import osimport sysimport loggingimport timefrom pathlib import Pathfrom concurrent.futures import ThreadPoolExecutorfrom tqdm import tqdmimport tkinter as tkfrom tkinter import filedialog, messagebox, ttkfrom tkinterdnd2 import DND_FILES, TkinterDnDimport jsonfrom pdf2docx import Converterimport pytesseractfrom pdf2image import convert_from_pathfrom docx import Documentfrom docx.shared import Pt, Cm, Inchesfrom docx.enum.text import WD_ALIGN_PARAGRAPHimport numexpr as neimport tempfileimport tracebackimport ioimport threadingimport queue# 获取程序运行路径def get_application_path():"""获取应用程序路径"""if getattr(sys, 'frozen', False):# 如果是打包后的exereturn os.path.dirname(sys.executable)else:# 如果是直接运行的python脚本return os.path.dirname(os.path.abspath(__file__))# 设置NumExpr线程数ne.set_num_threads(8)# 配置文件路径CONFIG_FILE = os.path.join(get_application_path(), "config.json")# 日志文件路径LOG_FILE = os.path.join(get_application_path(), "conversion.log")# 自定义StreamHandler来捕获所有输出class StreamToLogger(io.StringIO):def __init__(self, logger, level):super().__init__()self.logger = loggerself.level = levelself.buf = ''def write(self, buf):self.buf = buf.strip('\r\n\t ')if self.buf:self.logger.log(self.level, self.buf)def flush(self):passdef setup_logging():"""配置日志系统"""try:app_path = get_application_path()log_dir = os.path.join(app_path, 'logs')os.makedirs(log_dir, exist_ok=True)log_file = os.path.join(log_dir, 'conversion.log')# 创建loggerlogger = logging.getLogger()logger.setLevel(logging.DEBUG)# 创建文件处理器file_handler = logging.FileHandler(log_file, mode='w', encoding='utf-8')file_handler.setLevel(logging.DEBUG)# 创建控制台处理器console_handler = logging.StreamHandler()console_handler.setLevel(logging.INFO)# 创建格式化器formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(filename)s:%(lineno)d - %(message)s')file_handler.setFormatter(formatter)console_handler.setFormatter(formatter)# 添加处理器logger.addHandler(file_handler)logger.addHandler(console_handler)logging.debug(f"日志系统初始化成功，日志文件路径：{log_file}")return loggerexcept Exception as e:print(f"设置日志系统失败: {str(e)}")return None# 初始化日志记录器logger = setup_logging()if not logger:print("警告：日志系统初始化失败，程序将继续运行但不会记录日志")# 创建一个基本的日志记录器logger = logging.getLogger()logger.setLevel(logging.DEBUG)handler = logging.StreamHandler()handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))logger.addHandler(handler)def load_config():"""加载配置文件"""try:if os.path.exists(CONFIG_FILE):with open(CONFIG_FILE, 'r', encoding='utf-8') as f:config = json.load(f)logger.debug(f"成功加载配置文件: {config}")return configlogger.warning("配置文件不存在")return {}except Exception as e:logger.error(f"加载配置文件失败: {str(e)}")return {}def save_config(config):"""保存配置文件"""with open(CONFIG_FILE, 'w', encoding='utf-8') as f:json.dump(config, f, ensure_ascii=False, indent=4)def setup_config():"""首次运行配置界面"""root = TkinterDnD.Tk()root.title("PDF转Word工具 - 首次配置")root.geometry("600x400")# 设置窗口样式root.configure(bg='#f0f0f0')style = {'bg': '#f0f0f0', 'font': ('微软雅黑', 10)}button_style = {'bg': '#4CAF50', 'fg': 'white', 'font': ('微软雅黑', 10), 'padx': 10, 'pady': 5}# 创建说明标签tk.Label(root, text="首次使用需要配置以下路径：", **style).pack(pady=10)# Poppler路径配置poppler_frame = tk.Frame(root, bg='#f0f0f0')poppler_frame.pack(fill='x', padx=20, pady=5)tk.Label(poppler_frame, text="Poppler路径：", **style).pack(side='left')poppler_path = tk.StringVar()poppler_entry = tk.Entry(poppler_frame, textvariable=poppler_path, width=50)poppler_entry.pack(side='left', padx=5)def select_poppler():path = filedialog.askdirectory(title="选择Poppler安装目录")if path:poppler_path.set(path)tk.Button(poppler_frame, text="浏览", command=select_poppler, **button_style).pack(side='left')# Tesseract路径配置tesseract_frame = tk.Frame(root, bg='#f0f0f0')tesseract_frame.pack(fill='x', padx=20, pady=5)tk.Label(tesseract_frame, text="Tesseract路径：", **style).pack(side='left')tesseract_path = tk.StringVar()tesseract_entry = tk.Entry(tesseract_frame, textvariable=tesseract_path, width=50)tesseract_entry.pack(side='left', padx=5)def select_tesseract():path = filedialog.askdirectory(title="选择Tesseract安装目录")if path:tesseract_path.set(path)tk.Button(tesseract_frame, text="浏览", command=select_tesseract, **button_style).pack(side='left')# 说明文本help_text = """使用说明：1. Poppler路径：选择poppler的安装目录（包含bin文件夹的目录）2. Tesseract路径：选择Tesseract-OCR的安装目录3. 配置完成后点击"保存配置"即可开始使用"""tk.Label(root, text=help_text, justify='left', **style).pack(pady=10)def save_and_exit():if not poppler_path.get() or not tesseract_path.get():messagebox.showerror("错误", "请填写所有配置项！")returnconfig = {'POPPLER_PATH': poppler_path.get(),'TESSERACT_CMD': os.path.join(tesseract_path.get(), 'tesseract.exe')}save_config(config)root.destroy()tk.Button(root, text="保存配置", command=save_and_exit, **button_style).pack(pady=20)root.mainloop()class PDFConverterGUI:def __init__(self):self.root = TkinterDnD.Tk()self.root.title("PDF转Word工具")self.root.geometry("800x600")# 设置样式self.style = {'bg': '#f0f0f0', 'font': ('微软雅黑', 10)}self.button_style = {'bg': '#4CAF50', 'fg': 'white', 'font': ('微软雅黑', 10), 'padx': 10, 'pady': 5}# 绑定窗口关闭事件self.root.protocol("WM_DELETE_WINDOW", self.on_closing)self.setup_ui()def on_closing(self):"""处理窗口关闭事件"""try:if messagebox.askokcancel("退出", "确定要退出程序吗？"):self.root.destroy()sys.exit(0)except Exception as e:logger.error(f"关闭窗口时出错: {str(e)}")self.root.destroy()sys.exit(1)def setup_ui(self):# 创建主框架main_frame = tk.Frame(self.root, bg='#f0f0f0')main_frame.pack(fill='both', expand=True, padx=20, pady=20)# 路径选择区域path_frame = tk.Frame(main_frame, bg='#f0f0f0')path_frame.pack(fill='x', pady=10)tk.Label(path_frame, text="选择PDF文件或目录：", **self.style).pack(side='left')self.path_var = tk.StringVar()path_entry = tk.Entry(path_frame, textvariable=self.path_var, width=50)path_entry.pack(side='left', padx=5)tk.Button(path_frame, text="选择文件", command=self.select_file, **self.button_style).pack(side='left', padx=5)tk.Button(path_frame, text="选择目录", command=self.select_directory, **self.button_style).pack(side='left')# 文件列表区域list_frame = tk.Frame(main_frame, bg='#f0f0f0')list_frame.pack(fill='both', expand=True, pady=10)tk.Label(list_frame, text="待处理文件列表（支持拖放文件）：", **self.style).pack(anchor='w')# 创建带滚动条的列表框self.listbox_frame = tk.Frame(list_frame, bg='#f0f0f0')self.listbox_frame.pack(fill='both', expand=True)self.file_listbox = tk.Listbox(self.listbox_frame, width=80, height=15)self.file_listbox.pack(side='left', fill='both', expand=True)scrollbar = tk.Scrollbar(self.listbox_frame)scrollbar.pack(side='right', fill='y')self.file_listbox.config(yscrollcommand=scrollbar.set)scrollbar.config(command=self.file_listbox.yview)# 