scrapy 切换ip和useragent

scrapy middleware设置，注意设置setting文件

DOWNLOADER_MIDDLEWARES = {
   '爬虫名字.middlewares.RandomUserAgentMiddlware': 543,
   'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
}

middlewares.py文件编写类RandomUserAgentMiddlware

from scrapy import signals

from fake_useragent import UserAgent


class RandomUserAgentMiddlware(object):
    '''
    随机更换user-agent
    模仿并替换site-package/scrapy/downloadermiddlewares源代码中的
    useragent.py中的UserAgentMiddleware类
    '''

    def __init__(self, crawler):
        super(RandomUserAgentMiddlware, self).__init__()
        self.ua = UserAgent()
        # 可读取在settings文件中的配置，来决定开源库ua执行的方法，默认是random，也可是ie、Firefox等等
        self.ua_type = crawler.settings.get("RANDOM_UA_TYPE", "random")

    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler)

    # 更换用户代理逻辑在此方法中
    def process_request(self, request, spider):
        def get_ua():
            return getattr(self.ua, self.ua_type)

        print(get_ua())
        request.headers.setdefault('User-Agent', get_ua())

ip同理

class IpProxyDownloadMiddleware(object):
    '''
    随机更换IP
    '''

    def __init__(self, crawler):
        super(IpProxyDownloadMiddleware, self).__init__()

    def getIP(self, ):
        num = 1
        while True:
            proxy = requests.get('http://127.0.0.1:5010/get/?type=http').json()['proxy']
            # 验证IP是否可用
            url = "http://ip-api.com/json/" + proxy.split(":")[0] + "?lang=zh-CN"
            try:
                data = requests.get(url, proxies={"http": proxy}, timeout=10, headers={
                    'Connection': 'close'})
                print('scrapy第%s次尝试验证代理ip %s' % (num, proxy))
                num += 1
                if data.status_code == 200  :
                    print('scrapy初始化代理ip %s成功' % proxy)
                    break
            except  :
                traceback.print_exc()
                print('重试')
                 
        return 'http://' + proxy

    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler)

    # 更换用户代理逻辑在此方法中
    def process_request(self, request, spider):
        current_ip=random.choice(['http://45.144.3.208:59785' ])#这个ip不会允许scrapy链接
        request.meta['proxy'] = current_ip #self.getIP()
        print("scrapy.request:",current_ip)

    def process_response(self, request, response, spider):
        return response