【Python】爬虫

import requests
from bs4 import BeautifulSoup  
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)  #得url响应结果
        r.raise_for_status() 
        r.encoding = r.apparent_encoding  #设置为网页对应编码
        return r.text  
    except:  
        return ""


def fillPlayList(plist, html):
    soup = BeautifulSoup(html, "html.parser")  
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag): 
            tds = tr('td')  
            plist.append([tds[0].string, tds[1].string, tds[2].string])  
    pass


def printPlayList(plist, num):
    for i in range(num):
        p = plist[i]  
        print("{:^10}{:^10}{:^10}".format(p[0], p[1], p[2]))


def main():
    pinfo = []
    url = 'http://nba.hupu.com/stats/players'
    html = getHTMLText(url) 
    fillPlayList(pinfo, html) 
    printPlayList(pinfo, 21)  


if __name__ == '__main__':
main()