train-invoice-organizer 0.1.0__tar.gz

train_invoice_organizer-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 train-invoice-organizer contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

train_invoice_organizer-0.1.0/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: train-invoice-organizer
+Version: 0.1.0
+Summary: 自动提取铁路电子发票 ZIP 包中的 PDF，按乘车日期、时间、票价重命名整理
+Author-email: Violin True <ncunxi@sina.com>
+License: MIT
+Project-URL: Homepage, https://gitee.com/chuwanglin/train-invoice-organizer
+Project-URL: Repository, https://gitee.com/chuwanglin/train-invoice-organizer
+Keywords: train,invoice,railway,pdf,ticket,rename,organizer
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Office/Business :: Financial
+Classifier: Topic :: Utilities
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: PyMuPDF>=1.23.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: build>=0.10; extra == "dev"
+Requires-Dist: twine>=4.0; extra == "dev"
+Dynamic: license-file
+
+# train-invoice-organizer
+
+自动提取铁路电子发票 ZIP 包中的 PDF，按**乘车日期**、**时间**、**票价**重命名整理。
+
+## 功能
+
+- 递归解压嵌套的 ZIP 包（F 文件 → 内部 ZIP → PDF 发票）
+- 用 PyMuPDF 从 PDF 中智能提取乘车日期、发车时间和票价
+- 自动按 `YYYYMMDD_HHMM_价格.pdf` 格式重命名
+- 遇到同名文件自动添加序号后缀
+- 支持命令行一键运行，也支持作为 Python 库导入调用
+
+## 安装
+
+```bash
+pip install train-invoice-organizer
+```
+
+## 使用方式
+
+### 1. 命令行（安装后直接使用）
+
+```bash
+# 处理当前目录下的所有 ZIP 文件
+train-invoice-organizer
+
+# 指定目录
+train-invoice-organizer /path/to/your/zip/files
+
+# 指定输出目录
+train-invoice-organizer /path/to/zip/files -o /path/to/output
+
+# 显示详细日志
+train-invoice-organizer /path/to/zip/files -v
+```
+
+### 2. macOS 原生图形界面（推荐 Mac 用户）
+
+```bash
+# 弹出系统原生目录选择框，处理完成后自动打开 Finder
+train-invoice-gui
+```
+
+### 3. 作为 Python 库导入
+
+```python
+from train_invoice_organizer import organize_invoices, extract_ticket_info
+
+# 批量整理整个目录
+total = organize_invoices("/path/to/zip/files")
+print(f"共提取 {total} 张发票")
+
+# 或单独解析单张 PDF 信息
+info = extract_ticket_info("/path/to/single_ticket.pdf")
+print(info)  # 例如: 20260807_0845_104
+```
+
+## 提取规则
+
+| 字段 | 提取策略 |
+|------|---------|
+| **乘车日期** | 优先匹配 "日期+时间" 连续出现格式；若 PDF 排版导致分离，则先剔除 "开票日期" 干扰项，再匹配剩余日期 |
+| **时间** | 匹配 `HH:MM` 格式 |
+| **票价** | 优先匹配 `¥/￥` 后的整数；备用匹配 `(小写)104.00` 格式 |
+
+## 输出示例
+
+```
+已命名的火车发票汇总/
+├── 20260807_0845_104.pdf
+├── 20260808_1430_156.pdf
+├── 20260810_0920_89_1.pdf   # 重名时自动加序号
+└── 20260810_0920_89_2.pdf
+```
+
+## 依赖
+
+- Python >= 3.8
+- [PyMuPDF](https://pypi.org/project/PyMuPDF/) (fitz)
+
+## 开源协议
+
+MIT License

