爬虫
一、完善球赛程序，测试球赛你程序、所有函数的测试结果：
from random import random
def printIntro():
print("这个程序模拟两个选手A和B的排球竞技比赛")
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
def gameOver(a,b):
return a==15 or b==15
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
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))
print("2019310143016 卢佳纯")
def main():
printIntro()
probA, probB, n = getInputs()
winsA, winsB = simNGames(n, probA, probB)
printSummary(winsA, winsB)
print("排球竞技比赛赛制规定：")
print("1.前4局比赛采用25分制，每个队只有赢得至少25分，并同时超过对方2分时，才胜1局；")
print("2.正式比赛采用5局3胜制，决胜局的比赛采用15分制，一队先得8分后，两队交换场区，按原位置顺序继续比赛到结束；")
print("3.在决胜局（第五局）之比赛，先获15分并领先对方2分为胜；")
main()
SRE实战 互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。
测试函数：
首先对GameOver(a,b)函数进行测试
再对simOneGame(proA,proB)函数进行测试
后对simNGames(n,proA,proB)函数进行测试
def GameOver(N,scoreA,scoreB):
if N<=4:
return(scoreA>=25 and scoreB>=25 and abs(scoreA-scoreB)>=2)
else:
return(scoreA>=15 and abs(scoreA-scoreB)>=2) or (scoreB>=15 and abs(scoreA-scoreB)>=2)
ai=[]
bi=[]
try:
for scoreA,scoreB in ((1,25),(1,26),(25,25),(16,17),(28,30)):
if GameOver(scoreA,scoreB):
ai.append(scoreA)
bi.append(scoreB)
except:
print('Error')
print(ai)
print(bi)
#对simOneGame(proA,proB)函数进行测试
from random import random
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)
try:
n,scoreA,scoreB=1,1,21
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)
print(scoreA_ls,scoreB_ls)
except:
print('Error')
二、用requests库的get()函数访问百度网站，打印返回状态，text（）内容，计算text()和content属性所返回的页面内容的长度：
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 = 'http://www.baidu.com.cn/'
print(getHTMLText(url))
结果为：
三、制作一个简单的html页面：a、获取body标签的内容；b、获取id为first的标签对象；c、获取并打印html页面中的中文字符
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>菜鸟教程（runoob.com）</title>
</head>
<body>
<b>第一个html页面————来自学号2019310143016</b><br><br>
<p id="first">制作者的基本信息：</p>
</body>
<table border="1">
<tr>
<td>班级</td>
<td>姓名</td>
<td>年级</td>
</tr>
<tr>
<td>信计1班</td>
<td>纯牛奶</td>
<td>19级</td>
</tr>
</table>
</html>
四、利用爬虫获取2017中国大学排名：
import requests
from bs4 import BeautifulSoup
import bs4
import pandas as pd
info = []#用来存放爬取信息
url ="http://www.zuihaodaxue.com/Greater_China_ranking2017_0.html"
try:
r=requests.get(url,timeout=100)
r.raise_for_status()
r.encoding=r.apparent_encoding
soup = BeautifulSoup(r.text,"html.parser")
for tr in soup.find("tbody").children:
if isinstance(tr,bs4.element.Tag):
tds=tr.find_all("td")
info.append([tds[0].string,tds[1].string,tds[3].string])
print("{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名","学校名称","总分",chr(12288)))
for i in range(50):
print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(info[i][0],info[i][1],info[i][2],chr(12288)))
name = ["排名","学校名称","总分"]
test = pd.DataFrame(columns=name,data=info)
test.to_csv(r"C:\code_python\test1.csv")
print("保存成功")
except Exception as e :
print(e)
更多精彩
