【tkinter】模板 + 如何制作一个百度爬虫软件？

桃扇骨 2022-09-11 13:17 204阅读 0赞

### 文章目录 ###

*   *  1、多级窗口的显示以及我的模板
     *  2、单个窗口模板
     *  3、单个窗口模板2（李xinpeng）
     *  4、百度图片爬虫软件模板

## 1、多级窗口的显示以及我的模板 ##

import os.path
    import tkinter as tk
    from PIL import Image, ImageTk
    from pandas import read_excel, DataFrame
    from tkinter.scrolledtext import ScrolledText
    from tkinter import filedialog as fd
    import tkinter.messagebox
    
    
    # 打开指定图片，缩放至自定尺寸
    def get_image(filename, width, height):
        im = Image.open(filename).resize((width, height))
        return ImageTk.PhotoImage(im)
    
    
    class RootWindow:
        def __init__(self, master):
            self.master = master
    
            for i in range(num_win):
                self.new_button(title1, f'{ i}', win_list[i], int((bg_width - bt_width) / 2),
                                int(bg_height * (0.9 / num_win * i + 0.1)),
                                bt_width, bt_height)
    
        # x, y, width, height 分别代表button的左上角放置位置xy和按钮的长宽
        def new_button(self, text, number, _class, x, y, width, height):
            btnNew = tk.Button(self.master, text=text, font=('Arial', 14), bg='#84bf96', compound=tk.CENTER,
                               command=lambda: self.new_window(number, _class))
            btnNew.place(x=x, y=y, width=width, height=height)
    
        def new_window(self, number, class_):
            # Toplevel（顶级窗口）组件类似于 Frame 组件，但 Toplevel 组件是一个独立的顶级窗口，
            # 这种窗口通常拥有标题栏、边框等部件，和 Tk() 创建出来的根窗口是一样的，共享着一样的方法。
            self.new = tk.Toplevel(self.master)
            class_(self.new, number)
    
    
    # 小窗口的父类
    class Win:
        def __init__(self, master, number):
            self.sub_bg_width = 900
            self.sub_bg_height = 600
            self.master = master
            self.master.geometry(f"{ self.sub_bg_width}x{ self.sub_bg_height}+800+100")
            self.master.resizable(False, False)
            self.master.iconbitmap("./8字标.ico")
    
            # 这里是程序的输出窗口
            self.t = ScrolledText(self.master, height=34, width=83)
            # text最后pack
            self.t.place(x=297, y=130)
            # 输出结果对比表
            self.file_compare = DataFrame(columns=list(range(1, 23)), index=list(range(1, 23)))
    
            # self.master.resizable(False, False)
    
            # self.frame = tk.Frame(self.master)
            # self.frame.pack()
    
        # self.quit = tk.Button(self.master, text=f"退出窗口{number}", font=('Arial', 14), bg='#84bf96', compound=tk.CENTER,
        # command=self.close_window)
        # self.quit.pack()
        #
        # def close_window(self):
        # self.master.destroy()
        # 获取文件夹地址
        def dir_path_get(self, _var_change):
            dir_in_path = fd.askdirectory()
            _var_change.set(dir_in_path)
    
        def file_path_get(self, _var_change):
            file_in_path = fd.askopenfilename()
            _var_change.set(file_in_path)
    
        def judge_input(self, _input, input_type, _default='./'):
            ''' 判断输入是否合法 :param self: :param _input: 输入 :param input_type: 输入类型 :param _default: 默认输入 :return: '''
            if input_type == 'file':
                result = os.path.isfile(_input)
                if not result:
                    self.t.insert(tk.END, "错误：请输入正确的文件路径！\n\n")
                    self.t.update()
                    tk.messagebox.showerror('错误', '请输入正确的文件路径！')
    
                else:
                    return _input
            else:
                result = os.path.isdir(_input)
                if not result:
                    self.t.insert(tk.END, "将使用默认文件夹路径\n\n")
                    self.t.update()
                    return _default
                else:
                    return _input
    
