爬取小说

spider

  1. import scrapy
  2. from xiaoshuo.items import XiaoshuoItem
  5. class XiaoshuoSpiderSpider(scrapy.Spider):
  6.     name = 'xiaoshuo_spider'
  7.     allowed_domains = ['zy200.com']
  8.     url = 'http://www.zy200.com/5/5943/'
  9.     start_urls = [url + '11667352.html']
  11.     def parse(self, response):
  12.         info = response.xpath("/html/body/div[@id='content']/text()").extract()
  13.         href = response.xpath("//div[@class='zfootbar']/a[3]/@href").extract_first()
  14.         xs_item = XiaoshuoItem()
  15.         xs_item['content'] = info
  16.         yield xs_item
  18.         if href != 'index.html':
  19.             new_url = self.url + href
  20.             yield scrapy.Request(new_url, callback=self.parse)

items

  1. import scrapy
  4. class XiaoshuoItem(scrapy.Item):
  5.     # define the fields for your item here like:
  6.     content = scrapy.Field()
  7.     href = scrapy.Field()

pipeline

  1. class XiaoshuoPipeline(object):
  2.     def __init__(self):
  3.         self.filename = open("dp1.txt", "w", encoding="utf-8")
  5.     def process_item(self, item, spider):
  6.         content = item["title"] + item["content"] + '\n'
  7.         self.filename.write(content)
  8.         self.filename.flush()
  9.         return item
  11.     def close_spider(self, spider):
  12.         self.filename.close()