BeautifulSoup

BeautifulSoup库

Beautiful Soup库是解析、遍历、维护“标签树”的功能库，对应一个HTML/XML文档的全部内容

BeautifulSoup库的安装

pip install beautifulsoup4

实战：中国大学排名定向爬取

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLTest(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')
            ulist.append([tds[0].string,tds[1].string,tds[3].string])

def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    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 = getHTMLTest(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()

结果展示