429 Too Many Requests (太多请求)

当你需要限制客户端请求某个服务的数量,也就是限制请求速度时,该状态码就会非常有用。在此之前,有一些类似的状态码。例如“509 Bandwidth Limit Exceeded”。

如果你希望限制客户端对服务的请求数,可使用 429 状态码,同时包含一个 Retry-After 响应头用于告诉客户端多长时间后可以再次请求服务。

middlewares.py    # 当状态码是429的时候  爬虫暂停60秒 在爬取

from scrapy import signals
import time
from scrapy.downloadermiddlewares.retry import RetryMiddleware
from scrapy.utils.response import response_status_message


class TooManyRequestsRetryMiddleware(RetryMiddleware):

    def __init__(self, crawler):
        super(TooManyRequestsRetryMiddleware, self).__init__(crawler.settings)
        self.crawler = crawler

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

    def process_response(self, request, response, spider):
        if request.meta.get('dont_retry', False):
            return response
        elif response.status == 429:
            self.crawler.engine.pause()
            print("速度太快  暂停60秒")
            time.sleep(60)  # If the rate limit is renewed in a minute, put 60 seconds, and so on.
            self.crawler.engine.unpause()
            reason = response_status_message(response.status)
            return self._retry(request, reason, spider) or response
        elif response.status in self.retry_http_codes:
            reason = response_status_message(response.status)
            return self._retry(request, reason, spider) or response
        return response

settings.py

DOWNLOADER_MIDDLEWARES = {   # 开启暂停中间件
   'steam_market.middlewares.TooManyRequestsRetryMiddleware': 543,
}

RETRY_HTTP_CODES = [429, 500, 403]  # 这个状态重试


import random

DOWNLOAD_DELAY = random.random() + random.random() + random.random()
RANDOMIZE_DOWNLOAD_DELAY = True   # 发完一个请求 随机暂停一下 在发下一个请求