Python爬虫实现[中国最好大学排名2016]

中国最好大学排名网
http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html
输入:
url,num(打印行数)

输出:

三个函数:

#获取源码
def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status() #检查状态是否合法
        r.encoding = r.apparent_encoding #转码
        return r.text 
    except:
        return "" #返回空串

#用BeautifulSoap类写到列表里
def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser") #用html形式
    for tr in soup.find('tbody').children: #观察源码在tbody标签内的tr标签里面
        if isinstance(tr, bs4.element.Tag): #检查是否为bs4里的标签
            tds = tr('td') #将tr标签内有td标签的存到tds列表中
            ulist.append([tds[0].string, tds[1].string, tds[3].string]) #获取到string

#打印函数 num为打印行数
def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分")) #format的用法
    for i in range(num):
        u=ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

具体实现:

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[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=[] #列表
    url="http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()