python爬虫scrapy框架之增量式爬虫的示例代码

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from redis import Redis
from increment2_Pro.items import Increment2ProItem
import hashlib
class QiubaiSpider(CrawlSpider):
  name = 'qiubai'
  # allowed_domains = ['www.xxx.com']
  start_urls = ['https://www.qiushibaike.com/text/']

  rules = (
    Rule(LinkExtractor(allow=r'/text/page/\d+/'), callback='parse_item', follow=True),
  )

  def parse_item(self, response):

    div_list = response.xpath('//div[@class="article block untagged mb15 typs_hot"]')
    conn = Redis(host='127.0.0.1',port=6379)
    for div in div_list:
      item = Increment2ProItem()
      item['content'] = div.xpath('.//div[@class="content"]/span//text()').extract()
      item['content'] = ''.join(item['content'])
      item['author'] = div.xpath('./div/a[2]/h2/text() | ./div[1]/span[2]/h2/text()').extract_first()
      
			# 将当前爬取的数据做哈希唯一标识(数据指纹)
      sourse = item['content']+item['author']
      hashvalue = hashlib.sha256(sourse.encode()).hexdigest()

      ex = conn.sadd('qiubai_hash',hashvalue)
      if ex == 1:
        yield item
      else:
        print('没有可更新的数据可爬取')


    # item = {}
    #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
    #item['name'] = response.xpath('//div[@id="name"]').get()
    #item['description'] = response.xpath('//div[@id="description"]').get()
    # return item

from redis import Redis
class Increment2ProPipeline(object):
  conn = None
  def open_spider(self,spider):
    self.conn = Redis(host='127.0.0.1',port=6379)
  def process_item(self, item, spider):
    dic = {
      'author':item['author'],
      'content':item['content']
    }
    self.conn.lpush('qiubaiData',dic)
    print('爬取到一条数据,正在入库......')
    return item