Python scrapy爬取小说代码案例详解

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders.crawl import Rule, CrawlSpider

class BaiduSpider(CrawlSpider):
  name = 'qiushibaike'
  allowed_domains = ['qiushibaike.com']
  start_urls = ['https://www.qiushibaike.com/text/']#启始页面
#        
  rules= (
    Rule(LinkExtractor(restrict_xpaths=r'//a[@class="contentHerf"]'),callback='parse_item',follow=True),
    Rule(LinkExtractor(restrict_xpaths=r'//ul[@class="pagination"]/li/a'),follow=True)
  )

  def parse_item(self, response):
    title=response.xpath('//h1[@class="article-title"]/text()').extract_first().strip() #标题
    time=response.xpath(' //span[@class="stats-time"]/text()').extract_first().strip() #发布时间
    content=response.xpath('//div[@class="content"]/text()').extract_first().replace('　　','\n') #内容
    score=response.xpath('//i[@class="number"]/text()').extract_first().strip() #好笑数

    yield({"title":title,"content":content,"time":time,"score":score});

class QiushibaikePipeline:
  def open_spider(self,spider):#启动爬虫中调用
    self.f=open("xiaoshuo.txt","w",encoding='utf-8')
  def process_item(self, item, spider):
    info=item.get("title")+"\n"+ item.get("time")+" 好笑数"+item.get("score")+"\n"+ item.get("content")+'\n'
    self.f.write(info+"\n")
    self.f.flush()
  def close_spider(self,spider):#关闭爬虫中调用
    self.f.close()

ITEM_PIPELINES = {
  'qiushibaike.pipelines.QiushibaikePipeline': 300,
}

from scrapy.cmdline import execute
execute('scrapy crawl qiushibaike'.split())