spider/elabSpider/middlewares.py

# -*- coding: utf-8 -*-

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

from scrapy.downloadermiddlewares.retry import RetryMiddleware
from scrapy.utils.response import response_status_message
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
from scrapy import signals
from scrapy.conf import settings
import logging
import time
import fake_useragent


class ElabspiderSpiderMiddleware(object):
    # 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, dict 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 Response, dict
        # 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


class ElabspiderDownloaderMiddleware(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

        # proxy_user_pass = settings['PROXY_IDENTIFY'] + ':' + settings['PROXY_SECRETKEY']
        # encoded_proxy_pass = base64.encodebytes(bytes(proxy_user_pass.encode(encoding='utf-8')))

        #TODO: 开关代理
        # logging.info(msg='process request url: ' + request._url)
        # request.meta['proxy'] = settings['PROXY_HOST'] + ':' + settings['PROXY_PORT']
        # request.headers['Proxy-Authorization'] = 'Basic ' + 'SDVQMDI5OU44MzBBQzlDRDo1MTZGOTVEMDNFQjFGMDI2'
        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
        logging.info(msg='receive response status url: ' + response._url + ' status: ' + str(response.status))
        # if response.status != 200:
        #     logging.debug('retry url: ' + response._url)
        #     # proxy = self.get_random_proxy()
        #     # request.meta['proxy'] = proxy
        #     return request
        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)

    # def get_random_proxy(self):
    #     while 1:
    #         with open('proxies.txt', 'r') as f:
    #             proxies = f.readlines()
    #         if proxies:
    #             break
    #         else:
    #             time.sleep(1)
    #     proxy = random.choice(proxies).strip()
    #     return proxy


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()
            time.sleep(10)  # 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


class UserAgent(UserAgentMiddleware):

    def __init__(self, user_agent=''):
        self.user_agent = user_agent

    def process_request(self, request, spider):
        # agent = random.choice(self.user_agent_list)
        agent = fake_useragent.UserAgent(path=settings['USER_AGENT_PATH']).random
        if agent:
            # print("********Current UserAgent:%s************" % agent)
            # log(level=logging.DEBUG, msg='Current UserAgent: ' + agent)
            request.headers.setdefault('User-Agent', agent)