绑定拖放事件self.file_listbox.drop_target_register(DND_FILES)self.file_listbox.dnd_bind('<<Drop>>', self.handle_drop)# 进度条self.progress_var = tk.DoubleVar()self.progress = ttk.Progressbar(main_frame, variable=self.progress_var, maximum=100)self.progress.pack(fill='x', pady=10)# 状态标签self.status_var = tk.StringVar(value="就绪")tk.Label(main_frame, textvariable=self.status_var, **self.style).pack(pady=5)# 按钮区域button_frame = tk.Frame(main_frame, bg='#f0f0f0')button_frame.pack(pady=10)tk.Button(button_frame, text="开始转换", command=self.start_conversion, **self.button_style).pack(side='left', padx=5)tk.Button(button_frame, text="清空列表", command=self.clear_list, **self.button_style).pack(side='left', padx=5)tk.Button(button_frame, text="退出", command=self.root.quit, **self.button_style).pack(side='left', padx=5)def handle_drop(self, event):"""处理文件拖放事件"""files = event.data.split()for file in files:# 移除文件路径中的花括号（如果有）file = file.strip('{}')if file.lower().endswith('.pdf'):if file not in self.file_listbox.get(0, tk.END):self.file_listbox.insert(tk.END, file)self.path_var.set(os.path.dirname(file))elif os.path.isdir(file):# 如果是目录，则添加目录下的所有PDF文件pdf_files = find_pdf_files(file)for pdf_file in pdf_files:if pdf_file not in self.file_listbox.get(0, tk.END):self.file_listbox.insert(tk.END, pdf_file)self.path_var.set(file)def select_file(self):files = filedialog.askopenfilenames(title="选择PDF文件",filetypes=[("PDF文件", "*.pdf")])if files:for file in files:if file not in self.file_listbox.get(0, tk.END):self.file_listbox.insert(tk.END, file)self.path_var.set(os.path.dirname(files[0]))def select_directory(self):directory = filedialog.askdirectory(title="选择包含PDF文件的目录")if directory:self.path_var.set(directory)self.clear_list()pdf_files = find_pdf_files(directory)for file in pdf_files:self.file_listbox.insert(tk.END, file)def clear_list(self):self.file_listbox.delete(0, tk.END)self.progress_var.set(0)self.status_var.set("就绪")def start_conversion(self):files = list(self.file_listbox.get(0, tk.END))if not files:messagebox.showwarning("警告", "请先选择要转换的PDF文件！")returntotal_files = len(files)self.progress_var.set(0)def update_progress(current, total):try:progress = (current / total) * 100self.progress_var.set(progress)self.status_var.set(f"正在处理: {current}/{total}")self.root.update()except Exception as e:logger.error(f"更新进度时出错: {str(e)}")for i, file in enumerate(files, 1):try:self.status_var.set(f"正在处理: {os.path.basename(file)}")self.root.update()if process_single_pdf(file):self.file_listbox.itemconfig(i-1, {'bg': '#90EE90'}) # 浅绿色表示成功else:self.file_listbox.itemconfig(i-1, {'bg': '#FFB6C1'}) # 浅红色表示失败update_progress(i, total_files)except Exception as e:logger.error(f"处理文件失败: {str(e)}", exc_info=True)self.file_listbox.itemconfig(i-1, {'bg': '#FFB6C1'})self.status_var.set("转换完成！")messagebox.showinfo("完成", f"处理完成！共处理 {total_files} 个文件。")