五大核心组件、代理池

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

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

# class Midllepro1SpiderMiddleware(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 Request, 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
#
# def spider_opened(self, spider):
# spider.logger.info('Spider opened: %s' % spider.name)

# 定义UA池:
user_agent_list = [
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "
"(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "
"(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "
"(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "
"(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "
"(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "
"(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "
"(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
"(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "
"(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "
"(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]


class Midllepro1DownloaderMiddleware(object):
# 拦截正常请求:
def process_request(self, request, spider):
# 进行UA伪装:
request.headers["User-Agent"] = random.choice(user_agent_list)
# print(request.headers["User-Agent"])
# # 挂高匿的免费代理ip:
# request.meta["proxy"] = "http://39.137.95.74:80"
# print(request.meta["proxy"])
return None

# 拦截所有的响应:
def process_response(self, request, response, spider):
return response

# 拦截发生异常的请求对象:
def process_exception(self, request, exception, spider):
print(request)
return request # 将修正后的正常请求对象重新发送

# def spider_opened(self, spider):
# spider.logger.info('Spider opened: %s' % spider.name)
原文地址:https://www.cnblogs.com/zhang-da/p/12432103.html