結(jié)果效果

1、將pdf文件按指定頁(yè)數(shù)進(jìn)行分割
2、將pdf文件按頁(yè)導(dǎo)出jpg文件

image.png

源碼

import tkinter as tk
from tkinter import filedialog, messagebox, scrolledtext
import os

import fitz #python -m pip install PyMuPDF==1.18.7 -i https://pypi.tuna.tsinghua.edu.cn/simple
import PyPDF2
import datetime

import threading
import queue

class PDFInputApp:
    def __init__(self, root):
        self.root = root
        self.root.title("PDF-處理工具")
        self.root.geometry("500x330")

        # 創(chuàng)建標(biāo)簽和輸入框
        self.create_widgets()

        # 創(chuàng)建日志隊(duì)列和日志線程
        self.log_queue = queue.Queue()
        self.log_thread = threading.Thread(target=self.process_log_queue, daemon=True)
        self.log_thread.start()


    def create_widgets(self):
        # 設(shè)置列權(quán)重，使輸入框自動(dòng)擴(kuò)展
        self.root.grid_columnconfigure(1, weight=1)
        self.root.grid_columnconfigure(3, weight=1)  # 使第 3 列也具有擴(kuò)展性，確保按鈕居中

        # 選擇 PDF 文件
        self.pdf_label = tk.Label(self.root, text="選擇 PDF 文件:")
        self.pdf_label.grid(row=0, column=0, padx=10, pady=5, sticky=tk.E)

        self.pdf_path_var = tk.StringVar()
        self.pdf_entry = tk.Entry(self.root, textvariable=self.pdf_path_var, width=50)
        self.pdf_entry.grid(row=0, column=1, padx=10, pady=5, sticky=tk.W+tk.E)

        self.browse_button = tk.Button(self.root, text="瀏覽", command=self.browse_pdf)
        self.browse_button.grid(row=0, column=2, padx=10, pady=5, sticky=tk.W)

        # 輸入數(shù)字
        self.number_label = tk.Label(self.root, text="每份頁(yè)數(shù):")
        self.number_label.grid(row=1, column=0, padx=10, pady=5, sticky=tk.E)

        self.number_var = tk.IntVar()
        self.number_var.set(1)
        self.number_entry = tk.Entry(self.root, textvariable=self.number_var, width=50)
        self.number_entry.grid(row=1, column=1, padx=10, pady=5, sticky=tk.W+tk.E)

        # 顯示所選文件的路徑
        self.path_label = tk.Label(self.root, text="結(jié)果文件路徑:")
        self.path_label.grid(row=2, column=0, padx=10, pady=5, sticky=tk.E)

        self.out_path_var = tk.StringVar()
        self.path_entry = tk.Entry(self.root, textvariable=self.out_path_var, width=50, state='readonly')
        self.path_entry.grid(row=2, column=1, padx=10, pady=5, sticky=tk.W+tk.E)

        # 提交和導(dǎo)出按鈕放在同一行，居中顯示，中間有 10px 間隔
        self.submit_button = tk.Button(self.root, text="切割PDF", command=self.submit,width=15)
        self.export_button = tk.Button(self.root, text="導(dǎo)出圖片", command=self.export,width=15)

        # 使用空列 (column 3) 來(lái)創(chuàng)建 10px 的間隔
        self.root.grid_columnconfigure(3, minsize=5)  # 設(shè)置第 3 列的最小寬度為 10px

        # 將按鈕放置在第 4 行，跨越 3 列，居中對(duì)齊
        self.submit_button.grid(row=3, column=1, padx=10, pady=15, sticky=tk.W)
        self.export_button.grid(row=3, column=1, padx=10, pady=15, sticky=tk.E)

        # 添加日志文本框
        self.log_label = tk.Label(self.root, text="處理日志:")
        self.log_label.grid(row=4, column=0, padx=10, pady=5, sticky=tk.NE)

        # 使用 ScrolledText 控件創(chuàng)建帶滾動(dòng)條的多行文本框
        self.log_text = scrolledtext.ScrolledText(self.root, width=70, height=10, state='disabled')
        self.log_text.grid(row=4, column=1, columnspan=3, padx=10, pady=5, sticky=tk.W+tk.E)

    def browse_pdf(self):
        # 打開(kāi)文件對(duì)話框，限制只能選擇 PDF 文件
        file_path = filedialog.askopenfilename(
            filetypes=[("PDF 文件", "*.pdf")],
            title="選擇 PDF 文件"
        )
        if file_path:
            self.pdf_path_var.set(file_path)
            self.out_path_var.set(os.path.dirname(file_path))

    def submit(self):
        # 獲取輸入的 PDF 文件路徑和數(shù)字
        pdf_path = self.pdf_path_var.get()
        number = self.number_var.get()
        out_path = self.out_path_var.get()

