爬虫实例1-爬取新闻列表和发布时间

scrapy  startproject shop

import scrapy

class  ShopItem(scrapy.Item):

    title = scrapy.Field()

    time = scrapy.Field()

#  -*-coding:UTF-8-*-

import scrapy

from shop.items  import ShopItem

class  shopSpider(scrapy.Spider):

    name = "shop"

    allowed_domains =  ["news.xxxxxxx.xx.cn"]

    start_urls = ["http://news.xxxxx.xxx.cn/hunan/"]

    def parse(self,response):

item  = ShopItem()

item[‘title‘]  =  response.xpath("//div[@class=‘txttotwe2‘]/ul/li/a/text()").extract()

item[‘time‘]  =  response.xpath("//div[@class=‘txttotwe2‘]/ul/li/font/text()").extract()

yield  item

class  ShopPipeline(object):

    def process_item(self, item, spider):

        count=len(item[‘title‘])

        print ‘news count: ‘ ,count

        for i in range(0,count):

            print ‘biaoti: ‘+item[‘title‘][i]

            print ‘shijian: ‘+item[‘time‘][i]

        return item

root@kali:~/shop#  scrapy crawl shop --nolog

news count:  40

biaoti:  xxx建成国家食品安全示范城市

shijian:  (2017-06-16)

biaoti: xxxx考试开始报名

……………………

…………………..