商品数据分析

具体步骤如下

爬取商城数据，并进行分析

数据爬取并保存为scv格式

   import requests
   from lxml import etree
   data = []
   import pandas as pd
   urls = 'http://880098.cn/index.php?s=/index/goods/index/id/%d.html'
   for i in range(1,30):
       page = i
       url = urls%page
       response = requests.get(url)
       html = response.text
       if "资源不存在或已被删除" in html:
           print(str(page)+"页无数据")
       else:
           print("开始爬"+str(page)+"页")
           ele = etree.HTML(html)
           title = ele.xpath('/html/body/div[5]/div[2]/div[2]/div[1]/h1/text()')[0]
           price = ele.xpath('/html/body/div[5]/div[2]/div[2]/div[2]/div/div[2]/dd/b/text()')[0]
           sale_num = ele.xpath('/html/body/div[5]/div[2]/div[2]/div[2]/ul/li[1]/div/span[2]/text()')[0]
           look = ele.xpath('/html/body/div[5]/div[2]/div[2]/div[2]/ul/li[2]/div/span[2]/text()')[0]
           kucun = ele.xpath('/html/body/div[5]/div[2]/div[2]/div[2]/dl/dd/div[2]/div[3]/form/div[1]/div/dd/span/span/text()')[0]
           info = {
               'id':page, '题目':title,'价格':price, '销售量':sale_num, '浏览量':look, '库存':kucun
           }
           data.append(info)
   fc = pd.DataFrame(data)
   fc.to_csv("test.csv",index=False, encoding='utf-8')

用xftp上传到指定文件夹

爬取数据示例

1,MIUI/小米 小米手机4 小米4代 MI4智能4G手机包邮 黑色 D-LTE（4G）/TD-SCD,2100,684,0,125

2,苹果（Apple）iPhone 6 Plus (A1524)移动联通电信4G手机 金色 16G,4500.00-6800.00,714,0,1701

3,Samsung/三星 SM-G8508S GALAXY Alpha四核智能手机 新品 闪耀白,3888,546,0,235

4,Huawei/华为 H60-L01 荣耀6 移动4G版智能手机 安卓,1999,630,0,537

5,Meizu/魅族 MX4 Pro移动版 八核大屏智能手机 黑色 16G,2499,1037,,434

6,vivo X5MAX L 移动4G 八核超薄大屏5.5吋双卡手机vivoX5max,2998.9,608,0,319

7,纽芝兰包包女士2018新款潮百搭韩版时尚单肩斜挎包少女小挎包链条,168,482,0,320

8,MARNI Trunk 女士 中号拼色十字纹小牛皮 斜挎风琴包,356,473,0,35

数据清洗

上传数据

hadoop fs -mkdir -p /college hadoop fs -put /root/college/loan.csv /college

创建数据库

create database 库名; create table 表名1( id int, name string, price int, views int, sales int, stock int )row format delimited fields terminated by ',';

导入数据-》hive

load data inpath '/college/loan.csv' into table 表名;

load data [local] inpath ‘/root/data’ into table psn; 表示本地而不是Hadoop

创建新表存储

create table 表名2 like 表名2;

数据过滤

原理如下

insert into 表名2

select * from 表名1

where not id is null and not price is null and not views is null and not sales is null and not stock is null #作用是去除空值，我本来以为这个语句最简单结果用了好多!=等方法都不作用，只有这 种臃肿的语句会正确的过滤空值

and name not like '%包包%' and name not like'%衣%' and name not like'%女士%'#判断不属于电子产品的异常值

group by id,name,price,views,sales,stock; #这个就是去重了

数据分析并下载

INSERT OVERWRITE LOCAL DIRECTORY '/root/college022/’ ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t’ SELECT count(distinct author) FROM data;

数据可视化

数据切分

select split(name, '\ ') from data where split(name, '\ ')[0]='Huawei/华为';

切分之后，通过简单计数，就可做可视化完成这一部分的题目

   data = []
   with open("sss.txt", "r", encoding='utf-8') as f:
       for i in f.readlines():
           data += i.split("�")
   
   dict = {}
   for key in data:
       dict[key] = dict.get(key, 0) + 1
   print(dict.values())
   print(dict)