、middlewares.py

import random
from Autopjt.settings import IPPOOL
from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware

class IPPOOLS(HttpProxyMiddleware):
    def __init__(self,ip=''):
        self.ip = ip
    def process_request(self, request, spider):
        thisip = random.choice(IPPOOL)
        # 将对应的IP实际添加为具体代理，用该ip进行爬取
        request.meta['proxy']='http://' + thisip['ipaddr']

 

UA池

UAPOOL = ['Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.103 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.104 Safari/537.36',]

DOWNLOADER_MIDDLEWARES = {
   #'Autopjt.middlewares.MyCustomDownloaderMiddleware': 543,
   #'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware':123,
   #'Autopjt.middlewares.IPPOOLS':125,
   'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware':2,
   'Autopjt.middlewares.Uamid':1
}

middlewares.py

import random
from Autopjt.settings import UAPOOL
from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware

class Uamid(UserAgentMiddleware):
    def __init__(self,ua=''):
        self.ua = ua
    def process_request(self, request, spider):
        thisua = random.choice(UAPOOL)
        request.headers.setdefault('User-Agent',thisua)