scrapy crawl itcast -o teachers.json 爬虫案列

1. spider.py文件配置

     1 
     2 # -*- coding: utf-8 -*-
     3 import scrapy
     4 from itTeachers.items import ItteachersItem
     5 
     6 
     7 class ItcastSpider(scrapy.Spider):
     8     name = 'itcast'
     9     allowed_domains = ['itcast.cn']
    10     start_urls = ['http://www.itcast.cn/channel/teacher.shtml#']
    11 
    12     def parse(self, response):
    13         #with open("teacher.html","w") as f:
    14             #f.write(response.body)
    15 
    16         items = []
    17 
    18         teacher_list = response.xpath('//div[@class="li_txt"]')
    19         for each in teacher_list:
    20 
    21             #我们将得到的数据封装到一个'ItcastItem'对象
    22             item = ItteachersItem()
    23             name = each.xpath('h3/text()').extract()
    24             title = each.xpath('h4/text()').extract()
    25             info = each.xpath('p/text()').extract()
    26 
    27             #xpath返回的是包含一个元素的列表
    28             item['name'] = name[0]
    29             item['title'] = title[0]
    30             item['info'] = info[0]
    31 
    32             items.append(item)
    33         #直接返回最后数据
    34         return items
   ~                         

2. items.py文件配置

     1 # -*- coding: utf-8 -*-
     2 
     3 # Define here the models for your scraped items
     4 #
     5 # See documentation in:
     6 # https://doc.scrapy.org/en/latest/topics/items.html
     7 
     8 import scrapy
     9 
    10 
    11 class ItteachersItem(scrapy.Item):
    12     # define the fields for your item here like:
    13     # name = scrapy.Field()
    14     name = scrapy.Field()
    15     title = scrapy.Field()
    16     info = scrapy.Field()