使用scrapy框架爬取某商城部分数据并存入MongoDB

Posted 2020-12-20 星辰

爬取电商网站的商品信息:

    URL为: https://www.zhe800.com/ju_type/baoyou
    抓取不同分类下的商品数据
    抓取内容为商品的名称, 价格数字, 商品图片
    将商品图片二进制流, 商品名称和价格数字一同存储于MongoDB数据库

存储数据结构为:

{

          ‘name’: ‘懒人神奇, 看电影必备’,

          ‘price’: ‘5.5’,　　

　　   　　‘img’: ….,

           “category”: ‘家纺’

}

这里抓包就不说了，很简单，利用xpath进行解析

• by.py

  • # -*- coding: utf-8 -*-
    import scrapy
    from ..items import BywItem
    class BySpider(scrapy.Spider):
        name = \'by\'
        # allowed_domains = [\'baidu.com\']
        start_urls = [\'https://www.zhe800.com/ju_type/baoyou\']
    　　 
        def img_parse(self,response):
            item = BywItem()
            item[\'name\'] = response.meta[\'name\']
            # print(name)
            item[\'cate\'] = response.meta[\'cate\']
            # print(cate)
            item[\'price\'] = response.meta[\'price\']
            item[\'img\'] = response.body
            yield item
    
        #详情
        def xq_parse(self,response):
            cate = response.meta[\'cate\']
            print(cate)
            xq_list = response.xpath(\'//div[@class="con "]\')
            print(xq_list)
            for xq in xq_list:
                name = xq.xpath(\'./h3/a/@title\').extract_first()
                print(name)
                price = xq.xpath(\'./h4/em/text()\').extract_first()
                print(price)
                img_link = \'https:\' +xq.xpath(\'.//a/img/@data-original\').extract_first()
                print(img_link)
                meta = {
                    \'name\':name,
                    \'price\':price,
                    \'cate\':cate
                }
                yield scrapy.Request(url=img_link,callback=self.img_parse,meta=meta)
    
    
        def parse(self, response):
            a_list = response.xpath(\'//div[@class="area"]/a[position()>1]\')
            for a in a_list:
                cate = a.xpath(\'./em/text()\').extract_first()
                # print(cate)
                cate_link = \'https:\' +a.xpath(\'./@href\').extract_first()
                # print(cate_link)
                yield scrapy.Request(url=cate_link,callback=self.xq_parse,meta={\'cate\':cate})

• items.py

  • import scrapy
    
    
    class BywItem(scrapy.Item):
        # define the fields for your item here like:
        name = scrapy.Field()
        cate = scrapy.Field()
        price = scrapy.Field()
        img = scrapy.Field()

• pipelines.py

  • import pymongo
    conn = pymongo.MongoClient()  #连接
    db = conn.byw  #创建数据库
    table = db.by  #创建表
    
    class BywPipeline:
        def process_item(self, item, spider):
            table.insert_one(dict(item))  #插入数据
            return item

• settings.py

  • #ua
    
    USER_AGENT = \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/81.0.4044.92 Safari/537.36\'
    
    #robots协议
    ROBOTSTXT_OBEY = False
    
    
    
    #管道
    ITEM_PIPELINES = {
       \'byw.pipelines.BywPipeline\': 300,
    }

• 效果