#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ PDF 条码合成工具（带缩放与偏移配置） """ import tkinter as tk from tkinter import ttk, filedialog, scrolledtext import os import json import re import threading import fitz # PyMuPDF from PIL import Image CONFIG_FILE = "pdf_merge_config.json" class PDFMergeApp: def __init__(self, root): self.root = root self.root.title("PDF 条码合成工具") self.root.geometry("780x600") self.root.minsize(700, 500) # 路径变量 self.input_var = tk.StringVar() self.template_var = tk.StringVar() self.output_var = tk.StringVar() # 缩放与偏移变量 self.scale_var = tk.StringVar(value="100") # 相对于模板宽度的百分比 self.offset_x_var = tk.StringVar(value="0") # X 偏移（点） self.offset_y_var = tk.StringVar(value="10") # Y 偏移（点） self.build_ui() self.load_config() def build_ui(self): main_frame = ttk.Frame(self.root, padding="12") main_frame.grid(row=0, column=0, sticky=(tk.W, tk.E, tk.N, tk.S)) self.root.columnconfigure(0, weight=1) self.root.rowconfigure(0, weight=1) main_frame.columnconfigure(1, weight=1) # 输入文件夹 ttk.Label(main_frame, text="输入文件夹：").grid(row=0, column=0, sticky=tk.W, pady=6) ttk.Entry(main_frame, textvariable=self.input_var).grid(row=0, column=1, sticky=(tk.W, tk.E), padx=6) ttk.Button(main_frame, text="浏览…", width=10, command=self.select_input).grid(row=0, column=2, padx=4) # 模板文件 ttk.Label(main_frame, text="模板文件：").grid(row=1, column=0, sticky=tk.W, pady=6) ttk.Entry(main_frame, textvariable=self.template_var).grid(row=1, column=1, sticky=(tk.W, tk.E), padx=6) ttk.Button(main_frame, text="浏览…", width=10, command=self.select_template).grid(row=1, column=2, padx=4) # 输出文件夹 ttk.Label(main_frame, text="输出文件夹：").grid(row=2, column=0, sticky=tk.W, pady=6) ttk.Entry(main_frame, textvariable=self.output_var).grid(row=2, column=1, sticky=(tk.W, tk.E), padx=6) ttk.Button(main_frame, text="浏览…", width=10, command=self.select_output).grid(row=2, column=2, padx=4) # 参数配置区域 param_frame = ttk.LabelFrame(main_frame, text="合成参数（自动保存）", padding="10") param_frame.grid(row=3, column=0, columnspan=3, sticky=(tk.W, tk.E), pady=10) ttk.Label(param_frame, text="缩放比例（% 模板宽）：").grid(row=0, column=0, sticky=tk.W, padx=4) scale_entry = ttk.Entry(param_frame, textvariable=self.scale_var, width=10) scale_entry.grid(row=0, column=1, sticky=tk.W, padx=4) ttk.Label(param_frame, text="例：100 = 宽度填满模板").grid(row=0, column=2, sticky=tk.W, padx=4) ttk.Label(param_frame, text="X 偏移（点）：").grid(row=1, column=0, sticky=tk.W, padx=4, pady=6) ttk.Entry(param_frame, textvariable=self.offset_x_var, width=10).grid(row=1, column=1, sticky=tk.W, padx=4, pady=6) ttk.Label(param_frame, text="左上角水平偏移，0 表示贴左边").grid(row=1, column=2, sticky=tk.W, padx=4, pady=6) ttk.Label(param_frame, text="Y 偏移（点）：").grid(row=2, column=0, sticky=tk.W, padx=4) ttk.Entry(param_frame, textvariable=self.offset_y_var, width=10).grid(row=2, column=1, sticky=tk.W, padx=4) ttk.Label(param_frame, text="左上角垂直偏移，0 表示贴顶部").grid(row=2, column=2, sticky=tk.W, padx=4) # 开始按钮 btn_frame = ttk.Frame(main_frame) btn_frame.grid(row=4, column=0, columnspan=3, pady=10) self.start_btn = ttk.Button(btn_frame, text="▶ 开始处理", command=self.start_process) self.start_btn.pack() # 日志区域 ttk.Label(main_frame, text="处理日志：").grid(row=5, column=0, sticky=tk.W, pady=(8, 0)) self.log_text = scrolledtext.ScrolledText( main_frame, height=18, wrap=tk.WORD, state=tk.NORMAL, font=("Consolas", 10) ) self.log_text.grid(row=6, column=0, columnspan=3, sticky=(tk.W, tk.E, tk.N, tk.S), pady=4) main_frame.rowconfigure(6, weight=1) # 绑定参数变更自动保存 for var in (self.scale_var, self.offset_x_var, self.offset_y_var): var.trace_add("write", lambda *args: self.save_config()) # ---------- 路径选择 ---------- def select_input(self): folder = filedialog.askdirectory() if folder: self.input_var.set(folder) self.save_config() def select_template(self): file_path = filedialog.askopenfilename(filetypes=[("PDF 文件", "*.pdf")]) if file_path: self.template_var.set(file_path) self.save_config() def select_output(self): folder = filedialog.askdirectory() if folder: self.output_var.set(folder) self.save_config() # ---------- 配置持久化 ---------- def save_config(self): config = { "input_dir": self.input_var.get(), "template": self.template_var.get(), "output_dir": self.output_var.get(), "scale_percent": self.scale_var.get(), "offset_x": self.offset_x_var.get(), "offset_y": self.offset_y_var.get(), } try: with open(CONFIG_FILE, "w", encoding="utf-8") as f: json.dump(config, f, ensure_ascii=False, indent=2) except Exception: pass def load_config(self): if not os.path.exists(CONFIG_FILE): return try: with