爬虫--使用scrapy爬取糗事百科并在txt文件中持久化存储

# -*- 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

# -*- 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()

# -*- 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()

# -*- 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‘