import requests
from bs4 import BeautifulSoup
import bs4
def getHtmlText(url):
r = requests.get(url)
r.encoding = r.apparent_encoding
html = r.text
return html
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):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplt.format("排名", "学校", "省份", 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/zuihaodaxuepaiming2018.html"
html = getHtmlText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)
main()
Python爬虫爬取中国最好大学排行榜
最新推荐文章于 2024-05-08 03:05:41 发布