open(CONFIG_FILE, "r", encoding="utf-8") as f: config = json.load(f) self.input_var.set(config.get("input_dir", "")) self.template_var.set(config.get("template", "")) self.output_var.set(config.get("output_dir", "")) self.scale_var.set(config.get("scale_percent", "100")) self.offset_x_var.set(config.get("offset_x", "0")) self.offset_y_var.set(config.get("offset_y", "0")) except Exception: pass # ---------- 日志 ---------- def log(self, msg): self.log_text.insert(tk.END, msg + "\n") self.log_text.see(tk.END) self.root.update_idletasks() # ---------- 文字提取 ---------- def extract_text(self, page): text = page.get_text().strip() print(f"Extracted text: {text}") # Debug print if len(text) >= 2: return text try: import pytesseract pix = page.get_pixmap(dpi=300) mode = "RGBA" if pix.alpha else "RGB" img = Image.frombytes(mode, [pix.width, pix.height], pix.samples) if mode == "RGBA": img = img.convert("RGB") text = pytesseract.image_to_string(img, lang="chi_sim+eng").strip() return text except Exception: return "" def sanitize_filename(self, text): if not text: return "" lines = [ln.strip() for ln in text.splitlines() if ln.strip()] name = lines[0] if lines else text name = name[:60] name = re.sub(r'[\\/:*?"<>|\s]+', "_", name) return name.strip("._") # ---------- 核心处理 ---------- def start_process(self): t = threading.Thread(target=self.process, daemon=True) t.start() def process(self): self.start_btn.config(state=tk.DISABLED) self.log_text.delete(1.0, tk.END) input_dir = self.input_var.get() template_file = self.template_var.get() output_dir = self.output_var.get() # 解析参数 try: scale_percent = float(self.scale_var.get().strip() or "100") offset_x = float(self.offset_x_var.get().strip() or "0") offset_y = float(self.offset_y_var.get().strip() or "0") except ValueError: self.log("❌ 错误：缩放比例、X 偏移、Y 偏移必须是有效数字") self.start_btn.config(state=tk.NORMAL) return if not all([input_dir, template_file, output_dir]): self.log("❌ 错误：请完整填写输入文件夹、模板文件和输出文件夹") self.start_btn.config(state=tk.NORMAL) return if not os.path.isdir(input_dir): self.log(f"❌ 错误：输入文件夹不存在：{input_dir}") self.start_btn.config(state=tk.NORMAL) return if not os.path.isfile(template_file): self.log(f"❌ 错误：模板文件不存在：{template_file}") self.start_btn.config(state=tk.NORMAL) return if not os.path.exists(output_dir): os.makedirs(output_dir, exist_ok=True) pdf_files = [f for f in os.listdir(input_dir) if f.lower().endswith(".pdf")] if not pdf_files: self.log("⚠ 输入文件夹中没有找到 PDF 文件") self.start_btn.config(state=tk.NORMAL) return self.log(f"📁 共找到 {len(pdf_files)} 个 PDF 文件") self.log(f"⚙ 参数：缩放 {scale_percent}% 宽，偏移 ({offset_x}, {offset_y})\n") try: template_doc = fitz.open(template_file) if len(template_doc) == 0: self.log("❌ 错误：模板文件为空") self.start_btn.config(state=tk.NORMAL) return template_page = template_doc[0] template_rect = template_page.rect template_w = template_rect.width template_h = template_rect.height for pdf_name in pdf_files: pdf_path = os.path.join(input_dir, pdf_name) self.log(f"📄 正在处理：{pdf_name}") try: doc = fitz.open(pdf_path) odd_indices = list(range(0, len(doc), 2)) if not odd_indices: self.log(" ⚠ 该文件没有奇数页，已跳过") doc.close() continue safe_name = self.sanitize_filename(self.extract_text(doc[odd_indices[0]])) if not safe_name: safe_name = os.path.splitext(pdf_name)[0] new_doc = fitz.open() for idx in odd_indices: page = doc[idx] page_num = idx + 1 new_page = new_doc.new_page(width=template_w, height=template_h) # 1) 模板背景 new_page.show_pdf_page(template_rect, template_doc, 0, overlay=False) # 2) 计算输入页目标矩形 input_rect = page.rect # 按模板宽度的百分比计算目标宽度 target_w = template_w * (scale_percent / 100.0) # 等比例缩放高度 scale = target_w / input_rect.width target_h = input_rect.height * scale target_rect = fitz.Rect(offset_x, offset_y, offset_x + target_w, offset_y + target_h) # 3) 叠加输入页（前景） new_page.show_pdf_page(target_rect, doc, idx, overlay=True) self.log(f" ✔ 已合成第 {page_num} 页 → 尺寸 {target_w:.1f}×{target_h:.1f} 位置 ({offset_x}, {offset_y})") # 保存 out_name = f"{safe_name}.pdf" out_path = os.path.join(output_dir, out_name) counter = 1 while os.path.exists(out_path): stem, ext = os.path.splitext(out_name) out_path = os.path.join(output_dir, f"{stem}_{counter}{ext}") counter += 1 new_doc.save(out_path) new_doc.close() doc.close() self.log(f" 💾 已保存：{os.path.basename(out_path)}\n") except Exception as e: self.log(f" ❌ 处理失败：{str(e)}\n") template_doc.close() self.log("🎉 全部处理完成！") except Exception as e: self.log(f"❌ 发生错误：{str(e)}") self.start_btn.config(state=tk.NORMAL) if __name__ == "__main__": root = tk.Tk() app = PDFMergeApp(root) root.mainloop()