20191226_1_淘宝口红商品分析

这个单子那大哥人确实不怎么样，先是，我说我看下淘宝代码，他就要我便宜20，同意，之后给我们拉单子，一个单子要了10元，之后我和同学吃火锅，没有来得及回消息，就说我做的东西没有达到他的要求，要求我退一些钱，要不是为了店长的好评，我就翻脸了，没办法，谁叫是小菜鸡呢，那个晚上喝了点酒，心情有点不好，居然哭了，呵呵，不说了，看这个代码吧

from selenium import  webdriver
from selenium.webdriver.support.ui import WebDriverWait#延迟等待
from selenium.webdriver.support import expected_conditions as EC#查找元素
from selenium.webdriver.common.by import By
import time, re
from selenium.webdriver.common.action_chains import ActionChains
from selenium.common.exceptions import UnexpectedAlertPresentException
from time import sleep
import pandas as pd


def search(driver,wait):
    try:
        Input=wait.until(EC.presence_of_element_located((By.XPATH,'//*[@id="q"]')))#等待输入框显示
        Input.send_keys('口红')
        submit=wait.until(EC.element_to_be_clickable((By.XPATH,'//*[@id="J_TSearchForm"]/div[1]/button')))
        submit.click()#点击按钮
        tot_page=wait.until(EC.presence_of_element_located((By.XPATH,'//*[@id="mainsrp-pager"]/div/div/div/div[1]'))).text
        print(tot_page)#100页
        page_number=int(re.compile('(\d+)').search(tot_page).group(1))
        return 44
    except:
        driver.get('https://login.taobao.com/member/login.jhtml')
        sleep(6)
        driver.find_element_by_xpath('//*[@class="forget-pwd J_Quick2Static"]').click()
        sleep(2)
        driver.find_element_by_xpath('//*[@class="weibo-login"]').click()
        sleep(3)
        driver.find_element_by_name('username').send_keys('[email protected]')
        sleep(5)
        driver.find_element_by_name('password').send_keys('aS1233211234567')
        sleep(40)
        #driver.find_element_by_xpath('//*[@class="btn_tip"]/a/span').click()
        search(driver, wait)
        return 44




def get_products(browse):
    divs = browse.find_elements_by_xpath('//div[@class="items"]/div[@class="item J_MouserOnverReq  "]')  # 获取标签
    for div1 in divs:
        price = div1.find_element_by_xpath('.//div[@class="row row-1 g-clearfix"]/div[@class="price g_price g_price-highlight"]').text
        all_price.append(price)
        info = div1.find_element_by_xpath('.//div[@class="row row-2 title"]/a[@class="J_ClickStat"]').text
        all_info.append(info)
        producer = div1.find_element_by_xpath('.//div[@class="row row-3 g-clearfix"]/div[@class="location"]').text
        all_producer.append(producer)
        deal = div1.find_element_by_xpath('.//div[@class="row row-1 g-clearfix"]/div[@class="deal-cnt"]').text
        all_deal.append(deal)
        dic={'商品信息':info,'销售价格':price,'发货地':producer,'销售额':deal}
        print(dic)





def digging(driver,page):
    num=24
    while num!=page-1:
            driver.get('https://s.taobao.com/search?q=口红&s={}'.format(44*num))
            driver.implicitly_wait(10)
            get_products(driver)
            num += 1
            sleep(7)



if __name__ == "__main__":
    try:
        all_info = []
        all_deal = []
        all_price = []
        all_producer = []
        driver=webdriver.Chrome()
        wait = WebDriverWait(driver, 15)
        driver.get('https://www.taobao.com/')
        driver.maximize_window()
        page = search(driver,wait)
        print(type(page))
        digging(driver,page)
        print(all_info,all_price,all_producer,all_deal)
        lipstick=pd.DataFrame()
        lipstick['商品信息']=all_info
        lipstick['销售价格']=all_price
        lipstick['发货地']=all_producer
        lipstick['销售额']=all_deal
    finally:
         lipstick.to_excel('lipstick.xls2',index=False)

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False

test=pd.read_excel('lipstick.xls')

test.head()

	info	price	producer	sales
0	【圣诞礼物】MAC/魅可子弹头断货王口红唇膏 chili/牛血色/mac646	¥170.00	浙江 杭州	10万+人付款
1	【圣诞礼物】MAC/魅可尤雾弹唇膏哑光口红316/923人间水蜜桃新款	¥170.00	浙江 杭州	10万+人付款
2	Dior/迪奥圣诞星空限量口红套装烟花礼盒蓝金唇膏口红999 772 080	¥1368.00	福建 福州	209人付款
3	Christian Louboutin萝卜丁女王限量口红3支装001/001s/001m 3.5g	¥2508.00	福建 福州	26人付款
4	ChristianLouboutin萝卜丁进口女王权杖口红唇膏多色滋润保湿持久	¥788.00	浙江 杭州	1057人付款

test.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1059 entries, 0 to 1058
Data columns (total 4 columns):
info        1059 non-null object
price       1059 non-null object
producer    1059 non-null object
sales       1053 non-null object
dtypes: object(4)
memory usage: 33.2+ KB

#缺失值

test.isnull().sum()
test.dropna(inplace=True)

数据预处理

test['price']=test['price'].apply(lambda x: x.split('¥')[1])

import re
test['sales'] = test['sales'].apply(lambda x: re.findall(r"\d+\.?\d*",str(x)))

for i in test.index:
    test.loc[i,'sales']=test['sales'][i][0]

