25

  中国大学排名网站  http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html

2018年中国大学排名

#1
import requests
from bs4 import BeautifulSoup
import bs4
 
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()  
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "404" 
 
def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find('tbody').children:   
        if isinstance(tr,bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[2]])
    pass
 
def printUnivList(ulist,num):
    print("{:^6}".format("学校名称"))
    for i in range(num):
        u = ulist[i]
        print("{:^6}".format(u[1]))
 
 
def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20) 
main()

　　

 

 

#2
import requests
from bs4 import BeautifulSoup
import bs4
allUniv = []
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 fillUnivList(soup):
    data = soup.find_all('tr')
    for tr in data:   
        ltd = tr.find_all('td')
        if len(ltd)==0:
            continue
        singleUniv = []
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
        
def printUnivList(num):
    print("{:^10}".format("学校名称"))
    for i in range(num):
        u = allUniv[i]
        print("{:^10}".format(u[1]))
 
 
def main():
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(20) 
main()