Python爬虫requests库和BeatifulSoup库对中国大学排名定向爬虫源码实例

import requests
from bs4 import BeautifulSoup
import bs4

#获取所有网页内容
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:    
        return ""   #错误返回空列表
#获取所有大学排名信息
def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    #获取tbody所有子标签，即所有tr标签
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            #tr标签中查找所有tb标签
            tds = tr('td')
            #按照需求添加tb标签的非属性字符串
            ulist.append([tds[0].string,tds[1].string,tds[3].string])
#格式化打印大学排名信息
def printUnivList(ulist,num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    #chr(12288)表示实例不够时用中文空格格式填充
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo = []
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

if __name__ == "__main__":
    main()