网络爬虫-大学排名实例

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)
	pass

def printUnivList(ulist,num):
	print("{:^10}\t{:^6}\t{:^10}".format("daxue",'haode','zhende'))
	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)#20school
main()