train_invoice_organizer-0.1.0/README.md

@@ -0,0 +1,83 @@
+# train-invoice-organizer
+
+自动提取铁路电子发票 ZIP 包中的 PDF，按**乘车日期**、**时间**、**票价**重命名整理。
+
+## 功能
+
+- 递归解压嵌套的 ZIP 包（F 文件 → 内部 ZIP → PDF 发票）
+- 用 PyMuPDF 从 PDF 中智能提取乘车日期、发车时间和票价
+- 自动按 `YYYYMMDD_HHMM_价格.pdf` 格式重命名
+- 遇到同名文件自动添加序号后缀
+- 支持命令行一键运行，也支持作为 Python 库导入调用
+
+## 安装
+
+```bash
+pip install train-invoice-organizer
+```
+
+## 使用方式
+
+### 1. 命令行（安装后直接使用）
+
+```bash
+# 处理当前目录下的所有 ZIP 文件
+train-invoice-organizer
+
+# 指定目录
+train-invoice-organizer /path/to/your/zip/files
+
+# 指定输出目录
+train-invoice-organizer /path/to/zip/files -o /path/to/output
+
+# 显示详细日志
+train-invoice-organizer /path/to/zip/files -v
+```
+
+### 2. macOS 原生图形界面（推荐 Mac 用户）
+
+```bash
+# 弹出系统原生目录选择框，处理完成后自动打开 Finder
+train-invoice-gui
+```
+
+### 3. 作为 Python 库导入
+
+```python
+from train_invoice_organizer import organize_invoices, extract_ticket_info
+
+# 批量整理整个目录
+total = organize_invoices("/path/to/zip/files")
+print(f"共提取 {total} 张发票")
+
+# 或单独解析单张 PDF 信息
+info = extract_ticket_info("/path/to/single_ticket.pdf")
+print(info)  # 例如: 20260807_0845_104
+```
+
+## 提取规则
+
+| 字段 | 提取策略 |
+|------|---------|
+| **乘车日期** | 优先匹配 "日期+时间" 连续出现格式；若 PDF 排版导致分离，则先剔除 "开票日期" 干扰项，再匹配剩余日期 |
+| **时间** | 匹配 `HH:MM` 格式 |
+| **票价** | 优先匹配 `¥/￥` 后的整数；备用匹配 `(小写)104.00` 格式 |
+
+## 输出示例
+
+```
+已命名的火车发票汇总/
+├── 20260807_0845_104.pdf
+├── 20260808_1430_156.pdf
+├── 20260810_0920_89_1.pdf   # 重名时自动加序号
+└── 20260810_0920_89_2.pdf
+```
+
+## 依赖
+
+- Python >= 3.8
+- [PyMuPDF](https://pypi.org/project/PyMuPDF/) (fitz)
+
+## 开源协议
+
+MIT License

train_invoice_organizer-0.1.0/pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "train-invoice-organizer"
+version = "0.1.0"
+description = "自动提取铁路电子发票 ZIP 包中的 PDF，按乘车日期、时间、票价重命名整理"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+    {name = "Violin True", email = "ncunxi@sina.com"}
+]
+requires-python = ">=3.8"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: End Users/Desktop",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Office/Business :: Financial",
+    "Topic :: Utilities",
+]
+keywords = ["train", "invoice", "railway", "pdf", "ticket", "rename", "organizer"]
+dependencies = [
+    "PyMuPDF>=1.23.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "build>=0.10",
+    "twine>=4.0",
+]
+
+[project.scripts]
+train-invoice-organizer = "train_invoice_organizer.cli:main"
+train-invoice-gui = "train_invoice_organizer.gui:main"
+
+[project.urls]
+Homepage = "https://gitee.com/chuwanglin/train-invoice-organizer"
+Repository = "https://gitee.com/chuwanglin/train-invoice-organizer"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-dir]
+"" = "src"

train_invoice_organizer-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

train_invoice_organizer-0.1.0/src/train_invoice_organizer/__init__.py

@@ -0,0 +1,9 @@
+"""
+train-invoice-organizer
+自动提取铁路电子发票 ZIP 包中的 PDF，按乘车日期、时间、票价重命名整理。
+"""
+
+from .core import extract_ticket_info, process_single_f_file, organize_invoices
+
+__version__ = "0.1.0"
+__all__ = ["extract_ticket_info", "process_single_f_file", "organize_invoices"]

