-*- coding: utf-8 -*-

import scrapy

from mySpider.items import MyspiderItem

class MyspiderSpider(scrapy.Spider):
name = 'myspider'
allowed_domains = ['itcast.cn']
start_urls = ['http://www.itcast.cn/channel/teacher.shtml#ajavaee']

def parse(self, response):
    teacher_list = response.xpath('//div[@class="li_txt"]')
    teacherItem = []
    for each in teacher_list:
        item = MyspiderItem()
        name = each.xpath('./h3/text()').extract()
        title = each.xpath('./h4/text()').extract()
        info = each.xpath('./p/text()').extract()

        item['name'] = name[0].encode("gbk")
        item['title'] = title[0].encode("gbk")
        item['info'] = info[0].encode("gbk")

        teacherItem.append(item)

        # print(name[0])
        # print(title[0])
        # print(info[0])
    # pass
    return teacherItem

然后又用scrapy crawl spider -o spider.csv

https://blog.csdn.net/baidu_40801518/article/details/82055708