2021-02-16

北理工Python语言程序设计基础(第2版) 教材采用的学校比较多，第十章实例20，中国大学排名爬虫程序，因为网站改版，书上代码无法运行，过年没事根据新网站修改了一下程序，给需要的学生们参考。
import requests
from bs4 import BeautifulSoup
import re
allUniv = []
def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""
def fillUnivList(soup):
    data = soup.find_all('tr')
    for tr in range(1,len(data)):
        #ltd = tr.find_all('td')
        singleUniv = []
        #for td in ltd:
        for td in range(6):
            temp="".join(re.compile('[\d+(\.\d+)?(\u4e00-\u9fa5)]').findall(data[tr].contents[td].text))
            temp=re.sub("[()]","",temp)
            #singleUniv.append(td.string)
            singleUniv.append(temp)
        allUniv.append(singleUniv)
def printUnivList(num):
    #print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","培养规模"))
    print("{1:{0}>3}{2:{0}^9}{3:{0}^5}{4:{0}^5}{5:{0}^5}{6:{0}^4}".format(chr(12288),"排名","学校名称","省市","类型","总分","生源质量"))
    for i in range(num):
        u=allUniv[i]
        print("{1:>4}{2:{0}^10}{3:{0}^5}{4:{0}^5}{5:{0}^5}{6:{0}^8}".format(chr(12288),u[0],u[1],u[2],u[3],u[4],u[5]))
def main():
    url = 'https://www.shanghairanking.cn/rankings/bcur/201611'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(30)
main()