train_invoice_organizer-0.1.0/src/train_invoice_organizer/cli.py

@@ -0,0 +1,57 @@
+"""
+命令行入口。安装库后可直接运行：
+    train-invoice-organizer /path/to/zip/files
+"""
+
+import argparse
+import logging
+import os
+import sys
+
+from .core import organize_invoices
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description="自动提取铁路电子发票 ZIP 包中的 PDF，按乘车日期、时间、票价重命名整理。"
+    )
+    parser.add_argument(
+        "input_dir",
+        nargs="?",
+        default=os.getcwd(),
+        help="包含 ZIP 文件的目录路径（默认为当前目录）",
+    )
+    parser.add_argument(
+        "-o",
+        "--output",
+        dest="output_dir",
+        default=None,
+        help="指定输出目录（默认为 input_dir/已命名的火车发票汇总）",
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="显示详细日志",
+    )
+
+    args = parser.parse_args()
+
+    log_level = logging.DEBUG if args.verbose else logging.INFO
+    logging.basicConfig(
+        level=log_level,
+        format="%(levelname)s: %(message)s",
+        stream=sys.stdout,
+    )
+
+    try:
+        organize_invoices(args.input_dir, args.output_dir)
+    except FileNotFoundError as exc:
+        logging.error(exc)
+        return 1
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

