pythonTest/条码处理/SHEIN.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
PDF 条码合成工具（单文件输入，每页独立输出）
"""

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")
        self.offset_x_var = tk.StringVar(value="0")
        self.offset_y_var = tk.StringVar(value="10")

        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
        ttk.Label(main_frame, text="输入文件：").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)
        ttk.Entry(param_frame, textvariable=self.scale_var, width=10).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)

        # 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):
        file_path = filedialog.askopenfilename(filetypes=[("PDF 文件", "*.pdf")])
        if file_path:
            self.input_var.set(file_path)
            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_file": 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_file", ""))
            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()
        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 get_filename_from_text(self, text):
        """
        取第一段 + 第四段文字作为文件名
        如果第四段不存在，只用第一段
        如果第一段也不存在，返回空字符串
        """
        if not text:
            return ""
        lines = [ln.strip() for ln in text.splitlines() if ln.strip()]
        if not lines:
            return ""
        first = lines[0]
        fourth = lines[4] if len(lines) >= 5 else ""
        fourth = fourth.replace("¨", "0")
        fourth = fourth.replace("©", "1")
        fourth = fourth.replace("ª", "2")
        fourth = fourth.replace("«", "3")
        fourth = fourth.replace("°2", "4")
        fourth = fourth.replace("°2", "5")
        fourth = fourth.replace("®", "6")
        fourth = fourth.replace("°2", "7")
        fourth = fourth.replace("°", "8")
        fourth = fourth.replace("°2", "9")
        name = f"{first}_{fourth}" if fourth else first
        return self.sanitize_filename(name)

    def sanitize_filename(self, text):
        if not text:
            return ""
        name = text[:80]  # 限制长度
        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_file = 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_file, template_file, output_dir]):
            self.log("❌ 错误：请完整填写输入文件、模板文件和输出文件夹")
            self.start_btn.config(state=tk.NORMAL)
            return
        if not os.path.isfile(input_file):
            self.log(f"❌ 错误：输入文件不存在：{input_file}")
            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)

        self.log(f"📄 输入文件：{os.path.basename(input_file)}")
        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

            doc = fitz.open(input_file)
            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()
                template_doc.close()
                self.start_btn.config(state=tk.NORMAL)
                return

            self.log(f"📑 共 {len(doc)} 页，提取奇数页 {len(odd_indices)} 页\n")

            for idx in odd_indices:
                page = doc[idx]
                page_num = idx + 1

                # 从该页提取文字作为文件名
                page_text = self.extract_text(page)
                safe_name = self.get_filename_from_text(page_text)
                if not safe_name:
                    base = os.path.splitext(os.path.basename(input_file))[0]
                    safe_name = f"{base}_page{page_num}"

                # 创建单页新 PDF
                new_doc = fitz.open()
                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
                target_w = template_w * (scale_percent / 100.0)
                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)

                # 保存（自动处理重名）
                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()

                self.log(f"✔ 第 {page_num} 页  →  {os.path.basename(out_path)}")

            doc.close()
            template_doc.close()
            self.log(f"\n🎉 全部完成！共导出 {len(odd_indices)} 个 PDF")

        except Exception as e:
            self.log(f"\n❌ 发生错误：{str(e)}")

        self.start_btn.config(state=tk.NORMAL)


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