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:
print('Error')
return ""
def fillUnivlist(ulist, html):
soup = BeautifulSoup(html, 'html.parser')
for tr in soup.find('tbody').children:
if isinstance(tr, bs4.element.Tag):
#筛选出属性为Tag的tr,去掉其他文本
tds = tr('td')
ulist.append([tds[0].string,tds[1].string,
tds[2].string,tds[3].string])
def printUnivlist(ulist, num):
space = "{0:^10}\t{1:^10}\t{2:^10}\t{3:^6}"
print(space.format("排名","学校名称","地区","总分",
chr(12288)))
for i in range(num):
u = ulist[i]
print(space.format(u[0],u[1],u[2],u[3],
chr(12288)))
def main():
uinfo =[]
url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html'
html = getHtmlText(url)
fillUnivlist(uinfo, html)
printUnivlist(uinfo, 20)#打印20所学校的排名
main()