python爬虫学习淘宝页面定向爬取 DAY5

本文介绍了一种使用Python爬取淘宝商品信息的方法，通过解析网页获取商品价格和名称，并将结果整理输出。代码实现了请求网页、正则表达式匹配、数据打印及文件保存等功能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import requests
import re

def getHTMLTxt(url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""


def dealHTML(ulist,html):
    vpl = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
    rpl = re.findall(r'\"raw_title\"\:\".*?\"',html)
    for i in range(len(vpl)):
        vstr = eval(vpl[i].split(":")[1])
        rstr = eval(rpl[i].split(":")[1])
        ulist.append([vstr,rstr])

def printHTML(ulist,html):
    count=0
    print("{0:{3}<6}{1:{3}<8}\t{2:{3}^16}".format("序号","价格","商品名称",chr(12288)))
    for i in range(len(ulist)):
        count=count+1
        print("{0:{3}<4}\t{1:{3}^8}\t{2:{3}^16}".format(count,ulist[i][0],ulist[i][1],chr(12288)))

def wTXT(ulist,html):
    count=0
    f = open(r'C:\Users\lenovo\Desktop\书包价格.txt','w+')
    f.write("{0:{3}<6}{1:{3}<8}\t{2:{3}^16}".format("序号","价格","商品名称",chr(12288))+'\n')            
    for i in range(len(ulist)):
        count = count+1
        f.write("{0:{3}<4}\t{1:{3}^8}\t{2:{3}^16}".format(count,ulist[i][0],ulist[i][1],chr(12288))+'\n')
    f.close()
            
def main():
    page = 3
    urlm = "https://s.taobao.com/search?q="
    goods = "书包"
    ulist = []    
    for i in range(page):
        url = urlm+goods+"&s="+str(44*i)
        html = getHTMLTxt(url)
        dealHTML(ulist,html)
    printHTML(ulist,html)
    wTXT(ulist,html)
    
main()