Python 爬虫-获得大学排名

2017-07-29 23:20:24

主要技术路线：requests+bs4+格式化输出

import requests
from bs4 import BeautifulSoup

url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2017.html'

def gethtml(url):
    # 打开网页有风险，需要使用try-except语句进行风险控制
    kv = {'user-agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0'}
    try:
        r = requests.get(url,headers=kv)
        r.raise_for_status()   # 如果打开失败，则会抛出一个HttpError异常
        # encoding是从header中分析出来的编码方式，apparent_encoding是 从内容分析出的编码方式
        r.encoding=r.apparent_encoding
        return r
    except:
        print("打开失败")
        return -1

def gettext(r):
    soup = BeautifulSoup(r.text,'html.parser')
    #print(soup.prettify())
    tr = soup('tr')
    ls = list()
    lst = list()
    for i in range(4):
        th = tr[0]('th')
        lst.append(th[i].string)
    ls.append(lst)
    for i in range(1,len(tr)):
        td = tr[i]('td')
        lst=list()
        lst.append(i)
        for k in range(1,4):
            lst.append(td[k].string)
        ls.append(lst)
    return ls

def printtext(ls):
    for i in ls:
         print('{0:^10}\t{1:{3}^10}\t{2:^10}'.format(i[0],i[1],i[2],chr(12288)))

if __name__ =='__main__':
    r = gethtml(url)
    ls = gettext(r)
    printtext(ls)