    
    # 小窗口1
    # 对比两个研究方向相同的论文的个数
    class Win1(Win):
        def __init__(self, master, number):
            super().__init__(master, number)
            # self.master.geometry("900x600+200+200")
            self.meg = tk.Message(self.master, font=('Arial', 14), width=250,
                                  text="程序相关介绍：\n\n 1、该程序的作用是对比两个研究方向相同的论文的个数，输出分别为same.xls（相同文献表）"
                                       "、different1.xls（文件1的不同文献表）、different2.xls（文件2的不同文献表）\n\n"
                                       " 2、请输入将要对比的两个文件。默认输出路径为程序所在目录文件夹下。\n\n"
                                       " 3、在程序运行过程中，会在右边窗口显示程序运行状态\n\n"
                                       " 4、运行方法：点击目录按钮选择地址或在输入栏中直接输入。然后点击运行开始运行程序。")
            self.meg.place(x=20, y=130)
    
            # 输入框1
            self.var_in1 = tk.StringVar()
            self.var_in1.set('请在此处输入文件1的地址')
            self.entry_in1 = tk.Entry(self.master, textvariable=self.var_in1, font=('Arial', 14), width=42)
            self.entry_in1.place(x=20, y=10)
    
            # 地址输入按钮1
            self.but_in1 = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                     compound=tk.CENTER, command=lambda: self.file_path_get(self.var_in1))
            self.but_in1.place(x=540, y=10)
    
            # 输入框2
            self.var_in2 = tk.StringVar()
            self.var_in2.set('请在此处输入文件2的地址')
            self.entry_in2 = tk.Entry(self.master, textvariable=self.var_in2, font=('Arial', 14), width=42)
            self.entry_in2.place(x=20, y=50)
    
            # 地址输入按钮2
            self.but_in2 = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                     compound=tk.CENTER, command=lambda: self.file_path_get(self.var_in2))
            self.but_in2.place(x=540, y=50)
    
            # 输出框
            self.var_out = tk.StringVar()
            self.var_out.set('请在此处输入输出文件的文件夹地址')
            self.entry_out = tk.Entry(self.master, textvariable=self.var_out, font=('Arial', 14), width=42)
            self.entry_out.place(x=20, y=90)
    
            # 地址输出按钮
            self.but_out = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                     compound=tk.CENTER, command=lambda: self.dir_path_get(self.var_out))
            self.but_out.place(x=540, y=90)
    
            # 程序运行按钮
            self.but_start = tk.Button(self.master, text='运 行', font=('Arial', 22), bg='#84bf96', width=8, height=2,
                                       compound=tk.CENTER, command=self.excel_deal)
            self.but_start.place(x=670, y=20)
    
            self.master.mainloop()
    
        # -----------------------------------------------------------------------------------------
        # 1对比两个研究方向相似的文件个数
        def excel_deal(self):
            try:
                self.t.insert(tk.END, '---------------------------------------\n')
    
                input_1 = self.judge_input(self.var_in1.get(), 'file')
    
                input_2 = self.judge_input(self.var_in2.get(), 'file')
    
                store_path = self.judge_input(self.var_out.get(), 'dir')
    
                file_1 = read_excel(input_1)
                file_2 = read_excel(input_2)
                dataframe_1 = DataFrame(file_1)
                dataframe_2 = DataFrame(file_2)
    
                title_1 = list(dict.values(dataframe_1.to_dict()["Article Title"]))
                title_2 = list(dict.values(dataframe_2.to_dict()["Article Title"]))
    
                same = []
                different_1 = list(range(len(title_1)))
                different_2 = list(range(len(title_2)))
                for i in range(len(title_1)):
                    for j in range(len(title_2)):
                        if title_1[i] == title_2[j]:
                            same.append(i)
                            different_1.remove(i)
                            different_2.remove(j)
    
                file_column1 = [x for x in dataframe_1]
                file_column2 = [x for x in dataframe_2]
    
                file_same = DataFrame(columns=file_column1)
                file_different_1 = DataFrame(columns=file_column1)
                file_different_2 = DataFrame(columns=file_column2)
    
                for i in range(len(same)):
                    file_same.loc[i] = dataframe_1.loc[same[i]].tolist()
    
