易知大学任务25 第一次爬虫与测试

（1）测试

simOneGame(probA,porbB)

def printIntroduce():
    print('学号39，This program simulates a game between two players,A and  B')
    print('Probability(a number between 0~1) is used')
try:
    printIntroduce()
except:
    print("error")

getInput()

def getInput():
    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):"))
 
    m=eval(input("比赛的局数："))
 
    n = eval(input("模拟比赛的场次:"))
    return a,b,m,n
try:
    getInput()
except:
    print("error")

View Code

3) printSummary(winsA,winsB)

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))
try:
    printSummary(6,4)
except:
    print("error")

View Code

4）simNGames(m,n,probA,proB)

def simNGames(m,n,probA,probB):

    winsA,winsB = 0,0
    wa,wb=0,0

    for i in range(n):
        for i in range(m):

            #scoreA,scoreB = simOneGame(probA,probB)
            scoreA,scoreB=probA,probB
            if scoreA > scoreB:
                wa += 1
            else:
                wb += 1

            if wa==2:
                winsA+=1
                wa,wb=0,0
                break
            if wb==2:
                winsB+=1
                wa,wb=0,0
                break
    return winsA,winsB

m=eval(input())
n=eval(input())
probA=eval(input())
probB=eval(input())
print(simNGames(m,n,probA,probB))

（2）访问网站20次

 1 import requests
 2 def gethtml(url):
 3     try:
 4         r=requests.get(url)
 5         r.raise_for_status()
 6         r.encoding='utf-8'
 7         return r.text,r.status_code,len(r.text),len(r.text),len(r.content)
 8     except:
 9         return ""
10     
11 url="https://cn.bing.com/"
12 for i in range(20):
13     print(i)
14     print(gethtml(url))

View Code

结果：

（3）html

from bs4 import BeautifulSoup
import re
soup=BeautifulSoup("<head><title>菜鸟教程(runoob.com)</title></head><body><h1>我的第一个标题</h1><p id=frist>我的第一个段落。</p></body><tr><td>row 1,cell 1</td><td>row 1,cell 2</td></tr><tr><td>row 2,cell 1</td><td>row 2,cell 2</td></tr></body></table>","html.parser")
print(soup.head,"08")   
print(soup.body)      
print(soup.find_all(id="china"))  
r=soup.text
pat = re.findall(u'[u1100-uFFFDh]+?',r)
print(pat)

（4）中国大学排名

import requests
from bs4 import BeautifulSoup
import pandas as pd
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("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","年费"))
    for i in range(num):
        u=allUniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))
    return u
        
def main(num):
    url='http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
    html=getHTMLText(url)
    soup=BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)    

def writecsv(list):
    name = ['排名', '学校名称', '省份', '总分', '生源质量（新生高考成绩得分）', '培养结果（毕业生就业率）', '社会声誉（社会捐赠收入·千元）', '科研规模（论文数量·篇）',
            '科研质量（论文质量·FWCI）', '顶尖成果（高被引论文·篇）', '顶尖人才（高被引学者·人）', '科技服务（企业科研经费·千元）', '成果转化（技术转让收入·千元）', '学生国际化（留学生比例）']
    name2 = ['a', 'b', 'c']
    test = pd.DataFrame(columns=name, data=list)
    test.to_csv(r'C:UserslenovoDesktop作业集合python编程作业craw.csv', encoding='gbk')

def main(num):
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    try:
        printUnivList(num)
    except:
        pass
main(560)

易知大学 任务25 第一次爬虫与测试

易知大学任务25 第一次爬虫与测试