python爬虫入门---第二篇：获取2019年中国大学排名

import requests
from bs4 import BeautifulSoup
import bs4

def get_html_text(url):
    ‘‘‘返回网页的HTML代码‘‘‘
    try:
        res = requests.get(url, timeout = 6)
        res.raise_for_status()
        res.encoding = res.apparent_encoding
        return res.text
    except:
        return ‘‘

def fill_ulist(ulist, html):
    ‘‘‘将我们所需的数据写入一个列表ulist‘‘‘

    #解析HTML代码，并获得解析后的对象soup
    soup = BeautifulSoup(html, ‘html.parser‘)
    #遍历得到第一个<tbody>标签
    tbody = soup.tbody
    #遍历<tbody>标签的孩子，即<tbody>下的所有<tr>标签及字符串
    for tr in tbody.children:
        #排除字符串
        if isinstance(tr, bs4.element.Tag):
            #使用find_all()函数找到tr标签中的所有<td>标签
            u = tr.find_all(‘td‘)
            #将<td>标签中的字符串内容写入列表ulist
            ulist.append([u[0].string, u[1].string, u[2].string, u[3].string])

def display_urank(ulist):
    ‘‘‘格式化输出大学排名‘‘‘
    print("{:^10}\t{:^10}\t{:^10}\t{:^10}".format("排名", "大学名称", "省市", "总分"))
    for u in ulist:
        print("{:^10}\t{:^10}\t{:^10}\t{:^10}".format(u[0], u[1], u[2], u[3]))

def write_in_file(ulist, file_path):
    ‘‘‘将大学排名写入文件‘‘‘
    with open(file_path, ‘w‘) as file_object:
        file_object.write("{:^5}\t{:^6}\t{:^10}\t{:^10}\n".format("排名", "大学名称", "省市", "总分"))
        for u in ulist:
            file_object.write("{:^5}\t{:^6}\t{:^10}\t{:^10}\n".format(u[0], u[1], u[2], u[3]))

def main():
    ‘‘‘主函数‘‘‘
    ulist = []
    url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html‘
    file_path = ‘university rankings.txt‘
    html = get_html_text(url)
    fill_ulist(ulist, html)
    display_urank(ulist)
    write_in_file(ulist, file_path)

main()