1.写中间件RandomUserAgentMiddleware
2.代理池 列表
3.注册中间件.
class RandomUserAgentMiddleware(object):
'''
设置User-Agent
'''
def __init__(self, user_agent):
self.user_agent = user_agent
@classmethod
def from_crawler(cls, crawler):
return cls(
user_agent=crawler.settings.get('MY_USER_AGENT')
)
def process_request(self, request, spider):
agent = random.choice(self.user_agent)
# print('agent-----%s' %agent)
request.headers['User-Agent'] = agent
return None
MY_USER_AGENT = [
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:55.0) Gecko/20100101 Firefox/55.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:55.0) Gecko/20100101 Firefox/54.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:55.0) Gecko/20100101 Firefox/53.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:55.0) Gecko/20100101 Firefox/52.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:55.0) Gecko/20100101 Firefox/50.0",
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.2306.400 QQBrowser/9.5.10648.400",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
]