        # 驗(yàn)證輸入
        if not pdf_path:
            messagebox.showwarning("警告", "請(qǐng)選擇一個(gè) PDF 文件")
            return

        # if not number.i():
        #     messagebox.showwarning("警告", "請(qǐng)輸入有效的數(shù)字")
        #     return
        self.log(f"準(zhǔn)備開(kāi)始分隔文件{pdf_path}")
        self.split_pdf(pdf_path,out_path,number)
        # 處理邏輯（這里可以根據(jù)需要添加更多處理）
        messagebox.showinfo("分割處理成功!", f"PDF 文件: {pdf_path}\n每頁(yè): {number}完成分隔!")
        self.log(f"完成文件{pdf_path}分隔")

    def export(self):
         # 獲取輸入的 PDF 文件路徑和數(shù)字
        pdf_path = self.pdf_path_var.get()
        number = self.number_var.get()
        out_path = self.out_path_var.get()

        # 驗(yàn)證輸入
        if not pdf_path:
            messagebox.showwarning("警告", "請(qǐng)選擇一個(gè) PDF 文件")
            return
        self.log(f"準(zhǔn)備開(kāi)始分隔文件{pdf_path}")
        self.pdf_image(pdf_path,out_path,1.0,1.0,0)
        # 導(dǎo)出功能的邏輯（根據(jù)需要實(shí)現(xiàn)）
        messagebox.showinfo("導(dǎo)出成功", f"PDF 文件: {pdf_path}\n導(dǎo)出jpg成功!")
        self.log(f"完成文件{pdf_path}處理")

    #分割pdf
    def split_pdf(self,input_pdf, output_dir, num_pages_per_file):
        with open(input_pdf, "rb") as file:
            reader = PyPDF2.PdfReader(file)
            total_pages = len(reader.pages)
            
            for i in range(0, total_pages, num_pages_per_file):
                start_page = i
                end_page = min(i + num_pages_per_file, total_pages)
                self.log(f"開(kāi)始處理第{start_page}至｛end_page｝頁(yè)內(nèi)容")
                output_pdf = f"{output_dir}/split_{start_page+1}-{end_page}.pdf"
                writer = PyPDF2.PdfWriter()
                
                for page_num in range(start_page, end_page):
                    page = reader.pages[page_num]
                    writer.add_page(page)
                
                with open(output_pdf, "wb") as out_file:
                    writer.write(out_file)
                    self.log(f"Saved {output_pdf}")
    '''
    # 將PDF轉(zhuǎn)化為圖片
    pdfPath pdf文件的路徑
    imgPath 圖像要保存的文件夾
    zoom_x x方向的縮放系數(shù) - 值越大生成的文件越大
    zoom_y y方向的縮放系數(shù) - 值越大生成的文件越大
    rotation_angle 旋轉(zhuǎn)角度
    '''
    def pdf_image(self,pdfPath,imgPath,zoom_x,zoom_y,rotation_angle):
        # 打開(kāi)PDF文件
        pdf = fitz.open(pdfPath)
        # 逐頁(yè)讀取PDF
        for pg in range(0, pdf.pageCount):
            self.log(f"開(kāi)始處理第{pg}頁(yè)")
            page = pdf[pg]
            # 設(shè)置縮放和旋轉(zhuǎn)系數(shù)
            trans = fitz.Matrix(zoom_x, zoom_y).preRotate(rotation_angle)
            pm = page.getPixmap(matrix=trans, alpha=False)
            # 開(kāi)始寫(xiě)圖像
            pm.writePNG(imgPath+"\\image-"+str(pg)+".jpg")
            self.log(f"生成圖片 image-"+str(pg)+".jpg")
        pdf.close()


    def log(self, message):
        """將消息放入日志隊(duì)列中，由日志線程處理"""
        current_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        log_message = f"[{current_time}] {message}\n"
        self.log_queue.put(log_message)

    def process_log_queue(self):
        """從日志隊(duì)列中取出消息并更新日志文本框"""
        while True:
            try:
                log_message = self.log_queue.get(timeout=0.1)
                self.update_log_text(log_message)
            except queue.Empty:
                continue

    def update_log_text(self, log_message):
        """更新日志文本框的內(nèi)容"""
        # 確保在主線程中更新 GUI
        self.root.after(0, self._update_log_text, log_message)

    def _update_log_text(self, log_message):
        """實(shí)際更新日志文本框的方法"""
        # 啟用文本框編輯模式，插入日志，然后禁用編輯
        self.log_text.config(state='normal')
        self.log_text.insert(tk.END, log_message)
        self.log_text.config(state='disabled')

        # 滾動(dòng)到最新日志
        self.log_text.yview_moveto(1.0)

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