在很多时候,我们在写爬虫的时候需要去修改爬虫的请求头,那么话不多说,下面代码开始
在middlewares.py文件中创建请求头的列表,使用random函数来随机调用使用哪个请求头:
import random
class UserAgentDownloadMiddleware(object):
'''
下载器中间件
在发送下载之前要设置请求头
'''
USER_AGENTS = [
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36',
'Mozilla/5.0 (X11; Linux i686; rv:64.0) Gecko/20100101 Firefox/64.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:64.0) Gecko/20100101 Firefox/64.0',
]
def process_request(self, request, spider):
user_agent = random.choice(self.USER_AGENTS)
request.headers['User-Agent'] = user_agent