中国大学排名（网络爬虫信息提取）

最新推荐文章于 2024-09-19 23:38:37 发布

ur_ytii

最新推荐文章于 2024-09-19 23:38:37 发布

阅读量2.8k

点赞数 9

分类专栏： Python

本文链接：https://blog.csdn.net/ur_ytii/article/details/97931311

版权

Python 专栏收录该内容

12 篇文章 2 订阅

订阅专栏

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')
            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.cn/zuihaodaxuepaiming2016.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()

优化后的：

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')
            ulist.append(tds[0].string,tds[1].string,tds[2].string)

def printUnivList(ulist,num):
    tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
    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.cn/zuihaodaxuepaiming2016.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()