scrapy爬虫-代理IP中间件

class ProxyDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.
    def __init__(self):
        self.request_proxy_url = ""
        self.IpPool = Queue()  # 维护代理IP池
        self.Ipset = set()  # 记录已经取到的代理IP
        self.request_proxry(number=5)

    def request_proxry(self, number=5):
        """
        :param number: the number of getting proxies
        :return:
        """
        if self.IPportQueue.qsize() > 8:
            return
        url = 'https://dps.kdlapi.com/api/getdps/?orderid=987658645908252&num=%d&pt=1&dedup=1&format=json&sep=1' % number
        # lock.acquire()
        r = requests.get(url)
        # lock.release()
        dc = r.json()
        # print(dc,'123')
        for item in dc['data']['proxy_list']:
            if item in self.IPset:
                continue
            self.IPportQueue.put({'ipport': item, 'useTimes': 0})
            self.IPset.add(item)
            print(item, '+++++++++++++++++')

    def get_proxy_ip(self):
        item = self.IpPool.get()
        item["useTimes"] += 1
        if item["useTimes"] > 10:
            self.request_proxry(number=2)
        else:
            self.IpPool.put(item)
        return "https://" + item["ip_port"]

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        request.meta["proxy"] = self.get_proxy_ip()

        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)