第一个爬虫和测试

一、比赛的完善，测试函数。

#对gameover函数判断测试
def gameOver(a,b):
    if (a>=25 and abs(a-b)>=2 )or(b>=25 and abs(a-b)>=2):
        return True
    else:
        return False
    ai=[]
    bi=[]
    try:
        for a,b in ((25,25),(26,25),(27,26),(29,25)):
            if gameOver(a,b):
                ai.append(a)
                bi.append(b)
    except:
        print('Error')
        print(ai)
        print(bi)
#对simOneGame(proA,proB)函数进行测试
try:
    probA,probB=0.5,0.5
    scoreA,scoreB=0,0
    serving = "A"
    if serving == "A":
        if random() < probA:
            scoreA += 1
        else:
            serving="B"
    else:
        if random() < probB:
            scoreB += 1
        else:
            serving="A"
    print(scoreA) 
    print(scoreB)
except:
    print('Error')
    
 #对simNGames(n, probA, probB)进行测试  
try:
    n,scoreA,scoreB=1,24,26
    winsA, winsB = 0, 0
    scoreA_ls=[]
    scoreB_ls=[]
    for i in range(n):
        scoreA_ls.append(scoreA)
        scoreB_ls.append(scoreB)
        if scoreA > scoreB:
            winsA += 1
        else:
            winsB += 1
    print(winsA, winsB,scoreA_ls,scoreB_ls)
except:
    print('Error')  

　　

二、 用requests库的get（）函数访问Google主页20遍，打印返回状态，text（）内容，计算text（）属性和content（）属性所返回网页内容的长度。

import requests
from bs4 import BeautifulSoup
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        soup=BeautifulSoup(r.text)
        r.raise_for_status()
        r.encoding='utf-8'
        return r.text,r.status_code,len(r.text),r.encoding,len(soup.text)
    except:
        return ""   
url="http://www.google.cn/"
for i in range(20):
    print(i)
    print(getHTMLText(url))

　　结果如下：