python爬虫爬取淘宝商品信息


            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 = 'http://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：



更多内容请参考专题《python爬取功能汇总》进行学习。

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持中文源码网。