使用requests库和BeautifulSoup库实现对最好大学网大学排名信息爬取
代码:
import requests
from bs4 import BeautifulSoup
import bs4
#从网络上获取大学排名网页内容
def getHTMLText(url):
try:
r =requests.get(url,timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
#提取网页内容中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])
#利用数据结构展示并输出结果
def printUnivList(ulist,num):
tplt = "{0:^10} {1:{3}^10} {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)
main()