一、完善球賽程式，測驗球賽程式，
將代碼末尾稍作改動即可，若代碼正確，則運行，否則輸出Error，
from random import random
#列印程式介紹資訊
def printIntro():
print("19信計2班23號鄧若言")
print("這個程式模擬兩個選手A和B的乒乓球比賽")
print("程式運行需要A和B的能力值（以0到1之間的小數表示）")
#獲得程式運行引數
def printInputs():
a = eval(input("請輸入選手A的能力值(0-1): "))
b = eval(input("請輸入選手B的能力值(0-1): "))
n = eval(input("模擬比賽的場次: "))
return a, b, n
# 進行N場比賽
def simNGames(n, probA, probB):
winsA, winsB = 0, 0
for i in range(n):
for j in range(7): #進行7局4勝的比賽
scoreA, scoreB = simOneGame(probA, probB)
if scoreA > scoreB:
winsA += 1
else:
winsB += 1
return winsA,winsB
#進行一場比賽
def simOneGame(probA, probB):
scoreA, scoreB = 0, 0 #初始化AB的得分
serving = "A"
while not gameOver(scoreA, scoreB): #用while回圈來執行比賽
if scoreA==10 and scoreB==10:
return(simOneGame2(probA,probB))
if serving == "A":
if random() < probA: ##用亂數生成勝負
scoreA += 1
else:
serving="B"
else:
if random() < probB:
scoreB += 1
else:
serving="A"
return scoreA, scoreB
def simOneGame2(probA,probB):
scoreA,scoreB=10,10
serving = "A"
while not gameOver2(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
#比賽結束
def gameOver(a,b): #正常比賽結束
return a==11 or b==11
def gameOver2(a,b): #進行搶12比賽結束
if abs((a-b))>=2:
return a,b
#輸出資料
def printSummary(winsA, winsB):
n = winsA + winsB
print("競技分析開始，共模擬{}場比賽".format(n))
print("選手A獲勝{}場比賽，占比{:0.1%}".format(winsA, winsA/n))
print("選手B獲勝{}場比賽，占比{:0.1%}".format(winsB, winsB/n))
#主體函式
def main():
printIntro()
probA, probB, n = printInputs()
winsA, winsB = simNGames(n, probA, probB)
printSummary(winsA, winsB)
try:
main()
except:
print("Error!")
結果如下：
則測驗得代碼無誤，
二、用requests庫的get()函式訪問必應搜狗主頁20次，列印回傳狀態，text內容，并且計算text（）屬性和content屬性回傳網頁內容的長度，
關于requests庫的內容可戳以下鏈接
https://www.cnblogs.com/deng11/p/12863994.html
import requests
for i in range(20):
r=requests.get("https://www.sogou.com",timeout=30) #網頁鏈接可換
r.raise_for_status()
r.encoding='utf-8'
print('狀態={}'.format(r.status_code))
print(r.text)
print('text屬性長度{}，content屬性長度{}'.format(len(r.text),len(r.content)))
結果如下（取20次中的其中一次，text屬性內容太長所以不展示出來）：
三、根據所給的html頁面，保持為字串，完成如下要求：
（1）列印head標簽內容和你學號的后兩位
（2）獲取body標簽的內容
（3）獲取id的first的標簽物件
（4）獲取并列印html頁面中的中文字符
<!DOCTYPE html> <html> <head> <meta charset="utf-8"> <title>菜鳥教程(runoob.com)</title> </head> <body> <h1>我的第一個標題</h1> <p id="first">我的第一個段落，</p> </body> <table border="1"> <tr> <td>row 1, cell 1</td> <td>row 1, cell 2</td> </tr> </table> </html>
代碼如下：
from bs4 import BeautifulSoup r = ''' <!DOCTYPE html> <html> <head> <meta charset="utf-8"> <title>菜鳥教程(runoob.com) 23號的作業</title> </head> <body> <h1>我的第一個標題</h1> <p id="first">我的第一個段落，</p> </body> <table border="1"> <tr> <td>row 1, cell 1</td> <td>row 1, cell 2</td> </tr> </table> </html> ''' demo = BeautifulSoup(r,"html.parser") print(demo.title) print(demo.body) print(demo.p) print(demo.string)
效果如下：
四、爬取中國大學排名（年費2016），將資料存為csv檔案，
import requests
from bs4 import BeautifulSoup
ALL = []
def getHTMLtext(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = 'utf-8'
return r.text
except:
return ""
def fillUni(soup):
data = https://www.cnblogs.com/deng11/p/soup.find_all('tr')
for tr in data:
td1 = tr.find_all('td')
if len(td1) == 0:
continue
Single = []
for td in td1:
Single.append(td.string)
ALL.append(Single)
def printUni(num):
print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^6}{5:{0}^6}{6:{0}^6}{7:{0}^6}{8:{0}^6}{9:{0}^5}{10:{0}^6}{11:{0}^6}{12:{0}^6}{13:{0}^6}".format(chr(12288),"排名","學校名稱","省市","總分",\
"生源質量","培養結果","科研規模","科研質量",\
"頂尖成果","頂尖人才","科技服務",\
"產學研究合作","成果轉化"))
for i in range(num):
u = ALL[i]
print("{1:^4}{2:{0}^10}{3:{0}^6}{4:{0}^8}{5:{0}^9}{6:{0}^9}{7:{0}^7}{8:{0}^9}{9:{0}^7}{10:{0}^9}{11:{0}^8}{12:{0}^9}{13:{0}^9}".format(chr(12288),u[0],\
u[1],u[2],eval(u[3]),\
u[4],u[5],u[6],u[7],u[8],\
u[9],u[10],u[11],u[12]))
def main(num):
url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
html = getHTMLtext(url)
soup = BeautifulSoup(html,"html.parser")
fillUni(soup)
printUni(num)
main(10)
效果：
將爬取到的資料存為csv檔案，只需將printUni()函式換掉，
改動后的代碼如下：
import requests
from bs4 import BeautifulSoup
import csv
import os
ALL = []
def getHTMLtext(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = 'utf-8'
return r.text
except:
return ""
def fillUni(soup):
data = https://www.cnblogs.com/deng11/p/soup.find_all('tr')
for tr in data:
td1 = tr.find_all('td')
if len(td1) == 0:
continue
Single = []
for td in td1:
Single.append(td.string)
ALL.append(Single)
def writercsv(save_road,num,title):
if os.path.isfile(save_road):
with open(save_road,'a',newline='')as f:
csv_write=csv.writer(f,dialect='excel')
for i in range(num):
u=ALL[i]
csv_write.writerow(u)
else:
with open(save_road,'w',newline='')as f:
csv_write=csv.writer(f,dialect='excel')
csv_write.writerow(title)
for i in range(num):
u=ALL[i]
csv_write.writerow(u)
title=["排名","學校名稱","省市","總分","生源質量","培養結果","科研規模","科研質量","頂尖成果","頂尖人才","科技服務","產學研究合作","成果轉化"]
save_road="C:\\Users\\鄧若言\\Desktop\\html.csv"
def main(num):
url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
html = getHTMLtext(url)
soup = BeautifulSoup(html,"html.parser")
fillUni(soup)
writercsv(save_road,num,title)
main(10)
效果：
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/146928.html
標籤：Python
上一篇：Python--字串操作
下一篇：怎么反爬蟲爬取網站資訊