软件工程第七周理论与实践学习

一、理论学习

1、完成慕课第十章的相关学习

2、学习“设计和开发”

　　在需求分析阶段就应该对程序开发的框架有一个设计，这周在实践中明显感觉代码修改的地方比较多，扩展性非常不好，归根揭底就是最开始的设计没弄好，代码的框架搭的不够好，可见设计的重要性。

3、进一步熟悉UML建模

出口成诗顺序图

飞花令顺序图

二、实践学习

1、扩充诗词库

本周在上次129首的古诗基础上扩充了320首广为熟知的唐诗三百首，和之前采用一样的方式对网站的数据进行爬取存到本地txt文件再处理后导入数据库中。

 1 from urllib import  request,error
 2 from bs4 import BeautifulSoup
 3 
 4 if __name__ == '__main__':
 5 
 6     url = "https://so.gushiwen.org/gushi/tangshi.aspx"
 7 
 8     try:
 9 
10         req = request.Request(url)
11 
12         rsp = request.urlopen(req)
13 
14         html = rsp.read().decode()
15         soup=BeautifulSoup(html,'lxml')
16         html=soup.prettify()
17         div = soup.find_all('a',{'target':'_blank'})
18         div = div[1:-1]
19         name = div[0].string
20         f = open('D:\桌面\诗词库2.txt','w+',encoding='utf-8')
21         num = 1
22         for i in div:
23         #     print(i.string)
24         #     print(i.get('href'))
25             name = i.string
26             url = i.get('href')
27             req = request.Request('https://so.gushiwen.org'+url)
28             rsp = request.urlopen(req)
29             html = rsp.read().decode()
30             
31             soup=BeautifulSoup(html,'lxml')
32             html=soup.prettify()
33             div2 = soup.find('div',{'class':'contson'})
34             # print(div2.get('content'))
35             print(div2.get_text())
36             f.writelines([str(num),name,'\n',div2.get_text(),'\n'])
37             f.close
38             num+=1
39             
40     except error.URLError as e:
41         print("URLError:{0}".format(e.reason))
42         print("URLError:{0}".format(e))
43        
44 
45     except Exception as e:
46         print(e)

然后从把txt文件处理后导入数据库

import sys  
import re  
import os,time
import pymysql

conn = pymysql.connect(host='localhost', port=3306, user='root', passwd='newbegin',db='lsj',charset='utf8')
cur = conn.cursor(cursor=pymysql.cursors.DictCursor)

class WordCreate():
    def __init__(self,path):
        '''
        导入文件进行解析
        '''
        with open(path,encoding="utf-8") as file:
            content = file.read()
            
            x = re.findall(r'[（|(](.*?)[）|)]', content)
            print(x)
            for i in x:
                zifu = '('+i+')'
                content = content.replace(zifu,'')
                
            content = re.split(r'\d', content)
            content = [i for i in content if i != '']
            self.sc_list = []
            for i in content:
                weak_list = re.split(r'[、。；！？\n\s*]',i)
                weak_list = [i for i in weak_list if i != '']
                self.sc_list.append(weak_list)
        # print(self.sc_list)
    def OperationSql(self):
        num=130
        for i in self.sc_list:
            for _ in range(62-len(i)):  #导入诗词为62 导入赏析为61
                i.append('NULL')
                # print(len(i))
            
            num2 = 1
            for _ in range(61):
                sql = "UPDATE poetry SET yiwen_{}='{}' WHERE id ={}".format(num2, i[num2-1], num)
                print(sql)
                cur.execute(sql)
                num2 += 1
            # for _ in range(61):
            #     sql = "UPDATE poetry SET sentense_{}='{}' WHERE id ={}".format(num2, i[num2], num)
            #     print(sql)
            #     cur.execute(sql)
            #     num2 += 1
            conn.commit()
            num+=1
def main():
    
    generator = WordCreate('D:\桌面\诗词库-2-赏析.txt')  #选择合适的路径
    generator.OperationSql()
    
    
if __name__ == '__main__':
    main()