Python pdf 文件拆分按页数，按文件大小

 在训练我的"大模型应用-玄助"（支持文本检查，文件翻译，人像转动漫，表格识别，语音合成）时，我发现自己的知识集合需要拆分成一个个小文件。而这个大模型应用的要求是，每个文件大小不能超过20M。在网上找了一圈，我发现大部分的PDF拆分工具都需要付费，最少的也要3元。于是我心想，既然如此，不如自己动手,代码如下：

   一、提供了一个简单的页面进行选择：

import PyPDF2
import tkinter as tk
from tkinter import filedialog
import os


class PDFSplitterApp1:
    def __init__(self, filepath):
        self.root = filepath
        self.root.title("PDF Splitter")

        self.input_filepath = tk.StringVar()
        self.output_folder = tk.StringVar()

        self.split_type = tk.StringVar()
        self.split_type.set("pages")  # 默认按页拆分

        self.split_value = tk.StringVar()
        self.split_value_label = tk.Label(filepath, text="拆分值:")
        self.split_value_label.pack()

        self.split_value_entry = tk.Entry(filepath, textvariable=self.split_value)
        self.split_value_entry.pack()

        self.split_options_label = tk.Label(filepath, text="选择拆分方式:")
        self.split_options_label.pack()

        self.pages_radio = tk.Radiobutton(filepath, text="按页拆分", variable=self.split_type, value="pages")
        self.pages_radio.pack()

        self.size_radio = tk.Radiobutton(filepath, text="按文件大小拆分 (MB)", variable=self.split_type, value="size")
        self.size_radio.pack()

        self.range_radio = tk.Radiobutton(filepath, text="按页码范围拆分", variable=self.split_type, value="range")
        self.range_radio.pack()

        self.input_label = tk.Label(filepath, text="选择要拆分的PDF文件:")
        self.input_label.pack()

        self.input_entry = tk.Entry(filepath, textvariable=self.input_filepath, width=40, state='readonly')
        self.input_entry.pack()

        self.browse_button = tk.Button(filepath, text="浏览", command=self.browse_file)
        self.browse_button.pack()

        self.output_label = tk.Label(filepath, text="选择保存的文件夹:")
        self.output_label.pack()

        self.output_entry = tk.Entry(filepath, textvariable=self.output_folder, width=40, state='readonly')
        self.output_entry.pack()

        self.browse_output_button = tk.Button(filepath, text="浏览", command=self.browse_output_folder)
        self.browse_output_button.pack()

        self.split_button = tk.Button(filepath, text="开始拆分", command=self.split_pdf)
        self.split_button.pack()

    def browse_file(self):
        file_path = filedialog.askopenfilename(filetypes=[("PDF files", "*.pdf")])
        self.input_filepath.set(file_path)

    def browse_output_folder(self):
        folder_path = filedialog.askdirectory()
        self.output_folder.set(folder_path)

    def split_pdf(self):
        input_filepath = self.input_filepath.get()
        output_folder = self.output_folder.get()
        split_value = self.split_value.get()

        # 添加检查，确保文件路径不为空
        if not input_filepath:
            tk.messagebox.showerror("错误", "请选择要拆分的PDF文件")
            return

        # 添加检查，确保文件存在
        if not os.path.isfile(input_filepath):
            tk.messagebox.showerror("错误", "选择的PDF文件不存在")
            return

        # 添加检查，确保输出文件夹不为空
        if not output_folder:
            tk.messagebox.showerror("错误", "请选择保存的文件夹")
            return

        # 添加检查，确保拆分值不为空
        if not split_value:
            tk.messagebox.showerror("错误", "请输入拆分值")
            return

        try:
            split_value = int(split_value)
            if split_value <= 0:
                raise ValueError("拆分值必须为正整数")
        except ValueError as e:
            tk.messagebox.showerror("错误", f"无效的拆分值：{str(e)}")
            return

        pdf_reader = PyPDF2.PdfReader(input_filepath)

        if self.split_type.get() == "pages":
            self.split_by_pages(pdf_reader, output_folder, split_value)
        elif self.split_type.get() == "size":
            self.split_by_size(pdf_reader, output_folder, split_value)
        elif self.split_type.get() == "range":
            print(split_value)
            start_page, end_page = self.get_page_range(pdf_reader, split_value)
            self.split_by_range(pdf_reader, output_folder, start_page, end_page)

        tk.messagebox.showinfo("拆分完成", "PDF拆分完成！")

    def split_by_pages(self, pdf_reader, output_folder, split_value):
        total_pages = len(pdf_reader.pages)

        for page_start in range(0, total_pages, split_value):
            page_end = min(page_start + split_value, total_pages)

            pdf_writer = PyPDF2.PdfWriter()

            for page_num in range(page_start, page_end):
                pdf_writer.add_page(pdf_reader.pages[page_num])

            output_filepath = f"{output_folder}/pages_{page_start + 1}-{page_end}.pdf"

            with open(output_filepath, 'wb') as output_file:
                pdf_writer.write(output_file)

    def split_by_size(self, pdf_reader, output_folder, split_value):
        total_pages = len(pdf_reader.pages)

        # 计算每页的大小
        pdf_stream = pdf_reader.stream
        pdf_stream.seek(0, 2)  # 将流的位置移到文件末尾
        total_size_bytes = pdf_stream.tell()
        page_size_bytes = total_size_bytes / total_pages

        # 计算拆分的页数
        bytes_per_file = int(split_value * 1024 * 1024)  # 转换为字节
        pages_per_file = int(bytes_per_file / page_size_bytes)

        current_page = 0
        while current_page < total_pages:
            pdf_writer = PyPDF2.PdfWriter()
            for page_num in range(current_page, min(current_page + pages_per_file, total_pages)):
                pdf_writer.add_page(pdf_reader.pages[page_num])

            output_filepath = f"{output_folder}/split_{current_page + 1}-{current_page + len(pdf_writer.pages)}.pdf"

            with open(output_filepath, 'wb') as output_file:
                pdf_writer.write(output_file)

            current_page += len(pdf_writer.pages)

    def split_by_range(self, pdf_reader, output_folder, start_page, end_page):
        for page_num in range(start_page - 1, end_page):
            pdf_writer = PyPDF2.PdfFileWriter()
            pdf_writer.add_page(pdf_reader.pages[page_num])

            output_filepath = f"{output_folder}/pages_{page_num + 1}.pdf"

            with open(output_filepath, 'wb') as output_file:
                pdf_writer.write(output_file)

if __name__ == "__main__":
    root = tk.Tk()
    app = PDFSplitterApp1(root)
    root.mainloop()