爬虫

# -*- coding: utf-8 -*-
"""
Created on Thu May 23 00:41:48 2019

@author: h2446
"""

from random import random
def printIntro():
    print("这个程序模拟两支排球队A和B的排球比赛")
    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("请输入队伍A的能力值(0~1):"))
    b=eval(input("请输入队伍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):
        if (a>25 and abs(a-b)>=2 )or(b>25 and abs(a-b)>=2):
            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
def final(probA,probB):
     winsA,winsB=simNGames1(4,probA,probB)
     printSummary(winsA,winsB)
     if not winsA==3 or winsB==3:
         if winsA==winsB==2:
             winsA1,winsB1=simOneGame1(probA,probB)
             finalprintSummary(winsA,winsB)
     else:
         finalprintSummary(winsA,winsB)
def simNGames1(n,probA,probB):
     winsA,winsB=0,0
     for i in range(n):
         scoreA,scoreB=simOneGame2(probA,probB)
         if winsA==3 or winsB==3:
             break
         if scoreA>scoreB:
             winsA+=1
         else:
             winsB+=1
     return winsA,winsB
def simOneGame2(probA,probB):
     scoreA,scoreB=0,0
     serving="A"
     while not GG(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 simOneGame1(probA,probB):
    scoreA,scoreB=0,0
    serving="A"
    while not finalGameOver(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 GG(a,b):
    return a==3 or b==3
def finalGameOver(a,b):
     if (a==8 or b==8):
         if a>b:
             print("A队获得8分，双方交换场地")
         else:
             print("B队获得8分，双方交换场地")
     if (a>15 and abs(a-b)>=2 )or(b>15 and abs(a-b)>=2):
         return True
     else:
         return False
def finalprintSummary(winsA,winsB):
     n=winsA+winsB
     if n>=4:
         print("进行最终决赛")
         if winsA>winsB:
             print("最终决赛由A获胜")
         else:
             print("最终决赛由B获胜")
     else:
            if winsA>winsB:
                print("最终决赛由A获胜")
            else:
                print("最终决赛由B获胜")
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():
        printIntro()
        probA,probB,n=getInputs()
        winsA,winsB=simNGames(n,probA,probB)
        printSummary(winsA,winsB)
        final(probA,probB)
try:
    main()
except:
    print("Error")

 

 爬虫百度

import requests
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding='utf-8'
        print(r.status_code)
        print(r.text)
        print(r.encoding)
        print(r.text)
    except:
        return ""
for i in range(0,20):
    url="https://www.baidu.com"
    getHTMLText(url)

 

 谷歌

import requests
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding='utf-8'
        print(r.status_code)
        print(r.text)
        print(r.encoding)
        print(r.text)
    except:
        return ""
for i in range(0,20):
    url="https://www.Google.com"
    getHTMLText(url)

 

HTML的书写

from bs4 import BeautifulSoup
 
html='''<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>菜鸟教程（runoob.com)</title> 
</head>
<body>
         <hl>我的第一个标题</hl>
         <p id="first">我的第一个段落。</p> 
</body>
                  <table border="1">
          <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>
</table>
</html>'''
 
soup= BeautifulSoup(html)
print(soup.head,"学号45")
print("网页head标签内容:\n",soup.head,"\nnumber:12\n")
print("网页body标签内容:\n",soup.body,"\n")
print("网页id为first的标签:\n",soup.p,"\n")
print("网页中的中文字符:\n",soup.title.string)
print(soup.hl.string)
print(soup.p.string,"\n")

 

 爬取大学排名

import requests
import pandas as pd
import numpy as np
from bs4 import BeautifulSoup
import sqlite3
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):
    with open(r'C:\Users\HP\AppData\Local\kingsoft\WPS Office\大学排名.csv','w') as f:
        f.write("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}\n".format((chr(12288)),"排名","学校名称","省市","总分"))
        for i in range(num):
            u=allUniv[i]
            f.write("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^8.1f}\n".format((chr(12288)),i+1,u[1],u[2],eval(u[3]),u[6]))
        f.close()
    if 1:
        print("successful")
    else:
        print("fail")

def main(num):
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2017.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)

main(20)