(一)1、功能描述:
目标:获取淘宝搜索页面的信息,提取商品名称和价格;
理解:淘宝的搜索接口,翻页的处理;
技术路线: requests,re
2、程序的结构设计、
步骤1:提交商品搜索请求,循环获取页面;
步骤2:对每个页面,提取商品名称和价格信息;
(二)代码
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.split(':')[1])
title = eval(tlt.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)
输出结果
文章评论(0条评论)
登录后参与讨论