源代码:
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].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]))
#print("Suc"+str(num))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)
main()
运行结果:
总分那一项,没输出正确。
修改这里就可以了吧。因为对应的标签的序号是第四个。
程序的结构设计
步骤1:从网络上获取大学排名网页内容
getHTMLText()
步骤2:提取网页内容中信息到合适的数据结构
fillUnivList()printUnivList()
步骤3:利用数据结构展示并输出结果
printUnivList()
课程地址:https://www.icourse163.org/learn/BIT-1001870001?tid=1003245012#/learn/content?type=detail&id=1004574446&cid=1005754042