爬虫之爬取最好大学排名实例

爬取链接：http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html
程序设计结构：
1.获取大学排名网页内容 getHTMLText()
2.提取网页内容中信息到合适的数据结构 fillUnivList()
3.利用数据结构展示并输出结果 printUnivList()

完整代码 Python3.7 pycharm

import requests
from bs4 import  BeautifulSoup
import bs4


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(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds=tr('td')#等价于tr.find_all（'td')
            ulist.append([tds[0].string,tds[1].string,tds[2].string])
def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校","地区"))
    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/zuihaodaxuepaiming2019.html"
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

if __name__ == '__main__':
    main()

中文对齐格式优化：

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

修改为

def printUnivList(ulist, num):
    print("{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名", "学校", "地区",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(u[0], u[1], u[2],chr(12288)))

修改过程中可能出现 IndexError: tuple index out of range
所以上下一定对齐，chr()是在format 里面，以及其写法。