Python编写GUI界面案例：实现免费下载器

前言

嗨喽~大家好呀，这里是魔王呐 ❤ ~!

本次网站：

本文所有模块\环境\源码\教程皆可点击文章下方名片获取此处跳转

开发环境:

python 3.8 运行代码
pycharm 2022.3 辅助敲代码

模块使用：

import parsel >>> pip install parsel
import requests >>> pip install requests

如何安装python第三方模块:

win + R 输入 cmd 点击确定, 输入安装命令 pip install 模块名 (pip install requests) 回车
在pycharm中点击Terminal(终端) 输入安装命令

思路

一、数据来源分析

明确需求:

采集的网站是什么?

采集的数据是什么?

标题/内容
分析标题/内容是从哪里来的

通过浏览器自带工具: 开发者工具抓包分析

打开开发者工具: F12 / 鼠标右键点击检查选择network

刷新网页

搜索数据, 找到数据包

二. 代码实现

发送请求, 模拟浏览器对于url地址发送请求
获取数据, 获取服务器返回响应数据内容

开发者工具: response
解析数据, 提取我们想要的数据内容

标题/内容
保存数据, 把数据保存本地文件

代码实现

有个视频教程给大家录好啦，但是C站放不上来

源码资料电子书: 点击此处跳转文末名片获取

一、单章小说下载

发送请求
获取数据

import requests
url = '网站链接'
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
print(response)
# print(response.text)

解析数据

import re 
import parsel 

selector = parsel.Selector(response.text)
title = selector.xpath('//*[@class="bookname"]/h1/text()').get()
content = '\n'.join(selector.xpath('//*[@id="content"]/text()').getall())
print(title)
print(content)

保存数据

with open(title + '.txt', mode='a', encoding='utf-8') as f:

"""
第一章 标题
    小说内容
第二章 标题
    小说内容
"""

f.write(title)
f.write('\n')
f.write(content)
f.write('\n')

二、整本小说下载

import requests
import re
import parsel
import os
 
 
list_url = ''
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
html_data = requests.get(url=list_url, headers=headers).text
name = re.findall('<h1>(.*?)</h1>', html_data)[0]
file = f'{name}\\'
if not os.path.exists(file):
    os.mkdir(file)
 
url_list = re.findall('<dd> <a style="" href="(.*?)">', html_data)
for url in url_list:
    index_url = '网址' + url
    print(index_url)

    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
    }
    response = requests.get(url=index_url, headers=headers)
    print(response)

    selector = parsel.Selector(response.text)
    title = selector.xpath('//*[@class="bookname"]/h1/text()').get()
    content = '\n'.join(selector.xpath('//*[@id="content"]/text()').getall())
    print(title)

with open(file + title + '.txt', mode='a', encoding='utf-8') as f:

    """
    第一章 标题
        小说内容
    第二章 标题
        小说内容
    """

f.write(title)
f.write('\n')
f.write(content)
f.write('\n')

三、多线程采集

import requests
import re
import parsel
import os
import concurrent.futures

def get_response(html_url):

"""
发送请求函数
:param html_url: 请求链接
:return: response响应对象
"""

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
response = requests.get(url=html_url, headers=headers)
return response

def get_list_url(html_url):

"""
获取章节url/小说名
:param html_url: 小说目录页
:return:
"""

html_data = get_response(html_url).text
name = re.findall('<h1>(.*?)</h1>', html_data)[0]
url_list = re.findall('<dd> <a style="" href="(.*?)">', html_data)
return name, url_list

def get_content(html_url):

"""
获取小说内容/小说标题
:param html_url: 小说章节url
:return:
"""

html_data = get_response(html_url).text
title = re.findall('<h1>(.*?)</h1>', html_data)[0]
content = re.findall('<div id="content">(.*?)<p>', html_data, re.S)[0].replace('<br/><br/>', '\n')
return title, content

def save(name, title, content):

