2025-03-04-PDF转Word
DeepSeek等大模型从来都不是简单的写一个静态博客这么肤浅（太多博主都只讲这个内容了）借助全网大神的奇思妙想，拓展我狭隘的思维边界。
文章目录
- 2025-03-04-PDF转Word
- @[toc]
- 1-参考网址
- 2-学习要点
- 3-核心逻辑
- 4-核心代码
文章目录
- 2025-03-04-PDF转Word
- @[toc]
- 1-参考网址
- 2-学习要点
- 3-核心逻辑
- 4-核心代码
1-参考网址
- DeepSeek编写一个PDF转Word软件(参考当前)：https://blog.csdn.net/henanlion/article/details/145861672
- 个人尝试代码仓库：https://gitee.com/enzoism/pdf2word
2-学习要点
- 1）思维拓展-DeepSeek如何辅助编程
- 2）Python-编写PDF转Word：https://blog.csdn.net/2301_77717148/article/details/146015704
- 3）Python-使用tkinter：https://blog.csdn.net/2301_77717148/article/details/146015225
- 4）Python-使用threading和queue：https://blog.csdn.net/2301_77717148/article/details/146013352
- 5）Python-编写Requirements.txt：https://blog.csdn.net/2301_77717148/article/details/146012907
3-核心逻辑
- 1）使用pdf2docx库将PDF文件转换为Word文件
- 2）使用tkinter实现GUI界面
- 3）使用threading和queue实现多线程和消息队列通信
- 4）使用Requirements.txt管理依赖库
4-核心代码
- DeepSeek编写一个PDF转Word软件(参考当前)：https://blog.csdn.net/henanlion/article/details/145861672
import os
import tkinter as tk
from tkinter import ttk, filedialog, messagebox
from pdf2docx import Converter
import threading
import queue
class PDFToWordConverter:
def __init__(self, master):
self.master = master
master.title("PDF批量转Word")
master.geometry("610x295")
# 输入文件夹
self.lbl_input = tk.Label(master, text="输入文件夹：")
self.ent_input = tk.Entry(master, width=30)
self.btn_input = tk.Button(master, text="选择", command=self.select_input)
# 输出文件夹
self.lbl_output = tk.Label(master, text="输出文件夹：")
self.ent_output = tk.Entry(master, width=30)
self.btn_output = tk.Button(master, text="选择", command=self.select_output)
# 复选框
self.var_subdir = tk.BooleanVar()
self.var_open = tk.BooleanVar(value=True)
self.chk_subdir = tk.Checkbutton(master, text="包含子文件夹", variable=self.var_subdir)
self.chk_open = tk.Checkbutton(master, text="转换完成后打开目标文件夹", variable=self.var_open)
# 转换按钮
self.btn_convert = tk.Button(master, text="开始转换", command=self.start_conversion)
# 布局
self.lbl_input.grid(row=0, column=0, padx=10, pady=10, sticky=tk.W)
self.ent_input.grid(row=0, column=1, padx=5, pady=10, sticky=tk.EW)
self.btn_input.grid(row=0, column=2, padx=10, pady=10)
self.lbl_output.grid(row=1, column=0, padx=10, pady=10, sticky=tk.W)
self.ent_output.grid(row=1, column=1, padx=5, pady=10, sticky=tk.EW)
self.btn_output.grid(row=1, column=2, padx=10, pady=10)
self.chk_subdir.grid(row=2, column=1, padx=5, pady=5, sticky=tk.W)
self.chk_open.grid(row=3, column=1, padx=5, pady=5, sticky=tk.W)
self.btn_convert.grid(row=4, column=1, pady=10)
# 新增进度组件
self.progress_label = tk.Label(master, text="准备就绪")
self.progress_bar = ttk.Progressbar(master, orient=tk.HORIZONTAL, mode='determinate')
# 调整布局（新增两行）
self.progress_label.grid(row=5, column=0, columnspan=3, padx=10, pady=5, sticky=tk.W)
self.progress_bar.grid(row=6, column=0, columnspan=3, padx=10, pady=10, sticky=tk.EW)
# 消息队列用于线程通信
self.queue = queue.Queue()
master.after(100, self.process_queue)
# 配置列权重
master.columnconfigure(1, weight=1)
def select_input(self):
path = filedialog.askdirectory()
if path:
self.ent_input.delete(0, tk.END)
self.ent_input.insert(0, path)
def select_output(self):
path = filedialog.askdirectory()
if path:
self.ent_output.delete(0, tk.END)
self.ent_output.insert(0, path)
def start_conversion(self):
# 重置进度条
self.progress_bar['value'] = 0
self.progress_label.config(text="正在扫描PDF文件...")
input_dir = self.ent_input.get()
output_dir = self.ent_output.get()
if not input_dir or not output_dir:
messagebox.showerror("错误", "请先选择输入和输出文件夹！")
return
# 禁用转换按钮
self.btn_convert.config(state=tk.DISABLED)
threading.Thread(target=self.convert_files, args=(input_dir, output_dir), daemon=True).start()
def get_pdf_list(self, input_dir):
pdf_list = []
for root, dirs, files in os.walk(input_dir):
if not self.var_subdir.get() and root != input_dir:
continue
for file in files:
if file.lower().endswith('.pdf'):
pdf_list.append(os.path.join(root, file))
return pdf_list
def convert_files(self, input_dir, output_dir):
self.pdf_files = self.get_pdf_list(input_dir)
try:
total_files = len(self.pdf_files)
for index, pdf_path in enumerate(self.pdf_files):
# 更新当前文件进度
self.queue.put(("file_progress", (index + 1, total_files, pdf_path)))
# 构建输出路径
relative_path = os.path.relpath(os.path.dirname(pdf_path), input_dir) if self.var_subdir.get() else ""
output_path = os.path.join(output_dir, relative_path)
os.makedirs(output_path, exist_ok=True)
# 转换文件
docx_path = os.path.join(output_path, f"{os.path.splitext(os.path.basename(pdf_path))[0]}.docx")
cv = Converter(pdf_path)
cv.convert(docx_path, progress_callback=self.update_page_progress)
cv.close()
self.queue.put(("complete", None))
except Exception as e:
self.queue.put(("error", str(e)))
def update_page_progress(self, current, total):
# 页面级别进度（每文件0-100%）
progress = (current / total) * 100 if total != 0 else 0
self.queue.put(("page_progress", progress))
def process_queue(self):
try:
while True:
msg_type, data = self.queue.get_nowait()
if msg_type == "file_progress":
current, total, path = data
file_progress = (current / total) * 100
self.progress_bar['value'] = file_progress
self.progress_label.config(text=f"正在转换 {current}/{total}：{os.path.basename(path)}")
elif msg_type == "page_progress":
# 综合进度 = 文件进度 + 页面进度/总文件数
current_file_progress = self.progress_bar['value']
page_progress = data / len(self.pdf_files)
self.progress_bar['value'] = current_file_progress + page_progress
elif msg_type == "complete":
messagebox.showinfo("完成", "转换完成！")
if self.var_open.get():
os.startfile(self.ent_output.get())
self.btn_convert.config(state=tk.NORMAL)
self.progress_label.config(text="转换完成")
elif msg_type == "error":
messagebox.showerror("错误", f"转换出错：{data}")
self.btn_convert.config(state=tk.NORMAL)
self.progress_label.config(text="转换出错")
except queue.Empty:
pass
finally:
self.master.after(100, self.process_queue)
if __name__ == "__main__":
root = tk.Tk()
app = PDFToWordConverter(root)
root.mainloop()
