上半年在學bs4時的一個爬蟲,主要是針對table標籤的,可用於爬取其他類似網站,程式碼比較好更改

# -*- coding: utf-8 -*-
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")
    #soup.find('tbody').children是列表迭代型別,而如果是soup.find('tbody')則是標籤
    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])
            print(ulist)

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