爬虫练手：使用IP代理池，爬取微信文章信息

爬取对象：利用搜狗的微信搜索功能，爬取微信文章信息。
网址：http://weixin.sogou.com/
python版本：python3.5
注：因搜狗防爬机制较为严格，国内的免费代理IP一般均无效，所以本案例中使用的代理IP均无效，本博文只是为了记录和演示代理IP池的用法。

源代码

items.py

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

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class WeixinItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    #标题
    title = scrapy.Field()
    #链接
    link = scrapy.Field()
    #简介
    desc = scrapy.Field()

weixin_article.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from weixin.items import WeixinItem

class WeixinArticleSpider(scrapy.Spider):
    name = "weixin_article"
    allowed_domains = ["sogou.com"]
    start_urls = ['http://sogou.com/']

    def parse(self, response):
        #构造关键词
        key='python'
        for i in range(1,3):

            thispage = "http://weixin.sogou.com/weixin?query=python&_sug_type_=&sut=861&lkt=7%2C1483249474246%2C1483249475122&_sug_=y&type=2&sst0=1483249475225&page=" + str(i) + "&ie=utf8&w=01019900&dr=1"
            print("第" + str(i) + "次爬取，网址为:" + thispage)
            yield Request(url=thispage,callback=self.page)

    def page(self,response):
        print("在处理搜索列表页,正在爬的列表页:" + response.url)
        item = WeixinItem()
        item["title"] = response.xpath("//div[@class='txt-box']/h3/a/text()").extract()
        item["link"] = response.xpath("//div[@class='txt-box']/h3/a/@href").extract()
        item["desc"] = response.xpath("//p[@class='txt-info']/text()").extract()

        yield item

pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


class WeixinPipeline(object):
    def process_item(self, item, spider):
        for i in range(0,len(item["title"])):
            print("第%s篇文章的信息是："%i)
            print(item["title"][i])
            print(item["link"][i])
            print(item["desc"][i])
            print("------------------")
        return item

middlewares.py

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

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

from scrapy import signals
import random
from weixin.settings import IPPOOL
#导入官方代理IP的一个模块
from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware

class IPPOOLS(HttpProxyMiddleware):
    def __init__(self,ip=''):
        self.ip = ip

    def process_request(self, request, spider):
        thisip = random.choice(IPPOOL)
        print("当前使用的IP是：" + thisip["ipaddr"])
        try:
            request.meta["proxy"] = "http://" + thisip["ipaddr"]
        except Exception as e:
            pass


class WeixinSpiderMiddleware(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(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(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(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(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)

settings.py

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

# Scrapy settings for weixin project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'weixin'

SPIDER_MODULES = ['weixin.spiders']
NEWSPIDER_MODULE = 'weixin.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'weixin (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'weixin.middlewares.WeixinSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    # 'weixin.middlewares.MyCustomDownloaderMiddleware': 543,
#     'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware':123,
#     'weixin.middlewares.IPPOOLS':125,
# }

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'weixin.pipelines.WeixinPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

IPPOOL = [
    {"ipaddr":"110.73.33.207:6673"},
    {"ipaddr":"122.89.138.20:6675"},
    {"ipaddr":"110.72.20.245:6673"},
]