import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url)
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","学校名称","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/zuihaodaxuepaiming2018.html'
html = getHTMLText(url)
print ("aa")
fillUnivList(uinfo, html)
printUnivList(uinfo, 100)
main()
'''
最后输出结果会很整洁
{1:{3}^10} 1表示位置,{3}表示用第3个参数来填充,^表示居中,10表示占10个位置
这里的第三个参数就是char(12288)
之前是采用西文字符填充,现在采用中文字符填充
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplt.format("排名","学校名称","总分",chr(12288)))
for i in range(num):
u=ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
'''