帮我完成这四个步骤步骤1：从网络上获取网页内容getHTMLText() 步骤2：提取网页中的数据信息到合适的数据结构fillUnivList() 步骤3：将数据结构内容写入文件writeUlistfile() 步骤4：利用数据结构内容输出结果printUniverList()

步骤1：从网络上获取网页内容getHTMLText()

import requests

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

步骤2：提取网页中的数据信息到合适的数据结构fillUnivList()

from bs4 import BeautifulSoup

def fillUnivList(html, ulist):
    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])

步骤3：将数据结构内容写入文件writeUlistfile()

def writeUlistfile(ulist):
    with open('univlist.txt', 'w', encoding='utf-8') as f:
        for i in range(len(ulist)):
            f.write('{:<10}\t{:<10}\t{:<10}\n'.format(ulist[i][0], ulist[i][1], ulist[i][2]))

步骤4：利用数据结构内容输出结果printUniverList()

def printUniverList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))

完整代码：

import requests
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 fillUnivList(html, ulist):
    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 writeUlistfile(ulist):
    with open('univlist.txt', 'w', encoding='utf-8') as f:
        for i in range(len(ulist)):
            f.write('{:<10}\t{:<10}\t{:<10}\n'.format(ulist[i][0], ulist[i][1], ulist[i][2]))

def printUniverList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2017.html'
    html = getHTMLText(url)
    fillUnivList(html, uinfo)
    writeUlistfile(uinfo)
    printUniverList(uinfo, 20)     # 前20所大学

main()