锐客网

  1. 首页 > it技术 > >

Python|Python爬取淘宝商品信息

Python爬虫


pyhton爬取淘宝商品信息

    • 源码

源码 import requests
import re
def getHTMLText(url):
try:
r =requests.get(url,timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return “”
def parsePage(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 (“序号”,“价格”,“商品名称”))
count = 0
for g in ilt:
count= count+1
print(tplt.format(count,g[0],g[1]))
def main():
goods = ‘书包’
depth = 2
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)
parsePage(infoList,html)
except:
continue
printGoodsList(infoList)
【Python|Python爬取淘宝商品信息】main()

    推荐阅读


    上一篇：GitHub和IDEA结合

    下一篇：mac安装php + mysql + nginx + Apache简单配置