python爬虫爬取淘宝商品信息

168 阅读 0 评论 111 点赞

我是靠谱客的博主香蕉鸵鸟，最近开发中收集的这篇文章主要介绍python爬虫爬取淘宝商品信息，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

本文实例为大家分享了python爬取淘宝商品的具体代码，供大家参考，具体内容如下

import requests as req 
import re 
 
def getHTMLText(url): 
 try: 
 r = req.get(url, timeout=30) 
 r.raise_for_status() 
 r.encoding = r.apparent_encoding 
 return r.text 
 except: 
 return "" 
 
def parasePage(ilt, html): 
 try: 
 plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html) 
 tlt = re.findall(r'\"raw_title\"\:\".*?\"', html) 
 for i in range(len(plt)): 
  price = eval(plt[i].split(':')[1]) 
  title = eval(tlt[i].split(':')[1]) 
  ilt.append([price, title]) 
 except: 
 print("") 
 
 
def printGoodsList(ilt): 
 tplt = "{:4}\t{:8}\t{:16}" 
 print(tplt.format("序列号", "价格", "商品名称")) 
 count = 0 
 for j in ilt: 
 count = count + 1 
 print(tplt.format(count, j[0], j[1])) 
 
def main(): 
 goods = "python爬虫" 
 depth = 3 
 start_url = 'https://s.taobao.com/search?q=' + goods 
 infoList = [] 
 for i in range(depth): 
 try: 
  url = start_url + '&s=' + str(44*i) 
  html = getHTMLText(url) 
  parasePage(infoList, html) 
 except: 
  continue 
 printGoodsList(infoList) 
 
main()

效果图：