BeautifulSoup获取中国大学排名

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    """获取页面信息"""
    try:
        resp = requests.get(url, timeout=30)
        resp.raise_for_status()
        resp.encoding = resp.apparent_encoding
        return resp.text
    except:
        return ''

def fillUnivlist(ulist,html):
    """提取页面内容"""
    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):
    """打印"""
    uprint = '{0:^10}\t{1:{3}^10}\t{2:^10}'
    print(uprint.format("排名", "学校名称", "总分",chr(12288)))	# 处理打印排版问题
    for i in range(num):
        u = ulist[i]
        print(uprint.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfor = []

    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url)
    fillUnivlist(uinfor,html)
    printUnivlist(uinfor,20)
    # print(uinfor)

main()


你可能感兴趣的:(python)