item.py

 python


 -*- coding: utf-8 -*
import scrapy
class BokeItem(scrapy.Item):
    url=scrapy.Field()
    title=scrapy.Field()
    content=scrapy.Field()

boke_spider.py

 python


 -*- coding: utf-8 -*-
from scrapy.contrib.spiders import CrawlSpider ,Rule
from scrapy.contrib.linkextractors import LinkExtractor
from boke.items import BokeItem

class BokeItem(CrawlSpider):
    name = 'blog'
    start_urls =['http://blog.sina.com.cn/s/blog_4701280b0102eo83.html']

    def parse_torrent(self,response):
        torrent=BokeItem()
        torrent['url']=response.url
        torrent['title']=response.xpath("//h2[@class='titName SG_txta']/text()").extract()[0]
        torrent['content']=response.xpath("//div[@style='min-height:22px']/text()").extract()[0]
        return  torrent