Python的爬虫框架scrapy用21行代码写一个爬虫

04月07日

4月7日 淘金币淘里程领取京东签到已结束
发布日期: 2017-04-07 | 分类: 虚拟币 | 浏览:125177
淘金币一键领取 http://021.tw/t/ https://www.chaidu.com/App/Web/Taobao-Coin/ 【电脑端30金币】 https://taojinbi.taobao.com/inde ... auto_take=true 【手机端30金币】 http://h5.m.taobao...

class DemoItem(scrapy.Item):
 id = scrapy.Field()
 title = scrapy.Field()
 href = scrapy.Field()
 content = scrapy.Field()

# -*- coding: utf-8 -*-
import scrapy
from demo.items import DemoItem
from scrapy.http import Request
class TestSpider(scrapy.Spider):
 #定义爬虫的名字和需要爬取的网址
 name = "test"
 allowed_domains = ["www.abckg.com"]
 start_urls = ['http://www.abckg.com/']
 def parse(self, response):
 for resp in response.css('.post'):
  #实例化item
  item = DemoItem()
  #把获取到的内容保存到item内
  item['href'] = resp.css('h2 a::attr(href)').extract()
  item['title'] = resp.css('h2 a::text').extract()
  item['content'] = resp.css('.intro p::text').extract()
  yield item
  
 #下面是多页面的爬取方法
 urls = response.css('.pageinfo a::attr(href)').extract()
 for url in urls:
  yield Request(url, callback=self.parse)
 categorys = response.css('.menu li a::attr(href)').extract()
 for ct in categorys:
  yield Request(ct, callback=self.parse)

FEED_EXPORT_ENCODING = 'utf-8'

scrapy crawl test -o items.json