train_invoice_organizer-0.1.0/src/train_invoice_organizer/core.py

@@ -0,0 +1,193 @@
+"""
+核心功能：从 ZIP 嵌套包中提取铁路电子发票 PDF，
+按乘车日期、时间、票价重命名整理。
+"""
+
+import logging
+import os
+import re
+import shutil
+import tempfile
+import zipfile
+from pathlib import Path
+from typing import Optional
+
+import fitz
+
+logger = logging.getLogger(__name__)
+
+
+def extract_ticket_info(pdf_path: str | Path) -> str:
+    """
+    从铁路电子发票 PDF 中提取乘车日期、时间和票价，
+    返回格式为：YYYYMMDD_HHMM_价格 的字符串。
+
+    提取策略：
+        1. 优先匹配 "日期+时间" 连续出现的格式（乘车日期 T2）
+        2. 若排版导致换行，则先剔除 "开票日期" 干扰，再匹配日期
+        3. 票价优先匹配 ¥ 符号后的整数，备用匹配 "(小写)" 格式
+
+    Args:
+        pdf_path: PDF 文件路径。
+
+    Returns:
+        组合后的文件名主体，如 "20260807_0845_104"。
+        若某字段提取失败，会用 "未知日期"/"未知时间"/"未知票价" 占位。
+    """
+    date_str = "未知日期"
+    time_str = "未知时间"
+    price_str = "未知票价"
+
+    try:
+        doc = fitz.open(str(pdf_path))
+        if len(doc) > 0:
+            page = doc[0]
+            text = page.get_text()
+
+            # 策略1: 直接匹配 "日期紧接着时间"（乘车日期 T2）
+            datetime_match = re.search(
+                r"(\d{4})\s*[年-]\s*(\d{1,2})\s*[月-]\s*(\d{1,2})\s*日?\s*(\d{2})\s*:\s*(\d{2})",
+                text,
+            )
+
+            if datetime_match:
+                year, month, day, hour, minute = datetime_match.groups()
+                date_str = f"{year}{month.zfill(2)}{day.zfill(2)}"
+                time_str = f"{hour}{minute}"
+            else:
+                # 策略2: 日期和时间被排版分离的情况
+                time_match = re.search(r"(\d{2})\s*:\s*(\d{2})", text)
+                if time_match:
+                    hour, minute = time_match.groups()
+                    time_str = f"{hour}{minute}"
+
+                # 剔除 "开票日期" 所在的 T1，避免干扰乘车日期 T2
+                text_without_invoice_date = re.sub(
+                    r"开票日期\s*[:：]?\s*\d{4}\s*[年-]\s*\d{1,2}\s*[月-]\s*\d{1,2}\s*日?",
+                    "",
+                    text,
+                )
+                date_match = re.search(
+                    r"(\d{4})\s*[年-]\s*(\d{1,2})\s*[月-]\s*(\d{1,2})\s*日?",
+                    text_without_invoice_date,
+                )
+                if date_match:
+                    year, month, day = date_match.groups()
+                    date_str = f"{year}{month.zfill(2)}{day.zfill(2)}"
+
+            # 提取票价（整数部分）
+            # 优先匹配 ¥/￥ 符号后的数字
+            price_match = re.search(r"[¥￥]\s*(\d+)", text)
+            if not price_match:
+                # 备用：匹配 "(小写)104.00" 格式
+                price_match = re.search(r"小写.*?(\d+)\.\d{2}", text)
+
+            if price_match:
+                price_str = price_match.group(1)
+
+    except Exception as exc:
+        logger.warning("无法读取 PDF %s: %s", os.path.basename(str(pdf_path)), exc)
+    finally:
+        if "doc" in locals():
+            doc.close()
+
+    return f"{date_str}_{time_str}_{price_str}"
+
+
+def process_single_f_file(f_zip_path: str | Path, output_dir: str | Path) -> int:
+    """
+    处理单个 F 文件（主 ZIP 包）。
+
+    解压主 ZIP 后，递归查找内部嵌套的 ZIP 包，
+    从中提取 PDF 发票，解析信息后重命名并存入输出目录。
+
+    Args:
+        f_zip_path: 主 ZIP 文件路径。
+        output_dir: 提取后的 PDF 存放目录。
+
+    Returns:
+        成功提取的 PDF 数量。
+    """
+    output_dir = Path(output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    extracted_count = 0
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        logger.info("正在解压并分析: %s", os.path.basename(str(f_zip_path)))
+        try:
+            with zipfile.ZipFile(f_zip_path, "r") as zip_ref:
+                zip_ref.extractall(temp_dir)
+        except zipfile.BadZipFile:
+            logger.warning("[跳过] %s 不是有效的 ZIP 包。", os.path.basename(str(f_zip_path)))
+            return 0
+
+        temp_path = Path(temp_dir)
+        for inner_zip in temp_path.rglob("*.zip"):
+            extract_subdir = inner_zip.with_suffix(inner_zip.suffix + "_extracted")
+            extract_subdir.mkdir(exist_ok=True)
+
+            try:
+                with zipfile.ZipFile(inner_zip, "r") as zf:
+                    zf.extractall(extract_subdir)
+            except zipfile.BadZipFile:
+                logger.debug("跳过无效嵌套 ZIP: %s", inner_zip.name)
+                continue
+
+            for pdf_file in extract_subdir.rglob("*.pdf"):
+                base_name = extract_ticket_info(pdf_file)
+                new_filename = f"{base_name}.pdf"
+                dest_path = output_dir / new_filename
+
+                # 处理重名：自动添加递增序号后缀
+                counter = 1
+                while dest_path.exists():
+                    new_filename = f"{base_name}_{counter}.pdf"
+                    dest_path = output_dir / new_filename
+                    counter += 1
+
+                shutil.copy2(pdf_file, dest_path)
+                logger.info("[成功] 提取并重命名: %s", new_filename)
+                extracted_count += 1
+
+    return extracted_count
+
+
+def organize_invoices(
+    input_dir: str | Path,
+    output_dir: Optional[str | Path] = None,
+) -> int:
+    """
+    批量整理指定目录下的所有铁路电子发票 ZIP 包。
+
+    Args:
+        input_dir: 包含 ZIP 文件的目录路径。
+        output_dir: 输出目录路径。默认为 input_dir/已命名的火车发票汇总。
+
+    Returns:
+        成功提取的 PDF 总数量。
+    """
+    input_dir = Path(input_dir)
+    if not input_dir.exists():
+        raise FileNotFoundError(f"输入目录不存在: {input_dir}")
+
+    if output_dir is None:
+        output_dir = input_dir / "已命名的火车发票汇总"
+    else:
+        output_dir = Path(output_dir)
+
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    zip_files = sorted([f for f in input_dir.iterdir() if f.suffix.lower() == ".zip"])
+
+    if not zip_files:
+        logger.warning("在 %s 下没有找到任何 .zip 文件！", input_dir)
+        return 0
+
+    logger.info("共找到 %d 个 ZIP 文件，开始处理...", len(zip_files))
+
+    total = 0
+    for zip_file in zip_files:
+        total += process_single_f_file(zip_file, output_dir)
+
+    logger.info("处理完成！共提取 %d 张发票，存放于: %s", total, output_dir)
+    return total

