仿写原创——单页面爬取

import scrapyclass MaiziItem(scrapy.Item):    title = scrapy.Field()    link=scrapy.Field()    desc =scrapy.Field()

2.spider文件编写

# -*- coding: utf-8 -*-#encoding=utf-8import scrapyfrom LianHeZaoBao.items import LianhezaobaoItemreload(__import__('sys')).setdefaultencoding('utf-8') class MaimaiSpider(scrapy.Spider):    name = "lianhe"    allowed_domains = ["http://www.zaobao.com/news/china//"]    start_urls = (        'http://www.zaobao.com/news/china//',    )    def parse(self, response):                for li in response.xpath('//*[@id="l_title"]/ul/li'):            item = LianhezaobaoItem()            item['title'] = li.xpath('a[1]/p/text()').extract()            item['link']=li.xpath('a[1]/@href').extract()            item['desc'] = li.xpath('a[2]/p/text()').extract()                        yield item

3.保存文件:命令scrapy crawl lianhe -o lianhe.csv