爬虫--使用scrapy爬取糗事百科并在txt文件中持久化存储

工程目录结构

　spiders下的first源码

　　

# -*- coding: utf-8 -*-
import scrapy
from  firstblood.items  import firstblooditem
class firstspider(scrapy.spider):
    #爬虫文件的名称
    #当有多个爬虫文件时，可以通过名称定位到指定的爬虫文件
    name = 'first'
    #allowed_domains 允许的域名 跟start_url互悖
    #allowed_domains = ['www.xxx.com']
    #start_url 请求的url列表，会被自动的请求发送
    start_urls = ['https://www.qiushibaike.com/text/']
    def parse(self, response):
        '''
        解析请求的响应
        可以使用正则，xpath  ,因为scrapy 集成了xpath，建议使用xapth
        解析得到一个selector
        :param response:
        :return:
        '''
        all_data = []
        div_list=response.xpath('//div[@id="content-left"]/div')
        for div in div_list:
            #author=div.xpath('./div[1]/a[2]/h2/text()')#author 拿到的不是之前理解的源码数据而
            # 是selector对象,我们只需将selector类型对象下的data对象拿到即可
            #author=author[0].extract()
            #如果存在匿名用户时，将会报错（匿名用户的数据结构与登录的用户名的数据结构不一样）
            ''' 改进版'''

            author = div.xpath('./div[1]/a[2]/h2/text()| ./div[1]/span[2]/h2/text()')[0].extract()
            content=div.xpath('.//div[@class="content"]/span//text()').extract()
            content=''.join(content)
            #print(author+':'+content.strip(' \n \t '))


        #基于终端的存储
        #     dic={
        #         'author':author,
        #         'content':content
        #     }
        #     all_data.append(dic)
        # return all_data
        #持久化存储的两种方式
            #1 基于终端指令：parse方法有一个返回值
              #scrapy crawl first -o qiubai.csv --nolog
              #终端指令只能存储json,csv,xml等格式文件
            #2基于管道
            item = firstblooditem()#循环里面，每次实例化一个item对象
            item['author']=author
            item['content']=content
            yield item #将item提交给管道

items文件

　　

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

# define here the models for your scraped items
#
# see documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class firstblooditem(scrapy.item):
    # define the fields for your item here like:
    # name = scrapy.field()
    #item类型对象 万能对象，可以接受任意类型属性，字符串，json等
    author = scrapy.field()
    content = scrapy.field()

pipeline文件

　　

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

# define your item pipelines here
#
# don't forget to add your pipeline to the item_pipelines setting
# see: https://doc.scrapy.org/en/latest/topics/item-pipeline.html


#只要涉及持久化存储的相关操作代码都需要写在该文件种
class firstbloodpipeline(object):
    fp=none
    def open_spider(self,spider):
        print('开始爬虫')
        self.fp=open('./qiushibaike.txt','w',encoding='utf-8')
    def process_item(self, item, spider):
        '''
        处理item
        :param item:
        :param spider:
        :return:
        '''
        self.fp.write(item['author']+':'+item['content'])
        print(item['author'],item['content'])
        return item
    def close_spider(self,spider):
        print('爬虫结束')
        self.fp.close()

setting文件

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

# scrapy settings for firstblood project
#
# for simplicity, this file contains only settings considered important or
# commonly used. you can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

bot_name = 'firstblood'

spider_modules = ['firstblood.spiders']
newspider_module = 'firstblood.spiders'


# crawl responsibly by identifying yourself (and your website) on the user-agent
user_agent = 'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.77 safari/537.36'

# obey robots.txt rules
#默认为true ，改为false  不遵从robots协议  反爬
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 https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#spider_middlewares = {
#    'firstblood.middlewares.firstbloodspidermiddleware': 543,
#}

# enable or disable downloader middlewares
# see https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#downloader_middlewares = {
#    'firstblood.middlewares.firstblooddownloadermiddleware': 543,
#}

# enable or disable extensions
# see https://doc.scrapy.org/en/latest/topics/extensions.html
#extensions = {
#    'scrapy.extensions.telnet.telnetconsole': none,
#}

# configure item pipelines
# see https://doc.scrapy.org/en/latest/topics/item-pipeline.html
item_pipelines = {
   'firstblood.pipelines.firstbloodpipeline': 300,#300 为优先级
}

# enable and configure the autothrottle extension (disabled by default)
# see https://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 https://doc.scrapy.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'