北京理工大学-Python网络爬虫与信息提取学习笔记06

中国大学排名定向爬虫

观察网站源代码

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 fillUnibList(ulist,html):
    soup=BeautifulSoup(html,'html.parser')
    print(soup.find_all(string='扬州'))
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):   #检测tr类型，不在定义中就过滤掉
            tds=tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[3].string])

def printUnibList(ulist,num):  #num为列出学校的数量
    tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format('排名','学校名称','总分',chr(12288)))  #che(12288)为中文空格
    for i in range(num):
        u=ulist[i]
        print(tpl.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo=[]
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html=getHTMLText(url)
    fillUnibList(uinfo,html)
    printUnibList(uinfo,20)

main()

ps：学习链接 https://www.icourse163.org/learn/BIT-1001870001?tid=1206951268#/learn/announce