爬虫

import requests
from bs4 import BeautifulSoup
import bs4
info=[]
url ="http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html"
try:
    r=requests.get(url,timeout=100)
    r.raise_for_status()
    r.encouding=r.apparent_encoding
    soup=BeautifulSoup(r.text,"html.parser")
    for tr in soup.find("tbody").children:
        if isinstance(tr,bs4.element.Tag):
            tds=tr.find_all("td")
            info.append([tds[0].string,tds[1].string,tds[3].string])
    print("{0:^10}\t{1:{3}^10}\t{2}".format("排名","学校名称","总分",chr(12288)))
    for i in range(100):
        print("{0:^10}\t{1:^10}\t{2:^10}".format(info[i][0],info[i][1],info[i][2],chr(12288)))
except Exception as e:
    print(e)

  

上一篇:windows下 bash: npm: command not found-报错解决


下一篇:中国大学排名数据分析