                for i in range(len(different_1)):
                    file_different_1.loc[i] = dataframe_1.loc[different_1[i]].tolist()
    
                for i in range(len(different_2)):
                    file_different_2.loc[i] = dataframe_2.loc[different_2[i]].tolist()
    
                file_same.to_excel(os.path.join(store_path, 'same.xls'), index=False)
                file_different_1.to_excel(os.path.join(store_path, 'different_1.xls'), index=False)
                file_different_2.to_excel(os.path.join(store_path, 'different_2.xls'), index=False)
    
                self.t.insert(tk.END, f'相同文献的个数为:{ len(same)}\n\n')
                self.t.insert(tk.END,
                              f'文件1和文件2相同部分保存为了same.xls，不同部分，属于文件1的保存为了different1.xls。不同部分，属于文件2的保存为了different2.xls\n\n')
                self.t.insert(tk.END, '程序运行结束！\n\n')
                self.t.see(tk.END)
                self.t.update()
            except:
                self.t.insert(tk.END, '程序报错！请检查输入文件！\n\n')
    
    
    # 小窗口2
    # 对比同一文件夹下所有学科之间的交叉数 excel_compare
    class Win2(Win):
        def __init__(self, master, number):
            super().__init__(master, number)
            # self.master.geometry("900x600+200+200")
            self.meg = tk.Message(self.master, font=('Arial', 14), width=250,
                                  text="程序相关介绍：\n\n 1、该程序对比了同一文件夹下所有学科之间的交叉数，输出为一"
                                       "个关于各个学科交叉数目的表格 file_compare.xls\n\n"
                                       " 2、默认的输入路径为程序所在目录文件夹下的data文件夹，默认输出路径为程序所在目录文件夹下。\n\n"
                                       " 3、在程序运行过程中，会依次将不为零的结果显示在右边窗口。\n\n"
                                       " 4、运行方法：点击目录按钮选择地址或在输入栏中直接输入。然后点击运行开始运行程序。")
            self.meg.place(x=20, y=130)
    
            # 输入框
            self.var_in = tk.StringVar()
            self.var_in.set('请在此处输入输入文件夹的地址')
            self.entry_in = tk.Entry(self.master, textvariable=self.var_in, font=('Arial', 14), width=42)
            self.entry_in.place(x=20, y=30)
    
            # 地址输入按钮
            self.but_in = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                    compound=tk.CENTER, command=lambda: self.dir_path_get(self.var_in))
            self.but_in.place(x=540, y=30)
    
            # 输出框
            self.var_out = tk.StringVar()
            self.var_out.set('请在此处输入输出文件的文件夹地址')
            self.entry_out = tk.Entry(self.master, textvariable=self.var_out, font=('Arial', 14), width=42)
            self.entry_out.place(x=20, y=80)
    
            # 地址输出按钮
            self.but_out = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                     compound=tk.CENTER, command=lambda: self.dir_path_get(self.var_out))
            self.but_out.place(x=540, y=80)
    
            # 程序运行按钮
            self.but_start = tk.Button(self.master, text='运 行', font=('Arial', 22), bg='#84bf96', width=8, height=2,
                                       compound=tk.CENTER, command=self.excel_compare)
            self.but_start.place(x=670, y=20)
    
            self.master.mainloop()
    
        # -----------------------------------------------------------------------------------------
        # 2对比同一文件夹下所有学科之间的交叉数
        def excel_compare(self):
            try:
                self.t.insert(tk.END, '---------------------------------------\n')
    
                root = self.judge_input(self.var_in.get(), 'dir', './data')
    
                store_path = self.judge_input(self.var_out.get(), 'dir', './')
    
                for i in os.listdir(root):
                    for j in os.listdir(root):
                        self.deal_excel(i, j, root)
                self.file_compare.to_excel(os.path.join(store_path, "./file_compare.xls"))
                self.t.insert(tk.END, '程序运行结束！')
                self.t.see(tk.END)
                self.t.update()
    
            except:
                self.t.insert(tk.END, '程序报错！请检查输入文件！\n\n')
    
