import requests
from bs4 import BeautifulSoup
import bs4
def gethtml(url):
'''获取html页面'''
try:
r=requests.get(url,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return('获取网页成功')
def list1(ulist,html):
'''获取HTML页面关键信息添加到列表里'''
re=BeautifulSoup(html,'html.parser')
for tr in re.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds=tr.find_all('td')#返回类表类型,存储查找的结果
ulist.append([tds[0].string,tds[1].string,tds[2].string])
def printlist(ulist):
print("{:^10}\t{:^6}\t{:^10}".format("排名","学校","总分"))
for i in range(20):
u=ulist[i]
print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))
def main():
ulist=[]
url = 'http://www.zuihaodaxue.com/Greater_China_Ranking2019_0.html'
html=gethtml(url)
list1(ulist,html)
printlist(ulist)
main()
本文地址:https://blog.csdn.net/weixin_45774059/article/details/107326572
如对本文有疑问, 点击进行留言回复!!
南宁小程序开发,挑战百日学习计划第43天(拖拉登录框的写法)
让盒子水平居中解决方法!!!---(块元素,行内元素,行内块,文本)
CSS踩坑-------transform:scale(‘数字’)
网友评论