python爬取笔趣阁小说（TK可视化）

  1 import requests
  2 from lxml import etree
  3 from pyquery import PyQuery as pq 
  4 import re
  5 import time
  6 from datetime import datetime
  7 from tkinter import *
  8 import threading
  9 from tkinter import messagebox
 10  
 11 #获取小说内容-------------------------------------------------------------
 12 def content(a):
 13     response=requests.get(a,headers=header)
 14     response.encoding = 'utf-8'    
 15         dom = etree.HTML(response.text)
 16     content3=dom.xpath('//*[@id="content"]/text()')
 17     b=''.join(content3).replace(u'\xa0','\r\n')
 18     return b
 19 #获取小说目录-------------------------------------------------------------
 20 def get_mulu_url(index_url):
 21     response=requests.get(index_url,headers=header).text
 22     dom=etree.HTML(response)
 23     for i in range(13,end+13):
 24         herf = dom.xpath('//*[@id="list"]/dl/dd['+str(i)+']/a/@href')        
 25         title =dom.xpath('//*[@id="list"]/dl/dd['+str(i)+']/a/text()')        
 26         index_name_list.append(title)
 27         index_list.append(herf)
 28     print('获取目录成功')
 29 #下载小说---------------------------------------------------------------
 30 def download():
 31     try:
 32         for i in range(0,len(index_list)):
 33             a=index_url+''.join(index_list[i])
 34             content(a)
 35             title_name=''.join(index_name_list[i])
 36             print()
 37             import codecs
 38             with codecs.open('F:\小说1.txt','a+',encoding='utf-8') as f:
 39             #file=open('F:\小说.txt','a+',)
 40                 f.write(title_name)
 41                 f.write('\r\n')
 42                 f.write(content(a))
 43                 f.write('\r\n')
 44             #print(index_list)
 45             #print('下载'+''.join(index_name_list[i]+'完成'))
 46            # del index_list[0]
 47            # del index_name_list[0]
 48            # title_name1=''.join(index_name_list[i])
 49             print('下载'+title_name+'章完成')
 50             var_size.set('下载'+title_name+'章完成')
 51             time.sleep(1)
 52         var_size.set('下载完成')
 53     except:
 54         r = messagebox.askokcancel('警告', '网站被检测')
 55         print('error')#pass
        
 56  
 57 #主函数 启动获取目录线程----------------------------------------------------
 58 def main():
 59     var_size.set('正在获取目录和章节')
 60     print('正在获取目录和章节')
 61     global  index_url
 62     index_url=E1.get()
 63     global end    
 64     end=E2.get()
 65     end=int(end)
 66     print(index_url)
 67     get_mulu_url(index_url)
 68     time.sleep(2)
 69     a=datetime.now()
 70     var_size.set('开始下载')    
 71     print('开始下载时间为',a)
 72     t.start()
 73 #调用线程--------------------------------------------------------------------------
 74 def one():
 75     test=E2.get()
 76     if test =='':
 77         r = messagebox.askokcancel('警告-warning', '书籍链接和章节不可为空！')
 78     else:
 79         t1.start()
 80         
 81 if __name__ == "__main__":
 82     app=Tk()
 83     app.title('小说下载器')
 84     app.geometry('370x200')
 85     v1 = StringVar()
 86     v2 = StringVar()    
 87     index_list=[]
 88     index_name_list=[]
 89     #index_url='https://www.qu.la/book/44121/'
 90     header={'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3695.400 SLBrowser/10.0.3710.400'}
 91     
 92     var_size = StringVar()
 93     var_ck = StringVar()    
 94     
 95     label3=Label(app,text='小说官网：https://www.qu.la/').pack()
 96     label4=Label(app,textvariable=var_size).pack()    
 97  
 98     E2 = Entry(app,textvariable=v2,bd=5)#章节
 99     E1 = Entry(app,textvariable=v1,bd=5)#小说网站
100     E2.pack()
101     E1.pack()
102     
103     t=threading.Thread(target=download)#下载
104     t1=threading.Thread(target=main)#获取目录    
105  
106     run=Button(app,text='开始下载',command=one).pack()
107     label3=Label(app,text='1.章节号  2.书籍链接').pack()
108     app.mainloop()
109  
110