爬取淘宝网页的商品价格信息 ,但是没有获取到商品信息,应该是正则表达式有问题,但是我不知道问题在哪……
import requests
import re
#访问并获取网页
def getHtmlText(url):
try :
r = request.get(url,timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
#解析网页,获取信息
def parserPage(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(pat[i].split(':')[1])
title = eval(tlt[i].split(':')[1])
ilt.append([price,title])
except:
return 0
#打印信息
def printGoodList(lit):
tplt = "{:4}\t{:8}\t{:16}"
print(tplt.format("序号","价格","商品名称"))
count = 0
for g in lit:
count = count + 1
print(tplt.format(count,g[0],g[1]))
#主函数
def main():
goods = '书包'
#爬取网页的页数
depth = 2
start_url = "https://s.taobao.com/search?q=" + goods
infoList = []
for i in range (depth):
try :
url = start_url + '&s='+ str(44*i)
#页数标码为44,加44代表进下页
html = getHtmlText(url)
parsePage(infoList,html)
except:
continue
printGoodList(infoList)
main()
小白求指点,谢谢