词云

import codecs
import jieba
import pickle
# test['info'].to_csv('名称.txt', sep='\t', index=False)
# fin = codecs.open('名称.txt',mode = 'r', encoding = 'utf-8')
# # print (fin.read())
# #第一次运行程序时将分好的词存入文件
# text = ''
# with open('名称.txt',encoding = 'utf-8') as fin:
#     for line in fin.readlines():
#         line = line.strip('\n')
#         text += ' '.join(jieba.cut(line))
#         text += ' '
# fout = open('text.txt','wb')
# pickle.dump(text,fout)
# fout.close()

from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator
fr = open('text.txt','rb')
text = pickle.load(fr)
# print(text)
backgroud_Image = plt.imread('lipstick.jpg')
wc = WordCloud( background_color = 'white',    # 设置背景颜色
                mask = backgroud_Image,        # 设置背景图片
                max_words = 200,            # 设置最大现实的字数
                stopwords = STOPWORDS,        # 设置停用词
                font_path = 'simfang.ttf',# 设置字体格式，如不设置显示不了中文
                max_font_size = 200,            # 设置字体最大值
                random_state = 8,            # 设置有多少种随机生成状态，即有多少种配色方案
                )
wc.generate(text)
image_colors = ImageColorGenerator(backgroud_Image)
wc.recolor(color_func = image_colors)
plt.figure(figsize=(20,30))
plt.imshow(wc)
plt.axis('off')
plt.show()

商品价格对销售额的影响

test['sales']=test['sales'].astype('float')
test['sales']=test['sales'].astype('float')
test.head()

	info	price	producer	sales
0	【圣诞礼物】MAC/魅可子弹头断货王口红唇膏 chili/牛血色/mac646	170.00	浙江 杭州	10.0
1	【圣诞礼物】MAC/魅可尤雾弹唇膏哑光口红316/923人间水蜜桃新款	170.00	浙江 杭州	10.0
2	Dior/迪奥圣诞星空限量口红套装烟花礼盒蓝金唇膏口红999 772 080	1368.00	福建 福州	209.0
3	Christian Louboutin萝卜丁女王限量口红3支装001/001s/001m 3.5g	2508.00	福建 福州	26.0
4	ChristianLouboutin萝卜丁进口女王权杖口红唇膏多色滋润保湿持久	788.00	浙江 杭州	1057.0

tes1t=test.sort_values(by='price',ascending=True)
tes1t.head()

	info	price	producer	sales
795	正品MAC魅可棒棒糖唇釉唇彩染唇液镜面口红 18新款泫雅色106/108	101.00	上海	3077.0
789	正品MAC魅可棒棒糖唇釉唇彩染唇液镜面口红 18新款泫雅色106/108	101.00	上海	3077.0
347	【双旦礼遇季】珂莱欧炫彩丝绒雾面唇釉唇彩持久滋润显色口红新品	102.00	上海	204.0
1013	魅可MAC圣诞星空限定口红923牛血色316车厘子色646小辣椒大牌正品	102.00	山东 济南	2641.0
140	第二支10元意大利公主钻石品质魔镜口红ROSEPRETTY贵族限量版	1029.90	江苏 南京	1283.0

import seaborn as sns
sns.relplot(x="price", y="sales", data=test,
            kind='scatter', # ['scatter','line']
#             hue='day',  # 设置按颜色分类的第三变量
#             style='day', # 设置形状分类
            palette='husl',s=60, # 设置调色盘类型和散点大小
            aspect=2.5,height=6  # 设置图像大小和横纵比
           )

<seaborn.axisgrid.FacetGrid at 0x21e7d38deb8>

import seaborn as sns
sns.relplot(x="sales", y="price", data=test,
            kind='scatter', # ['scatter','line']
#             hue='day',  # 设置按颜色分类的第三变量
#             style='day', # 设置形状分类
            palette='husl',s=60, # 设置调色盘类型和散点大小
            aspect=2.5,height=6  # 设置图像大小和横纵比
           )

<seaborn.axisgrid.FacetGrid at 0x21e03a96860>

不同价格区间的商品平均销量分布

test['sales'].describe()

count    1053.000000
mean     1334.559354
std      1910.790570
min         0.000000
25%       136.000000
50%       526.000000
75%      1645.000000
max      9500.000000
Name: sales, dtype: float64

def function(x):
    if x<136:
        return 1
    elif 526>x>136:
        return 2
    elif 1645>x>526:
        return 3
    elif x>1645:
        return 4
test['label'] = test['sales'].apply(lambda x: function(x))

tips = sns.load_dataset("tips")
ax = sns.stripplot(x="label", y="sales", data=test)

for i in range(1,5):
    print('第{}类的商品平均销量为{}'.format(i,int((test['sales'][test['label']==i]).mean())))

第1类的商品平均销量为44
第2类的商品平均销量为306
第3类的商品平均销量为958
第4类的商品平均销量为4027

商品的价格分布情况分析

#这是一个密度图，你看两边都趋近零，但是最高的是0-1000中间，说明主要分布在这里
test['sales'].dropna().plot(kind='kde', xlim=(-2000,7500))

<matplotlib.axes._subplots.AxesSubplot at 0x21e027fc630>

labels = ['1','2','3','4']
sizes=[]
for i in range(1,5):
    sizes.append(int((test['sales'][test['label']==i]).count()))
explode = (0,0,0.1,0)
plt.pie(sizes,explode=explode,labels=labels,autopct='%1.1f%%',shadow=False,startangle=150)
plt.title("商品的价格分布")
plt.show()