爬虫获取中国大学排行榜

使用了requests库和bs4库

import requests
from bs4 import BeautifulSoup
import bs4


def getHtmlText(url): #返回response类型的文本属性
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""


def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, 'html.parser')

    for tr in soup.find('tbody').children:  #这个选tbody是因为刚好这个标签把全部的排名信息罩起来了，.children是遍历的一种方式（只获得下一层），返回的是迭代类型，只能用在循环中
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string,tds[3].string,tds[4].string])


def printUnivlist(ulist, num):
    with open("中国大学排名.txt",'w+') as f:
        tplt="{0:{5}^10}\t{1:{5}^10}\t{2:{5}^10}\t{3:{5}^10}\t{4:{5}^10}"
        print(tplt.format("排名", "学校", "省份","学校类型","总分",chr(12288)))  #:^10的意思是，限定输出宽度为10，而且右对齐
        f.write((tplt+"\n").format("排名", "学校", "省份","学校类型","总分",chr(12288)))
        for i in range(num):
            u = ulist[i]
            f.write((tplt+"\n").format(u[0], u[1], u[2],u[3],u[4],chr(12288)))
            print(tplt.format(u[0], u[1], u[2],u[3],u[4],chr(12288)))
    print("Suc" + str(num))


def main():
    uinfo = []
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2020.html"
    html = getHtmlText(url)

    fillUnivList(uinfo, html)
    printUnivlist(uinfo, 40)

main()

效果如下图：