Python Tkinter 项目实例：小说在线阅读器(爬虫部分已过期)

1，项目概况
项目名称：
小说在线阅读器
项目需求：
1，根据关键字检索，实现从互联网获取所需链接。
2，对获取的链接进行解析，获取二级链接，获取的链接以文件的形式保存。
3，实现小说在线阅读。
所需技术：
Python基本爬虫，Python tkinter GUI设计
2，项目代码：

from fake_useragent import UserAgent
from bs4 import BeautifulSoup as Bp
import tkinter as tk
import tkinter.messagebox
import requests as req
import re
import os
#弹出窗口提示，说明使用须知。
tkl = tk.Tk()
tkl.title('验证窗口')
tkl.geometry('250x100')
tkinter.messagebox.showinfo(title='使用须知',message='''1,本软件需要连接网络才能够正常使用，使用本软件时请先连接网络！\n2,本软件仅供学习交流使用，请勿私自传播！\n3,鉴于本人水平有限，本软件若有不足之处，望见谅。\n4,在软件获取链接或者解析时请勿操作软件，否则可能会导致软件无响应！''')
tlable = tk.Label(tkl,text='阅读须知后请关闭此窗口!!!',font=('Arial',12))
tlable.pack()
tkl.mainloop()
#创建主窗口
app = tk.Tk()
app.title('小说搜索解析阅读器v1.0')
app.geometry('800x600')

lable = tk.Label(app,text='请输入关键字',font=('Arial',12))
lable.pack()
#定义搜索框
search_entry = tk.Entry(app,show=None,width=50)
search_entry.pack()

#定义功能函数
def getdata():
    st.delete(1.0,tk.END)
    url = 'http://www.biquge.info/modules/article/search.php'
    #伪装头部
    ua = UserAgent()
    header = {'User-Agent':ua.random}
    key = search_entry.get()
    #爬取链接
    try:
        r = req.post(url,{'searchkey':key},headers=header)
    except Exception as e:
        tkinter.messagebox.showinfo(title='警告！',message='获取链接失败，请点击按钮重试！')
        return
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    re_list = []
    soup = Bp(r.text,'html.parser')
    data = soup.find_all('a')
    for item in data:
        try:
            if re.findall(key,item.text):
                re_list.append(item.text + ':' + 'http://www.biquge.info' + item['href'])
        except:
            continue
    if not re_list:
        st.insert('insert','没有发现！')
    dvar = '-*---------------------*-\n请在下面复制要解析的链接，注意：一次只能解析一条\n' + '\n'.join(re_list)
    st.insert('insert',dvar)
    return

#定义按钮实现功能
search_button = tk.Button(app,text='获取链接',width=12,
                          height=2,command=getdata)
search_button.pack()

lable1 = tk.Label(app,text='链接显示区域',font=('Arial',12))
lable1.pack()

st = tk.Text(app,width=80,height=5)
st.pack()

lable2 = tk.Label(app,text='请输入链接',font=('Arial',12))
lable2.pack()

read_entry = tk.Entry(app,show=None,width=80)
read_entry.pack()
#定以函数，用以实现相关按钮功能
def readlink():
    url = read_entry.get()
    try:
        rd = req.get(url)
        rd.raise_for_status()
        rd.encoding = rd.apparent_encoding
        soup = Bp(rd.text,'html.parser')
        readdata = soup.find_all('a')
        read_re_data = []
        for item in readdata:
            try:
                if 'html' in item['href'] and 'http' not in item['href']:
                    read_re_data.append(url + item['href'])
                else:
                    continue
            except:
                continue
        with open('read.txt','w') as wfile:
            wfile.write('\n'.join(read_re_data))
            wfile.close()
    except:
        tkinter.messagebox.showinfo(title='警告', message='发生错误，请重试！')
    return

read_button = tk.Button(app,text='解析',width=12,
                          height=2,command=readlink)
read_button.pack()
#readapp用于设置阅读窗口
def readapp():
    readapp = tk.Tk()
    readapp.title('阅读界面')
    readapp.geometry('1000x800')

    lable = tk.Label(readapp,text='阅读界面',font=('Arial',12))
    lable.pack()
    if not os.path.exists('read.txt'):
        tkinter.messagebox.showinfo(title='错误',message='未找到文件！')
        readapp.destroy()
        return
    with open('page.tmp','w') as file:
        file.write('1')
        file.close()
    def downd():
        if not os.path.exists('page.tmp'):
            tkinter.messagebox.showinfo(title='错误', message='请重试！')
        rf = open('page.tmp','r')
        page = int(eval(rf.read()))
        page += 1
        rf.close()
        page_str = str(page)
        rfs = open('page.tmp','w')
        rfs.write(page_str)
        rfs.close()
        readt.delete(1.0,tk.END)
        rfile = open('read.txt', 'r')
        url = rfile.readlines()
        rfile.close()
        readr = req.get(url[page][:-1:])
        readr.raise_for_status()
        readr.encoding = readr.apparent_encoding
        soup = Bp(readr.text, 'html.parser')
        data = soup.find_all('div', id='content')
        for item in data:
            readt.insert('insert', item.text)
        return
    def upd():
        if not os.path.exists('page.tmp'):
            tkinter.messagebox.showinfo(title='错误', message='请重试！')
        rf = open('page.tmp', 'r')
        page = int(eval(rf.read()))
        rf.close()
        if page <= 1:
            tkinter.messagebox.showinfo(title='错误', message='没有上一章了！')
            return
        page -= 1
        page_str = str(page)
        rfs = open('page.tmp', 'w')
        rfs.write(page_str)
        rfs.close()
        readt.delete(1.0, tk.END)
        rfile = open('read.txt', 'r')
        url = rfile.readlines()
        rfile.close()
        readr = req.get(url[page][:-1:])
        readr.raise_for_status()
        readr.encoding = readr.apparent_encoding
        soup = Bp(readr.text, 'html.parser')
        data = soup.find_all('div', id='content')
        for item in data:
            readt.insert('insert', item.text)
        return

    button1 = tk.Button(readapp,text='上一章',width=10,height=2,command=upd)
    button1.pack()

    button2 = tk.Button(readapp,text='下一章',width=10,height=2,command=downd)
    button2.pack()

    readt = tk.Text(readapp, width=120, height=50)
    rfile = open('read.txt','r')
    url = rfile.readlines()
    rfile.close()
    readr = req.get(url[1][:-1:])
    readr.raise_for_status()
    readr.encoding = readr.apparent_encoding
    soup = Bp(readr.text,'html.parser')
    data = soup.find_all('div',id='content')
    for item in data:
        readt.insert('insert',item.text)
    readt.pack()

    readapp.mainloop()

read_button1 = tk.Button(app,text='阅读',width=12,
                         height=2,command=readapp)

read_button1.pack()

app.mainloop()

3，项目效果：