        def deal_excel(self, file1, file2, root):
            file_1 = read_excel(os.path.join(root, file1))
            file_2 = read_excel(os.path.join(root, file2))
    
            dataframe_1 = DataFrame(file_1)
            dataframe_2 = DataFrame(file_2)
    
            title_1 = list(dict.values(dataframe_1.to_dict()["Article Title"]))
            title_2 = list(dict.values(dataframe_2.to_dict()["Article Title"]))
    
            same = []
            different_1 = list(range(len(title_1)))
            different_2 = list(range(len(title_2)))
            for i in range(len(title_1)):
                for j in range(len(title_2)):
                    if title_1[i] == title_2[j]:
                        same.append(i)
                        different_1.remove(i)
                        different_2.remove(j)
    
            file_column1 = [x for x in dataframe_1]
            file_column2 = [x for x in dataframe_2]
    
            file_same = DataFrame(columns=file_column1)
            file_different_1 = DataFrame(columns=file_column1)
            file_different_2 = DataFrame(columns=file_column2)
    
            for i in range(len(same)):
                file_same.loc[i] = dataframe_1.loc[same[i]].tolist()
    
            for i in range(len(different_1)):
                file_different_1.loc[i] = dataframe_1.loc[different_1[i]].tolist()
    
            for i in range(len(different_2)):
                file_different_2.loc[i] = dataframe_2.loc[different_2[i]].tolist()
    
            file_same.to_excel('same.xls', index=False)
            file_different_1.to_excel('different_1.xls', index=False)
            file_different_2.to_excel('different_2.xls', index=False)
    
            if len(same) != 0:
                self.t.insert(tk.END, "-" * 20)
                self.t.insert(tk.END, '\n')
                self.t.insert(tk.END, "文件1:{} , 文件2:{}".format(file1, file2))
                self.t.insert(tk.END, '\n')
                self.t.insert(tk.END, "相同的数目为：{}".format(len(same)))
                self.t.insert(tk.END, '\n')
                self.t.see(tk.END)
                self.t.update()
    
            file1_num = int(file1[0:2])
            file2_num = int(file2[0:2])
            self.file_compare.loc[file1_num][file2_num] = len(same)
    
    
    # 小窗口3
    # 计算出研究方向编号1和研究方向编号2两列中各个不同学科的数目 def excel_cal_elem
    class Win3(Win):
        def __init__(self, master, number):
            super().__init__(master, number)
            self.meg = tk.Message(self.master, font=('Arial', 14), width=250,
                                  text="程序相关介绍：\n\n"
                                       " 1、该程序计算了研究方向编号1和研究方向编号2两列中各个不同学科的数目 并将结果制表，存为count.xls\n\n"
                                       " 2、请输入文件路径。默认的输出路径为程序所在目录文件夹下。\n\n"
                                       " 3、在程序运行过程中，会依次将预览表格输出在右边窗口。\n\n"
                                       " 4、运行方法：点击目录按钮选择地址或在输入栏中直接输入。然后点击运行开始运行程序。")
            self.meg.place(x=20, y=130)
    
            # 输入框
            self.var_in = tk.StringVar()
            self.var_in.set('请在此处输入文件的地址')
            self.entry_in = tk.Entry(self.master, textvariable=self.var_in, font=('Arial', 14), width=42)
            self.entry_in.place(x=20, y=30)
    
            # 地址输入按钮
            self.but_in = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                    compound=tk.CENTER, command=lambda: self.file_path_get(self.var_in))
            self.but_in.place(x=540, y=30)
    
            # 输出框
            self.var_out = tk.StringVar()
            self.var_out.set('请在此处输入输出文件的文件夹地址')
            self.entry_out = tk.Entry(self.master, textvariable=self.var_out, font=('Arial', 14), width=42)
            self.entry_out.place(x=20, y=80)
    
            # 地址输出按钮
            self.but_out = tk.Button(self.master, text='目录', font=('Arial', 10), bg='#84bf96', width=6,
                                     compound=tk.CENTER, command=lambda: self.dir_path_get(self.var_out))
            self.but_out.place(x=540, y=80)
    
