我用 Python 分析了一波热卖年货，原来大家都在买这些东西？

pip install selenium

# coding=utf8  
import re  
from selenium.webdriver.chrome.options import Options  
from selenium import webdriver  
import time  
import csv  
  
  
# 搜索商品，获取商品页码  
def search_product(key_word):  
    # 定位输入框  
    browser.find_element_by_id("q").send_keys(key_word)  
    # 定义点击按钮，并点击  
    browser.find_element_by_class_name('btn-search').click()  
    # 最大化窗口：为了方便我们扫码  
    browser.maximize_window()  
    # 等待15秒，给足时间我们扫码  
    time.sleep(15)  
    # 定位这个“页码”，获取“共100页这个文本”  
    page_info = browser.find_element_by_xpath('//div[@class="total"]').text  
    # 需要注意的是：findall()返回的是一个列表，虽然此时只有一个元素它也是一个列表。  
    page = re.findall("(\d+)", page_info)[0]  
    return page  
  
  
# 获取数据  
def get_data():  
    # 通过页面分析发现：所有的信息都在items节点下  
    items = browser.find_elements_by_xpath('//div[@class="items"]/div[@class="item J_MouserOnverReq  "]')  
    for item in items:  
        # 参数信息  
        pro_desc = item.find_element_by_xpath('.//div[@class="row row-2 title"]/a').text  
        # 价格  
        pro_price = item.find_element_by_xpath('.//strong').text  
        # 付款人数  
        buy_num = item.find_element_by_xpath('.//div[@class="deal-cnt"]').text  
        # 旗舰店  
        shop = item.find_element_by_xpath('.//div[@class="shop"]/a').text  
        # 发货地  
        address = item.find_element_by_xpath('.//div[@class="location"]').text  
        # print(pro_desc, pro_price, buy_num, shop, address)  
        with open('{}.csv'.format(key_word), mode='a', newline='', encoding='utf-8-sig') as f:  
            csv_writer = csv.writer(f, delimiter=',')  
            csv_writer.writerow([pro_desc, pro_price, buy_num, shop, address])  
  
  
def main():  
    browser.get('https://www.taobao.com/')  
    page = search_product(key_word)  
    print(page)  
    get_data()  
    page_num = 1  
    while int(page) != page_num:  
        print("*" * 100)  
        print("正在爬取第{}页".format(page_num + 1))  
        browser.get('https://s.taobao.com/search?q={}&s={}'.format(key_word, page_num * 44))  
        browser.implicitly_wait(25)  
        get_data()  
        page_num += 1  
    print("数据爬取完毕！")  
  
  
if __name__ == '__main__':  
    key_word = input("请输入你要搜索的商品：")  
    option = Options()  
    browser = webdriver.Chrome(chrome_options=option,  
                               executable_path=r"C:\Users\cherich\AppData\Local\Google\Chrome\Application\chromedriver.exe")  
    main()  

import pandas as pd  
import matplotlib as mpl  
mpl.rcParams['font.family'] = 'SimHei'  
from wordcloud import WordCloud  
from ast import literal_eval  
import matplotlib.pyplot as plt  
datas = pd.read_csv('./年货.csv',encoding='gbk')  
datas  

li = []  
for each in datas['关键词'].values:  
    new_list = str(each).split(',')  
    li.extend(new_list)  
def func_pd(words):  
    count_result = pd.Series(words).value_counts()  
    return count_result.to_dict()  
  
frequencies = func_pd(li)  
frequencies.pop('其他')  
  
plt.figure(figsize = (10,4),dpi=80)  
wordcloud = WordCloud(font_path="STSONG.TTF",background_color='white', width=700,height=350).fit_words(frequencies)  
plt.imshow(wordcloud)  
plt.axis("off")  
plt.show()  

# plt.pie(x,lables,autopct,shadow,startangle,colors,explode)  
food_type = datas.groupby('价格区间').size()  
plt.figure(figsize=(8,4),dpi=80)  
explodes= [0,0,0,0,0.2,0.1]  
size = 0.3  
plt.pie(food_type, radius=1,labels=food_type.index, autopct='%.2f%%', colors=['#F4A460','#D2691E','#CDCD00','#FFD700','#EEE5DE'],  
       wedgeprops=dict(width=size, edgecolor='w'))  
plt.title('年货价格区间占比情况',fontsize=18)  
plt.legend(food_type.index,bbox_to_anchor=(1.5, 1.0))  
plt.show()  

data = datas.groupby(by='店铺名')['销量'].sum().sort_values(ascending=False).head(10)  
plt.figure(figsize = (10,4),dpi=80)  
  
plt.ylabel('销量')  
plt.title('年货销量前十名店铺',fontsize=18)  
colors = ['#F4A460','#D2691E','#CDCD00','#EEE5DE', '#EEB4B4', '#FFA07A', '#FFD700']  
plt.bar(data.index,data.values, color=colors)  
plt.xticks(rotation=45)  
plt.show()  

foods = datas.groupby(by='类别')['销量'].sum().sort_values(ascending=False).head(10)  
foods.sort_values(ascending=True,inplace=True)  
plt.figure(figsize = (10,4),dpi=80)  
plt.xlabel('销量')  
plt.title('年货推荐购买排行榜',fontsize=18)  
colors = ['#F4A460','#D2691E','#CDCD00','#CD96CD','#EEE5DE', '#EEB4B4', '#FFA07A', '#FFD700']  
plt.barh(foods.index,foods.values, color=colors,height=1)  
plt.show()