第一个爬虫和测试

Posted 2020-12-06 zhangsijie

完善球赛程序并测试

#羽毛球比赛分析及测试
#每局双方打到20平后，一方领先2分即算该局获胜；若双方打成29平后，一方领先1分，即算该局取胜。
from random import random
def printIntro():
    print("这个程序模拟两个选手A和B的羽毛球比赛")
    print("程序运行需要A和B的能力值（以0到1之间的小数表示）")
def getInputs():
    a = eval(input("请输入选手A的能力值(0-1): "))
    b = eval(input("请输入选手B的能力值(0-1): "))
    n = eval(input("模拟比赛的场次: "))
    return a, b, n
def simNGames(n, probA, probB):
    winsA, winsB = 0, 0
    for i in range(n):
        scoreA, scoreB = simOneGame(probA, probB)
        if scoreA > scoreB:
            winsA += 1
        else:
            winsB += 1
    return winsA, winsB

try:
     simNGames(0.55)        #测试
except:
     print("simNGames Error")
 
def gameOver(a,b): 
    if a>=20 and b>=20: 
        if abs(a-b)==2: 
            return True 
    if a>29 or b>29: 
        if a==30 or b==30: 
            return True 
    else: 
        return False 
        
def simOneGame(probA, probB):
    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

try:
     simOneGame(0.54)           #测试
except:
     print("simNGame Error")
     
def printSummary(winsA, winsB):
    n = winsA + winsB
    print("竞技分析开始，共模拟{}场比赛".format(n))
    print("选手A获胜{}场比赛，占比{:0.1%}".format(winsA, winsA/n))
    print("选手B获胜{}场比赛，占比{:0.1%}".format(winsB, winsB/n))
def main():
    print(48)
    printIntro()
    probA, probB, n = getInputs()
    winsA, winsB = simNGames(n, probA, probB)
    printSummary(winsA, winsB)
main()

用requests的get0函数访问搜狗搜索主页20次，打印返回状态，text0内容，计算 text0属性和content属性所返回网页内容的长度。

import requests
def gethtmlText(url):
    try:
       r = requests.get(url, timeout=30)
       r.raise_for_status()
       r.encoding = ‘utf-8‘
       return r.text
    except:
        return ""
    
url = "http://www.sogou.com/"
print(getHTMLText(url))

爬取中国大学排名网站

import requests
from bs4 import BeautifulSoup
allUniv = []
def getHTMLText(url):
    try:
        r = requests.get(url, 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}^6}{4:{0}^4}{5:{0}^10}".format(chr(12288),"排名","学校名称","省市","总分","年费"))
    for i in range(num):
        u=allUniv[i]
        print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^11}".format(chr(12288),u[0],u[1],u[2],eval(u[3]),u[11]))
def main():
    url = ‘http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html‘
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(10)
main()