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 ""
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].text.strip(),tds[1].text.strip(),tds[4].text.strip()]) # strip函数移除空格或换行符
def printUnivList(ulist,num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" # {3}表示使用format的第三个变量，即chr(12288)中文字符填充
print("{:^9}\t{:^15}\t{:^8}".format("排名","学校名称","分数"))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
def main():
uinfo = []
url = "https://www.shanghairanking.cn/rankings/bcur/2020"
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20) # 前20所
main()
2020中国最好大学排名.py（亲测有效）的相关教程结束。
