python爬去淘宝西装数据_西装数据集-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_38233696/article/details/90241440

使用Python爬取淘宝上的西装数据，通过TF-IDF计算后，应用KMeans进行聚类分析。最终结果显示了不同类型的西装关键词，包括新款、秋冬、修身、商务等，以及KMeans聚类后的结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

python爬去淘宝西装数据

啥也不说代码先码上

#爬取数据
from selenium import webdriver
from bs4 import BeautifulSoup
import time
import csv
import re

titles,prices,shops,sales = [],[],[],[]

#csvFile = open("xizhuang_women.csv","w",newline='') # newline=''解决空白行问题
csvFile = open("xizhuang_men.csv","w",newline='')
writer = csv.writer(csvFile)
writer.writerow(('title','price','shop','sale'))

def getInfo(page):
    #url_women = "https://re.taobao.com/search?&extra=&refpid=420435_1006&keyword=%E8%A5%BF%E8%A3%85%20%E5%A5%B3&_input_charset=utf-8&page="+str(page)+"&isinner=0&rewriteKeyword"
    url_men = "https://re.taobao.com/search?&extra=&refpid=420435_1006&keyword=%E8%A5%BF%E8%A3%85%20%E7%94%B7&_input_charset=utf-8&page="+str(page)+"&isinner=0&rewriteKeyword"
    
    #配置headless
    fireFoxOptions = webdriver.FirefoxOptions()
    fireFoxOptions.set_headless() #设置为headless模式
    driver = webdriver.Firefox(firefox_options=fireFoxOptions)
    time.sleep(2)
#    driver.get(url_women)
    driver.get(url_men)
    
    soup = BeautifulSoup(driver.page_source, 'html.parser')
    titles = soup.findAll('span',class_='title')
    prices = soup.findAll('span',class_='pricedetail')
    shops = soup.findAll('span',class_='shopNick')
    sales = soup.findAll('span',class_='payNum')
    print(len(titles))
    for i in range(len(titles)):
        saleNum = re.findall(r"\d+\.?\d*",sales[i].get_text()) #提取销售数量数值
        writer.writerow((titles[i].get_text(),prices[i].find('strong').get_text(),shops[i].get_text(),''.join(saleNum)))
        
    driver.quit() # 表示关闭浏览器

for page in range(0,10): # 爬取前10页
    print ("正在爬取第{}页".format(page))
    getInfo(page)

csvFile.close() # 关闭文件
print("完成！")

#                           第一步 计算TFIDF  
import codecs
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
import jieba
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

print('计算tfidf：')

# 语料库corpus构建
corpus = [] # 语料库
filepath_men = '.\\data\\xizhuang_men.csv'
filepath_women = '.\\data\\xizhuang_women.csv'
#def corpusCreate(path):
#    file = open(path,'r')
#    lines = file.readlines()
#    file.close()
#        
#    # 只分词的语料库
#    for line in lines:
#        ziduan = line.split(',')
#        title = ziduan[0]
#        cut_text = jieba.cut(title) # 分词
#        result = " ".join(cut_text)
#        corpus.append(result)
#corpusCreate(filepath_men)
#corpusCreate(filepath_women)

# 去停用词的语料库 
jiebaTxt = open('.\\output\\jieba.txt', mode = 'w') # 存储预处理后的文本结果
remove_words = [u'的', u'，',u'和', u'是', u'随着', u'对于', u'对',u'等',u'能',u'都',u'。',u' ',u'、