scrapyip池(ip route命令)

from scrapy import signals

class MyscrapyDownloaderMiddleware(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.

    @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)

 import logging
from twisted.internet import defer
from twisted.internet.error import TimeoutError, DNSLookupError, \
        ConnectionRefusedError, ConnectionDone, ConnectError, \
        ConnectionLost, TCPTimedOutError
from twisted.web.client import ResponseFailed

from scrapy.exceptions import NotConfigured
from scrapy.utils.response import response_status_message
from scrapy.core.downloader.handlers.http11 import TunnelError
from scrapy.utils.python import global_object_name

logger = logging.getLogger(__name__)


class RetryMiddleware(object):

    # IOError is raised by the HttpCompression middleware when trying to
    # decompress an empty response
    EXCEPTIONS_TO_RETRY = (defer.TimeoutError, TimeoutError, DNSLookupError,
                           ConnectionRefusedError, ConnectionDone, ConnectError,
                           ConnectionLost, TCPTimedOutError, ResponseFailed,
                           IOError, TunnelError)

    def __init__(self, settings):
        if not settings.getbool('RETRY_ENABLED'):
            raise NotConfigured
        self.max_retry_times = settings.getint('RETRY_TIMES')
        self.retry_http_codes = set(int(x) for x in settings.getlist('RETRY_HTTP_CODES'))
        self.priority_adjust = settings.getint('RETRY_PRIORITY_ADJUST')

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

    def process_response(self, request, response, spider):
        if request.meta.get('dont_retry', False):
            return response
        if response.status in self.retry_http_codes:
            reason = response_status_message(response.status)
            return self._retry(request, reason, spider) or response
        return response
    
	# 捕获错误信息触发执行
    def process_exception(self, request, exception, spider):
        # 如果错误属于捕获列表内的错误，并且，请求元信息内设置的配置为设置重启 - 处理错误请求
        if isinstance(exception, self.EXCEPTIONS_TO_RETRY) \
                and not request.meta.get('dont_retry', False):
            return self._retry(request, exception, spider)

    def _retry(self, request, reason, spider):
        # 重试次数获取
        retries = request.meta.get('retry_times', 0) + 1
		# 最多重试次数
        retry_times = self.max_retry_times
        if 'max_retry_times' in request.meta:
            retry_times = request.meta['max_retry_times']

        stats = spider.crawler.stats
        # 若重试次数未达到最多重试次数
        if retries <= retry_times:
            logger.debug("Retrying %(request)s (failed %(retries)d times): %(reason)s",
                         {'request': request, 'retries': retries, 'reason': reason},
                         extra={'spider': spider})
            retryreq = request.copy()
            retryreq.meta['retry_times'] = retries
            retryreq.dont_filter = True
            retryreq.priority = request.priority + self.priority_adjust

            if isinstance(reason, Exception):
                reason = global_object_name(reason.__class__)

            stats.inc_value('retry/count')
            stats.inc_value('retry/reason_count/%s' % reason)
            # 返回request对象 （属于 process_exception 返回）
            return retryreq
        # 否则不进行重试
        else:
            stats.inc_value('retry/max_reached')
            logger.debug("Gave up retrying %(request)s (failed %(retries)d times): %(reason)s",
                         {'request': request, 'retries': retries, 'reason': reason},
                         extra={'spider': spider})

import scrapy
from bs4 import BeautifulSoup

from myscrapy.items import IpSpiderItem


class IpSpider(scrapy.Spider):
    name = 'ipspider'

    # 替代start_urls
    def start_requests(self):
        # dont_filter=False 开启去重功能（爬过的url不再爬取），需要 setting 内的配置
        # 根据爬取页规则，指定爬取页数
        for page in range(1, 5):
            yield scrapy.Request('https://www.kuaidaili.com/free/inha/%s/' % page, self.parse, dont_filter=True, )

    def parse(self, response):
        body = str(response.body, encoding='utf-8')
        ippool = BeautifulSoup(body, 'lxml')
        iptable = ippool.find('table', class_='table table-bordered table-striped')
        ip_trs = iptable.tbody.find_all('tr')
        for tr in ip_trs:
            ip = tr.find('td', attrs={'data-title': 'IP'}).text
            port = tr.find('td', attrs={'data-title': 'PORT'}).text
            print('http://%s:%s' % (ip, port))
            item = IpSpiderItem()
            item['ip'] = 'http://%s:%s' % (ip, port)
            yield item

 import pymongo
import random
from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware

class MyProxyMiddleware(HttpProxyMiddleware):
    def process_request(self, request, spider):
        conn = pymongo.MongoClient(spider.settings.get('MONGO_URI'))
        db = conn[spider.settings.get('MONGO_DATABASE')]
        collection = db['ips']
        ip = random.choice([obj for obj in collection.find()])
        request.meta['proxy'] = ip['ip']