"""
保存数据函数
:param name: 小说名
:param title: 章节名
:param content: 内容
:return:
"""

file = f'{name}\\'
if not os.path.exists(file):
    os.mkdir(file)
with open(file + title + '.txt', mode='a', encoding='utf-8') as f:

    """
    第一章 标题
        小说内容
    第二章 标题
        小说内容
    """

        f.write(title)
        f.write('\n')
        f.write(content)
        f.write('\n')
    print(title, '已经保存')
 
 
def main(home_url):
    title, content = get_content(html_url=home_url)
    save(name, title, content)
 
 
if __name__ == '__main__':
    url = ''
    name, url_list = get_list_url(html_url=url)
    exe = concurrent.futures.ThreadPoolExecutor(max_workers=7)
    for url in url_list:
        index_url = '网址' + url
        exe.submit(main, index_url)
    exe.shutdown()

四、采集排行榜所有小说

import requests
import re
import parsel
import os

def get_response(html_url):

"""
发送请求函数
:param html_url: 请求链接
:return: response响应对象
"""

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
response = requests.get(url=html_url, headers=headers)
return response

def get_list_url(html_url):

"""
获取章节url/小说名
:param html_url: 小说目录页
:return:
"""

    html_data = get_response(html_url).text
    name = re.findall('<h1>(.*?)</h1>', html_data)[0]
    url_list = re.findall('<dd> <a style="" href="(.*?)">', html_data)
    return name, url_list
 
 
def get_content(html_url):

"""
获取小说内容/小说标题
:param html_url: 小说章节url
:return:
"""

html_data = get_response(html_url).text
title = re.findall('<h1>(.*?)</h1>', html_data)[0]
content = re.findall('<div id="content">(.*?)<p>', html_data, re.S)[0].replace('<br/><br/>', '\n')
return title, content

def save(name, title, content):

"""
保存数据函数
:param name: 小说名
:param title: 章节名
:param content: 内容
:return:
"""

file = f'{name}\\'
if not os.path.exists(file):
    os.mkdir(file)
with open(file + title + '.txt', mode='a', encoding='utf-8') as f:

    """
    第一章 标题
        小说内容
    第二章 标题
        小说内容
    """

    f.write(title)
    f.write('\n')
    f.write(content)
    f.write('\n')
print(title, '已经保存')

"""
获取小说ID
:param html_url: 某分类的链接
:return:
"""

def get_novel_id(html_url):
    novel_data = get_response(html_url=html_url).text
    selector = parsel.Selector(novel_data)
    href = selector.css('.l .s2 a::attr(href)').getall()
    href = [i.replace('/', '') for i in href]
    return href
 
 
def main(home_url):
    href = get_novel_id(html_url=home_url)
    for novel_id in href:
        novel_url = f'网址/{novel_id}/'
        name, url_list = get_list_url(html_url=novel_url)
        print(name, url_list)
        for url in url_list:
            index_url = '' + url
            title, content = get_content(html_url=index_url)
            save(name, title, content)
        break
 
 
if __name__ == '__main__':
    html_url = ''
    main(html_url)

五、搜索小说功能

模块

import requests
import re
import parsel
import os
import prettytable as pt

发送请求函数

def get_response(html_url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
    }
    response = requests.get(url=html_url, headers=headers)
    return response

获取章节url/小说名

def get_list_url(html_url):
    html_data = get_response(html_url).text
    name = re.findall('<h1>(.*?)</h1>', html_data)[0]
    url_list = re.findall('<dd> <a style="" href="(.*?)">', html_data)
    return name, url_list

获取小说内容/小说标题

def get_content(html_url):
    html_data = get_response(html_url).text
    title = re.findall('<h1>(.*?)</h1>', html_data)[0]
    content = re.findall('<div id="content">(.*?)<p>', html_data, re.S)[0].replace('<br/><br/>', '\n')
    return title, content

保存数据函数

def save(name, title, content):
    file = f'{name}\\'
    if not os.path.exists(file):
        os.mkdir(file)
    with open(file + name + '.txt', mode='a', encoding='utf-8') as f:
        f.write(title)
        f.write('\n')
        f.write(content)
        f.write('\n')
    print(title, '已经保存')

