第一个简单的python爬虫：爬取ATP男子网球世界排名

#Tennis.py
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 fillTennisListMan(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('table',attrs={"cellspacing": 1}).children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[2].string, tds[3].string])

def printTennisListMan(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
    
def main():
    uinfoman = []
    urlman = 'http://www.8tennis.com/rank-atp/'
    print("ATP当前排名:")
    htmlman = getHTMLText(urlman)
    fillTennisListMan(uinfoman, htmlman)
    printTennisListMan(uinfoman, 21) # 21 univs
    
main()