python scrapy basic

scrapy startproject todo scrapy genspider -t basic todolist 192.168.126.181 cd todo vi items.py import scrapy

class TodoItem(scrapy.Item): todo=scrapy.Field() riqi=scrapy.Field()

vi todolist.py

-- coding: utf-8 --

import scrapy from todo.items import TodoItem

class TodolistSpider(scrapy.Spider): name = 'todolist' allowed_domains = ['192.168.126.181'] start_urls = ['http://192.168.126.181:9999/simpletodo']

def parse(self, response):
    items=[]
    trs=response.xpath('//table//tr')
    for tr in trs:
      todos=tr.xpath('.//td[@class="todo"]')
      if len(todos)>0:
         item=TodoItem()
         item["todo"]=todos[0].xpath("./text()").extract()[0]
         item["riqi"]=todos[1].xpath("./text()").extract()[0]
         items.append(item)
    return items

scrapy crawl todolist