from bs4 import BeautifulSoup
import requests
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].string,tds[1].string,tds[2].string])
def printUnivList(ulist, num):
print("{:^10}\t{:^6}\t{:^10}".format('排名',"学校","总分"))
for i in range(num):
u = ulist[i]
print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming-zongbang-2020.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)
main()
IDLE 运行时不报错,不异常,总是无疾而终,插入提示语也未见效,最终发现最后的main后未加“()”
被自己蠢哭