初出茅庐----数据库的学习应用

初出茅庐----数据库的学习应用

一、SQList数据库的学习笔记

python3环境下，python自带SQList库，无需下载即可使用

1.数据库的使用流程

 

2.数据库的操作

（1）Connection对象

函数	描述
sqlite3.Connection.execute()	执行SQL语句
sqlite3.Connection.cursor()	返回游标对象
sqlite3.Connection.commit()	提交事务
sqlite3.Connection.rollback()	回滚事务
sqlite3.Connection.close()	关闭连接

（2）Cursor对象

函数	描述
close(...)	关闭游标
execute(...)	执行SQL语句
executemany(...)	重复执行多次SQL语句
executescript(...)	一次执行多条SQL语句
fetchall(...)	从结果集中返回所有行记录
fetchmany(...)	从结果集中返回多行记录
fetchone(...)	从结果集中返回一行记录

3.尝试使用

import sqlite3    #导入模块
def sql():
    connection=sqlite3.connect('example.db')#连接数据库
    c=connection.cursor()
    #创建表
    c.execute('''CREATE TABLE t1 (date text, trans text, symbol text, qty real, price real)''')
    #插入一条记录
    c.execute("INSERT INTO t1 VALUES ('2006-01-05','BUY', 'RHAT', 100, 35.14)")

    connection.commit()#提交当前事务，保存数据
    for row in c.execute('SELECT * FROM stocks ORDER BY price'):#查找数据
        print(row)

    connection.close()

sql()

结果如图所示

二、爬取大学排名

代码实现如下

# -*- coding: utf-8 -*-
"""
@author: xiayiLL
"""

import sqlite3
from pandas import DataFrame
class function:
    def __init__(s,dbName,tableName,data,e_columns,c_columns,Read_All=True):
        s.dbName=dbName
        s.tableName=tableName
        s.data=data
        s.e_columns=e_columns
        s.c_columns=c_columns
        s.Read_All=Read_All
        
    def creattable(s):
        connect=sqlite3.connect(s.dbName)
        connect.execute("CREATE TABLE {}({})".format(s.tableName,s.e_columns))
        connect.commit()
        connect.close()
    
    def destroytable(s):
        connect=sqlite3.connect(s.dbName)
        connect.execute("DROP TABLE {}".format(s.tableName))
        connect.commit()
        connect.close()
        
    def getdata(s):
        connect=sqlite3.connect(s.dbName)
        cursor=connect.cursor()
        cursor.execute("SELECT * FROM {}".format(s.tableName))
        dataList=cursor.fetchall()
        connect.close()
        return dataList
    
    def inserDataS(s):
        connect=sqlite3.connect(s.dbName)
        connect.executemany("INSERT INTO {} VALUES(?,?,?,?,?,?,?)".format(s.tableName), s.data)
        connect.commit()
        connect.close()
        
    def searchData(s,conditions,ifprint=True):
        connect=sqlite3.connect(s.dbName)
        cursor=connect.cursor()
        cursor.execute("SELECT * FROM {} WHERE {}".format(s.tableName, conditions))
        data=cursor.fetchall()
        cursor.close()
        connect.close()
        if ifprint:
            s.printData(data)
        return data
    
    def deleteData(s,conditions):
        connect=sqlite3.connect(s.dbName)
        connect.execute("DELETE FROM {} WHERE {}".format(s.tableName,conditions))
        connect.commit()
        connect.close()
        
    def printData(s,data):
        print("{1:{0}^3}{2:{0}<11}{3:{0}<4}{4:{0}<4}{5:{0}<5}{6:{0}<5}{7:{0}^5}".format(chr(12288),*s.c_columns))
        for i in range(len(data)):
            print("{1:{0}<4.0f}{2:{0}<10}{3:{0}<5}{4:{0}<6}{5:{0}<7}{6:{0}<8}{7:{0}<7.0f}".format(chr(12288),*data[i]))
            
    def run(s):
        try:
            s.creattable()
            print("创建数据库")
            s.inserDataS()
            print("表创建，数据插入")
        except Exception as e:
            print("Error: ", e)
            print("数据库已存在")
        if s.Read_All:
            s.printData(s.getdata())
            
def get_Data(f_Name):
    data=[]
    f=open(f_Name,'r',encoding='utf-8')
    for line in f.readlines():
        line=line.replace('
','')
        line=line.split(',')
        for i in range(len(line)):
            try:
                if line[i]=='':
                    line[i]='0'
                line[i]=eval(line[i])
            except:
                continue
        data.append(tuple(line))
    e_columns='Rank real,University text,Province text,Grade real,SourseQuality real,TrainingResult real,ResearchScale real'
    c_columns=["排名","学校名称","省市","总分","生涯质量","培养结果","人才培养总分"]
    return data[i:],e_columns,c_columns
    
def main():
    f_Name="E:\daxuepaiming_data.csv"
    data,e_columns,c_columns=get_Data(f_Name)
    dbName="E://university.db"
    tableName="university"
    SQL=function(dbName,tableName,data,e_columns,c_columns,False)
    SQL.run()
    print("查找数据项（University='广东技术师范大学'):")
    SQL.searchData("University='广东技术师范大学'",True)
    print("查找数据项并按照培养结果进行排序(Province='广东省'):")
    SQL.searchData("Province='广东'ORDER BY ResearchScale",True)
    Weight=[0.35,0.2,0.1,0.1,0.1,0.1,0.05]
    value,sum=[],0
    sample=SQL.searchData("Province='广东省'",False)
    for i in range(len(sample)):
        for j in range(len(Weight)):
            sum+=sample[i][4+j]*Weight[j]
        value.append(sum)
        sum=0
    university=[university[i] for university in sample]
    uv,tmp=[],[]
    for i in range(len(university)):
        tmp.append(university[i])
        tmp.append(value(i))
        uv.append(tmp)
        tmp=[]
    df=DataFrame(uv,columns=list(("大学","总分")))
    df=df.sort_values('总分')
    df.index=[i for i in range(1,len(uv)+1)]
    print("筛选【广东省】并按照培养结果进行大学排名的结果:
",df)
    SQL.deleteData("Province='北京市'")
    SQL.deleteData("Province='广东省'")
    SQL.deleteData("Province='山东省'")
    SQL.deleteData("Province='山西省'")
    SQL.deleteData("Province='江西省'")
    SQL.deleteData("Province='河南省'")
    print("删除数据成功!")
    SQL.printData(SQL.getdata())
    SQL.destroytable()
    print("表删除成功!")

main()    
    
    

结果如图所示