飞道的博客

爬虫入门(大学排名)

339人阅读  评论(0)
import requests
import bs4
from bs4 import BeautifulSoup
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 fillunilist(ulist,html):
    soup=BeautifulSoup(html,"html.parser")
    for tr in soup.find('tbody').children:
       if isinstance(tr,bs4.element.Tag):
            td=tr('td')
            ulist.append([td[0].string,td[1].string,td[2].string])                       
def show(ulist,num):
    tplt="{0:^10}\t{1:^10}\t{2:^10}"
    print(tplt.format("排名","学校","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)
    fillunilist(uinfo,html)
    show(uinfo,20)
main()

转载:https://blog.csdn.net/qq_37443534/article/details/105232486
查看评论
* 以上用户言论只代表其个人观点,不代表本网站的观点或立场