第一个爬虫和测试

（1）完善球赛程序，测试你写的球赛程序

from random import random

def printIntro():
    try:
        print("模拟羽毛球比赛")
        print("学号：2019310143108")
    except:
        print("printIntro error!")
   
def getInputs():
    try:
        a = eval(input("A的能力值："))
        b = eval(input("B的能力值："))
        n = eval(input("场次："))
        return a,b,n
    except:
        print("getInputs error!")

def gameOver(scoreA,scoreB):
    try:
        return (max(scoreA,scoreB)==21 and min(scoreA,scoreB)<20) or \
               (max(scoreA,scoreB)==30) or \
               (scoreA>20 and scoreB>20 and abs(scoreA-scoreB)>1)
    except:
        print("gameOver error!")
     
def simOneGame(probA,probB):
    try:
        scoreA,scoreB = 0,0
        serving = "A"
        while not gameOver(scoreA,scoreB):
            if serving == "A":
                if random() < probA:
                    scoreA += 1
                else:
                    serving = "B"
            else:
                if random() < probB:
                    scoreB += 1
                else:
                    serving = "A"
        return scoreA,scoreB
    except:
        print("simOneGame error!")

def simNGame(n,probA,probB):
    try:
        winsA,winsB = 0,0
        for i in range(n):
            if winsA<(n//2)+1 and winsB<(n//2)+1:
                scoreA,scoreB = simOneGame(probA,probB)
                if scoreA > scoreB:
                    winsA += 1
                else:
                    winsB += 1
            else:
                break
        return winsA,winsB
    except:
        print("printIntro error!")
        
def printSummary(winsA,winsB):
    try:
        n = winsA + winsB
        if winsA > winsB:
            X = "A"
        else:
            X = "B"
        print("共模拟了{}场比赛".format(n))
        print("A获胜{}场，占比{:0.1%}".format(winsA,winsA/n))
        print("B获胜{}场，占比{:0.1%}".format(winsB,winsB/n))
        print("{}获胜".format(X))
    except:
        print("printSummary error!")

def main():
    printIntro()
    probA,probB,n = getInputs()
    winsA,winsB = simNGame(n,probA,probB)
    printSummary(winsA,winsB)

main()

正确结果：

错误结果：

（2）请用requests库的get()函数访问“360搜索主页”20次，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
def getHTMLText(url):
    try: 
        for i in range(0,20):                   
            r = requests.get(url, timeout=30)
        r.raise_for_status() 
        r.encoding = 'utf-8' 
        return r.status_code,r.text,r.content,len(r.text),len(r.content)
    except:
        return ""
url = "https://www.360.cn/?tn=80035161_1_dg"
print(getHTMLText(url))

返回状态：

返回网页内容的长度：

（4）爬中国大学排名网站内容

import requests
from bs4 import BeautifulSoup
allUniv = []
def getHTMLText(ur1):
    try:
        r = requests.get(ur1,timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""

def fillUnivList(soup):
    data = soup.find_all('tr')
    for tr in data:
        ltd = tr.find_all('td')
        if len(ltd) == 0:
            continue
        singleUniv = []
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
        
def printUnivList(num):
    print("{1:^2}{2:{0}^10}{3:{0}^4}{4:{0}^4}{5:{0}^10}".format\
          (chr(12288),"排名","学校名称","省市","总分","培养规模"))
    for i in range(num):
        u = allUniv[i]
        print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}".format\
              (chr(12288),u[0],u[1],u[2],eval(u[3]),u[6]))
        
def main(num):
    ur1 = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html"
    html = getHTMLText(ur1)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)
    
main(10)

只拿中国大学排名的前十所大学：