python之定向爬虫实例

第一步：打开python的IDLE（版本为python 3.7）

第二步：点击file-new file

第三步：输入如下代码，并点击run module就能看到结果

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","总分",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
        # print("Suc" + str(num))
 
 
def main():
    uinfo = []
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo,20) # 20 unives
main()