            # 程序运行按钮
            self.but_start = tk.Button(self.master, text='运 行', font=('Arial', 22), bg='#84bf96', width=8, height=2,
                                       compound=tk.CENTER, command=self.excel_cal_elem)
            self.but_start.place(x=670, y=20)
    
            self.master.mainloop()
    
        # -----------------------------------------------------------------------------------------
        # 3计算出研究方向编号1和研究方向编号2两列中各个不同学科的数目
        def excel_cal_elem(self):
            try:
                self.t.insert(tk.END, '---------------------------------------\n')
    
                file_path = self.judge_input(self.var_in.get(), 'file')
                store_path = self.judge_input(self.var_out.get(), 'dir')
    
                file = read_excel(file_path)
                dataframe = DataFrame(file)
                dataframe = dataframe.fillna(int(0))
    
                title1 = list(dict.values(dataframe.to_dict()["研究方向编号1"]))
                title2 = list(dict.values(dataframe.to_dict()["研究方向编号2"]))
    
                count = DataFrame(columns=["研究方向编号1", "研究方向编号2"], index=[range(1, 23)])
    
                for i in range(1, 23):
                    count.loc[i] = [0, 0]
    
                for j in [0, 1]:
                    if j == 0:
                        for i in title1:
                            count.iloc[int(i), j] += 1
                    else:
                        for i in title2:
                            count.iloc[int(i), j] += 1
    
                count.to_excel(os.path.join(store_path, "count.xls"))
                self.t.insert(tk.END, "列的元素个数表:\n")
                self.t.insert(tk.END, count)
                self.t.insert(tk.END, '\n\n')
                self.t.insert(tk.END, '程序运行结束！\n\n')
                self.t.see(tk.END)
                self.t.update()
    
            except:
                self.t.insert(tk.END, '程序报错！请检查输入文件！\n\n')
    
    
    if __name__ == '__main__':
        # 子窗口数
        num_win = 3
        # 子窗口列表
        win_list = [Win1, Win2, Win3]
    
        bg_width = 640
        bg_height = 360
        bt_width = 400
        bt_height = 50
    
        # 窗体一的名字
        title1 = "对比两个excel中的相同论文数并输出"
        # 窗体二的名字
        title2 = "多个excel相同论文数横向对比，并画表"
        # 窗体三的名字
        title3 = "excel列的元素个数计算"
        window = tk.Tk()
        window.title("文献对比处理软件 作者：xxx")
        window.geometry(f"{ bg_width}x{ bg_height}+100+100")
        # 不能被调整大小
        window.resizable(False, False)
        # 设置窗口图标
        window.iconbitmap("./8字标.ico")
    
        canvas = tk.Canvas(window, width=bg_width, height=bg_height)
        # image_file = tk.PhotoImage(file='new.gif')
        im_window = get_image('1.jpg', bg_width, bg_height)
        canvas.create_image(bg_width / 2, bg_height / 2, image=im_window)
        canvas.pack()
    
        self = RootWindow(window)
        window.mainloop()

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16]  
![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 1]

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 2]  
![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 3]

## 2、单个窗口模板 ##

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 4]

## 3、单个窗口模板2（李xinpeng） ##

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 5]

## 4、百度图片爬虫软件模板 ##

![在这里插入图片描述][watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 6]

[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16]: /images/20220828/dadff3d7360a43a09129866c5c86b793.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 1]: /images/20220828/ca7ee1ee4fed4b3889437ecc6d07648c.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 2]: /images/20220828/af6ed6bf2e04485890b412a985cdc4f5.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 3]: /images/20220828/7f1e9da0b7ea44818fbbf8d120ffc910.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 4]: /images/20220828/9935badb8ce745709051011db850fbed.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 5]: /images/20220828/a645ef867cd14f269a63457290a68c5f.png
[watermark_type_ZHJvaWRzYW5zZmFsbGJhY2s_shadow_50_text_Q1NETiBAbWlyYWNsZW9f_size_20_color_FFFFFF_t_70_g_se_x_16 6]: /images/20220828/d64157f0917447fdaec75f79869b88c2.png