newsspider/decspider/middlewares.py

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
from .myutils import ProxyPool
from .settings import USERNAME, PASSWORD
from faker import Faker


class DecspiderSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @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_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

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


class DecspiderDownloaderMiddleware:
    # 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.

    @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
        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)
    

class ProxyMiddleware:
    def __init__(self):
        # 初始化代理列表和每个代理的失败计数
        self.proxy_pool = ProxyPool()
        self.proxy_failures = {proxy: 0 for proxy in self.proxy_pool.proxy_list}
        self.fake = Faker()


    def process_request(self, request, spider):
        # 为每个请求随机选择一个代理
        proxy = self.proxy_pool.get_one()
        if proxy not in self.proxy_failures:
            self.proxy_failures[proxy] = 0 
        request.meta['proxy'] = "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": USERNAME, "pwd": PASSWORD, "proxy": proxy}
        ua = self.fake.user_agent()
        request.headers['User-Agent'] = ua
        spider.logger.info(f'Using proxy: {proxy}\nUsing UA: {ua}')


    def process_response(self, request, response, spider):
        # 如果响应正常，返回响应
        if response.status in [200, 301, 302]:
            return response
        # 如果响应异常，处理失败计数
        else:
            self._handle_proxy_failure(request.meta['proxy'], spider)
            # 重新调度请求
            return request


    def process_exception(self, request, exception, spider):
        # 处理发生异常的请求
        self._handle_proxy_failure(request.meta['proxy'], spider)
        # 重新调度请求
        return request


    def _handle_proxy_failure(self, http_proxy, spider):
        # 增加指定代理的失败计数
        proxy = http_proxy.split('@')[-1][:-1]
        self.proxy_failures[proxy] += 1
        spider.logger.error(f'Proxy {proxy} failed, failure count: {self.proxy_failures[proxy]}')

        # 如果某个代理失败次数达到2次，从列表中移除
        if self.proxy_failures[proxy] >= 2:
            self.proxy_pool.remove(proxy)
            del self.proxy_failures[proxy]
            spider.logger.error(f'Removed proxy {proxy} after consecutive failures.', level=spider.logger.ERROR)


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