|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
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]))
print("")
def main():
goods = 'cherry轴键盘'
depth = 2
start_url = 'https://s.taobao.com/search?q=' + goods
infoList = []
for i in range(depth):
try:
url = start_url + '&s='
html = getHTMLText(url)
parsePage(infoList,html)
except:
continue
printGoodsList(infoList)
main()
只打印出了序号,价格和名称三个标题,没有具体的信息,求各位帮我看看哪里出了问题 |
|