第五周 | |
所花时间 | 15h左右 |
代码量 | 1000行左右 |
博客量 | 4篇 |
学到的知识点 | python基础的一些知识 |
摘要:通过学习,对python中的BeautifulSoup有了一定的了解,通过和之前学过的requests库结合,爬取了2019年中国大学的排名。(数据均来自HTML页面)
一、中国大学排名
![](https://img.laitimes.com/img/9ZDMuAjOiMmIsIjOiQnIsISPrdEZwZ1Rh5WNXp1bwNjW1ZUba9VZwlHdsATOfd3bkFGazxCMx8VesATMfhHLlN3XnxCMwEzX0xiRGZkRGZ0Xy9GbvNGLpZTY1EmMZVDUSFTU4VFRR9Fd4VGdsYTMfVmepNHLrJXYtJXZ0F2dvwVZnFWbp1zczV2YvJHctM3cv1Ce-YWan5iY4YWO1cjZyIWYilTYhFmMjNzNkZ2NhFjN4UTZmBTN58CX5EzLcdDMxIDMy8CXn9Gbi9CXzV2Zh1WavwVbvNmLvR3YxUjL4M3Lc9CX6MHc0RHaiojIsJye.gif)
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[3].string])
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)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2], chr(12288)))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.com/Greater_China_Ranking2019_0.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20) # 20 univs
main()
中国大学排名