|
|
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
爬取淘宝页面商品信息
正则表达式好像不对,没有爬到信息
- import requests
- import re
- def getHtmlText(url):
- try :
- r = request.get(url,timeout = 30)
- r.raise_for_status()
- r.encoding = r.apparent_encoding
- return r.text
- except:
- return ""
- 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
- 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]))
- def main():
- goods = '书包'
- 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)
- html = getHtmlText(url)
- parsePage(infoList,html)
- except:
- continue
- printGoodList(infoList)
-
-
- main()
复制代码
求大佬指正 |
|