pyhton爬虫笔记之实战 爬取淘宝商品价格和名称

# -*- coding: utf-8 -*-"""Created on Wed Nov 8 18:55:18 2017@author: xuanxuan"""# -*- coding: utf-8 -*- """ Created on Wed Nov 8 18:33:38 2017 @author: xuanxuan """ import requests import re def getHTMLText(url): try: r=requests.get(url) r.raise_for_status() r.encoding=r.apparent_encoding return r.text except: return "" def parserPage(ilt,html): plt=re.findall('\"view_price\"\:\"[\d\.]*\"',html) tlt=re.findall('\"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]) def printinfo(ilt): format0='{:4}\t{:8}\t{:16}' print(format0.format("序号","商品价格","商品名称")) count=0 for L in ilt: count=count+1 print(format0.format(count,L[0],L[1])) def main(): goods='鞋子' depth=3 start_url='http://s.taobao.com/search?q='+goods goodsinfo=[] for i in range(depth): url=start_url+'&s='+str(44*i) html=getHTMLText(url) parserPage(goodsinfo,html) printinfo(goodsinfo) main()