嵩天老师在B站上的课程部分源代码1

中国大学定向爬虫代码

# _*_ coding:utf-8 _*_
# 开发时间：2020/2/18 15:02
# 文件名称：Chinese_university_ranking.py
# 开发工具：PyCharm
import requests
from bs4 import BeautifulSoup
import bs4

def get_html_text(url):
    """获取网页的内容"""
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ''

def fill_univ_list(ulist, html):
    """获取网页内容里面的特定信息"""
    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 print_univ_list(ulist, name):
    """打印出大学排名"""
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^16}"
    print(tplt.format('排名','大学名称','分数',chr(12288)))
    for i in range(name):
        uli = ulist[i]
        print("{0:^10}\t{1:{3}^15}\t{2:^10}".format(uli[0], uli[1], uli[2],chr(12288)))

    print('\t...\n'+'\t显示的大学数量为前' + str(name)+'名。')

def main():
    unifo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html = get_html_text(url)
    fill_univ_list(unifo, html)
    print_univ_list(unifo, 20)
    
main()

技术路线：request–bs4库