最好大学网
robots
目标网页
import requests
import bs4
from bs4 import BeautifulSoup
# 获取大学排名网页内容
def getHTMLText(url):
try:
r = requests.get(url, timeout=30) #请求URL超时,产生超时异常
r.raise_for_status() #如果转态不是200,引发HTTPError错误
r.encoding = r.apparent_encoding
return r.text
except:
return ""
# 提取信息到合适的数据结构
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[3].string])
# 利用数据结构数据展示并输出结果
def printUnivList(ulist, num):
print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分")) #^ 居中对齐
for i in range(num):
u = ulist[i]
print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))
# 主函数
def main():
uinfo = []
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 10) #10 univs
main()
# 利用数据结构数据展示并输出结果(优化)
def printUnivList(ulist, num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplt.format("排名", "学校名称", "总分", chr(12288))) #采用中文字符的空格填空 chr(12288)
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2], chr(12288)))
# 主函数
def main():
uinfo = []
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 10) #10 univs
main()