使用python爬蟲爬取最好大學網大學排名實例

使用requests庫和BeautifulSoup庫實現對最好大學網大學排名信息爬取

鏈接:http://www.zuihaodaxue.com/Greater_China_Ranking2019_0.html

代碼:

import requests
from bs4 import BeautifulSoup
import bs4

#從網絡上獲取大學排名網頁內容
def getHTMLText(url):
    try:
        r =requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#提取網頁內容中信息到合適的數據結構
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])

#利用數據結構展示並輸出結果
def printUnivList(ulist,num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","學校名稱","總分",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/Greater_China_Ranking2019_0.html'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

main()

本文為學習北京理工大學爬蟲mooc跟着敲得實例代碼.附上鏈接:https://www.bilibili.com/video/av9784617?from=search&seid=17441199644632730564