获取小说ID

def get_novel_id(html_url):
    novel_data = get_response(html_url=html_url).text
    selector = parsel.Selector(novel_data)
    href = selector.css('.l .s2 a::attr(href)').getall()
    href = [i.replace('/', '') for i in href]
    return href

搜索功能

def search(word):
    search_url = f'网址/searchbook.php?keyword={word}'
    search_data = get_response(html_url=search_url).text
    selector = parsel.Selector(search_data)
    lis = selector.css('.novelslist2 li')
    novel_info = []
    tb = pt.PrettyTable()
    tb.field_names = ['序号', '书名', '作者', '书ID']
    num = 0
    for li in lis[1:]:
        name = li.css('.s2 a::text').get()
        novel_id = li.css('.s2 a::attr(href)').get().replace('/', '')
        writer = li.css('.s4::text').get()
        dit = {
            'name': name,
            'writer': writer,
            'novel_id': novel_id,
        }
        tb.add_row([num, name, writer, novel_id])
        num += 1
        novel_info.append(dit)
    print('你搜索的结果如下:')
    print(tb)
    novel_num = input('请输入你想要下载的小说序号: ')
    novel_id = novel_info[int(novel_num)]['novel_id']
    return novel_id

主函数

def main(word):
    novel_id = search(word)
    novel_url = f'网址/{novel_id}/'
    name, url_list = get_list_url(html_url=novel_url)
    print(name, url_list)
    for url in url_list:
        index_url = '网址' + url
        title, content = get_content(html_url=index_url)
        save(name, title, content)
        
if __name__ == '__main__':
    word = input('请输入你搜索小说名: ')
    main(word)

六、GUI界面

import tkinter as tk
from tkinter import ttk
 
def show():
    name = name_va.get()
    print('输入的名字是:', name)
 
def download():
    name = num_va.get()
    print('输入的序号:', name)
 
root = tk.Tk()
root.title('完整代码添加VX：python5180 ')
root.geometry('500x500+200+200')
name_va = tk.StringVar()

search_frame = tk.Frame(root)
search_frame.pack(pady=10)

tk.Label(search_frame, text='书名 作者', font=('微软雅黑', 15)).pack(side=tk.LEFT, padx=10)
tk.Entry(search_frame, relief='flat', textvariable=name_va).pack(side=tk.LEFT)
 
num_va = tk.StringVar()

download_frame = tk.Frame(root)
download_frame.pack(pady=10)
tk.Label(download_frame, text='小说 序号', font=('微软雅黑', 15)).pack(side=tk.LEFT, padx=10)
tk.Entry(download_frame, relief='flat', textvariable=num_va).pack(side=tk.LEFT)
button_frame = tk.Frame(root)
button_frame.pack(pady=10)
tk.Button(button_frame, text='查询', font=('微软雅黑', 10), relief='flat', bg='#88e2d6', width=10, command=show).pack(side=tk.LEFT, padx=10)
tk.Button(button_frame, text='下载', font=('微软雅黑', 10), relief='flat', bg='#88e2d6', width=10, command=download).pack(side=tk.LEFT, padx=10)
 
columns = ('num', 'writer', 'name', 'novel_id')
columns_value = ('序号', '作者', '书名', '书ID')
tree_view = ttk.Treeview(root, height=18, show='headings', columns=columns)
tree_view.column('num', width=40, anchor='center')
tree_view.column('writer', width=40, anchor='center')
tree_view.column('name', width=40, anchor='center')
tree_view.column('novel_id', width=40, anchor='center')
tree_view.heading('num', text='序号')
tree_view.heading('writer', text='作者')
tree_view.heading('name', text='书名')
tree_view.heading('novel_id', text='书ID')
tree_view.pack(side=tk.LEFT, fill=tk.BOTH, expand=True)
root.mainloop()