def validate_environment():"""检查环境依赖是否就绪"""missing_deps = []if not os.path.exists(POPPLER_PATH):missing_deps.append(f"Poppler路径不存在: {POPPLER_PATH}")if not os.path.exists(TESSERACT_CMD):missing_deps.append(f"Tesseract路径不存在: {TESSERACT_CMD}")if missing_deps:for dep in missing_deps:logger.error(dep)return Falsereturn Truedef extract_text_from_image(image):"""从图片中提取文字"""try:# 配置OCR参数custom_config = r'--oem 3 --psm 6 -l chi_sim'text = pytesseract.image_to_string(image, config=custom_config)return textexcept Exception as e:logger.error(f"OCR识别出错: {str(e)}", exc_info=True)return ""def process_single_pdf(pdf_path):"""处理单个PDF文件"""temp_file = Nonetemp_path = Nonetry:start_time = time.time()pdf_name = os.path.basename(pdf_path)word_path = os.path.splitext(pdf_path)[0] + '.docx'logger.info(f"▶ 开始处理: {pdf_name}")# 基础转换cv = Converter(pdf_path)cv.convert(word_path)cv.close()logger.info(" 基础转换完成")# OCR处理images = convert_from_path(pdf_path, poppler_path=POPPLER_PATH)total_pages = len(images)logger.info(f" 共检测到 {total_pages} 页需要OCR识别")# 创建临时文件来存储OCR识别的文本temp_path = os.path.join(tempfile.gettempdir(), f'ocr_text_{int(time.time())}.txt')temp_file = open(temp_path, 'w', encoding='utf-8')# 对每一页进行OCR识别for idx, image in enumerate(images):logger.info(f" 正在处理第 {idx+1}/{total_pages} 页")text = extract_text_from_image(image)if text.strip(): # 如果识别到文字temp_file.write(f"第{idx+1}页识别到的文字:\n{text}\n\n")# 确保所有内容都写入文件temp_file.flush()temp_file.close()temp_file = None# 将OCR识别的文字添加到Word文档中if os.path.exists(temp_path):with open(temp_path, 'r', encoding='utf-8') as f:ocr_text = f.read()if ocr_text.strip():logger.info(" 正在将OCR识别的文字添加到Word文档...")# 打开已转换的Word文档doc = Document(word_path)# 添加OCR识别的文字doc.add_paragraph("\nOCR识别结果：")doc.add_paragraph(ocr_text)# 保存文档doc.save(word_path)logger.info(f" 已添加OCR识别结果")cost_time = time.time() - start_timelogger.info(f"✓ 处理完成，耗时 {cost_time:.2f} 秒\n")return Trueexcept Exception as e:logger.error(f"转换失败: {str(e)}", exc_info=True)return Falsefinally:# 确保临时文件被关闭和删除if temp_file and not temp_file.closed:try:temp_file.close()except:passif temp_path and os.path.exists(temp_path):try:os.unlink(temp_path)except:passdef find_pdf_files(directory):"""递归查找所有PDF文件"""pdf_files = []try:for root, _, files in os.walk(directory):for file in files:if file.lower().endswith('.pdf'):full_path = os.path.join(root, file)pdf_files.append(full_path)return pdf_filesexcept Exception as e:logger.error(f"文件搜索失败: {str(e)}")return []def main():try:print("程序启动...")logger.info("程序启动")# 检查配置文件config = load_config()if not config:print("首次运行，请进行配置...")logger.info("首次运行，启动配置界面")setup_config()config = load_config()if not config:print("配置失败，程序退出")logger.error("配置失败，程序退出")return# 设置全局变量global POPPLER_PATH, TESSERACT_CMDPOPPLER_PATH = config.get('POPPLER_PATH')TESSERACT_CMD = config.get('TESSERACT_CMD')pytesseract.pytesseract.tesseract_cmd = TESSERACT_CMDprint(f"Poppler路径: {POPPLER_PATH}")print(f"Tesseract路径: {TESSERACT_CMD}")# 验证环境if not validate_environment():print("环境验证失败")logger.error("环境验证失败")messagebox.showerror("错误", "环境配置不正确，请检查配置！")return# 启动GUIprint("启动GUI界面...")logger.info("启动GUI界面")app = PDFConverterGUI()app.root.mainloop()except Exception as e:error_msg = f"程序运行出错: {str(e)}\n{traceback.format_exc()}"print(error_msg)logger.error(error_msg)messagebox.showerror("错误", f"程序运行出错：{str(e)}")finally:# 确保所有日志都被写入for handler in logger.handlers:handler.flush()handler.close()if __name__ == "__main__":main()
推荐本站淘宝优惠价购买喜欢的宝贝:
本文链接：https://hqyman.cn/post/11256.html 非本站原创文章欢迎转载，原创文章需保留本站地址！
微信支付宝扫一扫，打赏作者吧～休息一下~~
萌ICP备20248119号