train_invoice_organizer-0.1.0/src/train_invoice_organizer/gui.py

@@ -0,0 +1,86 @@
+"""
+macOS 原生图形交互入口。
+
+安装库后，macOS 用户可直接运行：
+    train-invoice-gui
+
+它会弹出系统原生的目录选择框，处理完成后自动在 Finder 中打开结果文件夹。
+"""
+
+import logging
+import os
+import subprocess
+import sys
+
+from .core import organize_invoices
+
+logger = logging.getLogger(__name__)
+
+
+def select_directory_mac() -> str:
+    """使用 Mac 原生的 AppleScript 调出目录选择框。"""
+    apple_script = """
+    try
+        tell application "SystemUIServer"
+            activate
+            set myFolder to choose folder with prompt "请选择包含火车票发票 ZIP 文件的目录:"
+        end tell
+        return POSIX path of myFolder
+    on error
+        return ""
+    end try
+    """
+    try:
+        result = subprocess.run(
+            ["osascript", "-e", apple_script],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+        return result.stdout.strip()
+    except Exception as exc:
+        logger.error("调出目录选择器失败: %s", exc)
+        return ""
+
+
+def open_finder(path: str) -> None:
+    """在 Finder 中打开指定路径。"""
+    try:
+        subprocess.run(["open", path], check=False)
+    except Exception as exc:
+        logger.warning("无法自动打开 Finder: %s", exc)
+
+
+def main() -> int:
+    """macOS 图形交互入口。"""
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(levelname)s: %(message)s",
+        stream=sys.stdout,
+    )
+
+    print("正在启动目录选择器...")
+    selected_dir = select_directory_mac()
+
+    if not selected_dir:
+        print("\n已取消选择。")
+        return 1
+
+    print(f"\n您选择的目录是: {selected_dir}")
+
+    try:
+        organize_invoices(selected_dir)
+    except FileNotFoundError as exc:
+        logger.error(exc)
+        return 1
+
+    # 处理完成后自动打开 Finder
+    output_dir = os.path.join(selected_dir, "已命名的火车发票汇总")
+    if os.path.exists(output_dir):
+        open_finder(output_dir)
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: train-invoice-organizer
+Version: 0.1.0
+Summary: 自动提取铁路电子发票 ZIP 包中的 PDF，按乘车日期、时间、票价重命名整理
+Author-email: Violin True <ncunxi@sina.com>
+License: MIT
+Project-URL: Homepage, https://gitee.com/chuwanglin/train-invoice-organizer
+Project-URL: Repository, https://gitee.com/chuwanglin/train-invoice-organizer
+Keywords: train,invoice,railway,pdf,ticket,rename,organizer
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Office/Business :: Financial
+Classifier: Topic :: Utilities
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: PyMuPDF>=1.23.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: build>=0.10; extra == "dev"
+Requires-Dist: twine>=4.0; extra == "dev"
+Dynamic: license-file
+
+# train-invoice-organizer
+
+自动提取铁路电子发票 ZIP 包中的 PDF，按**乘车日期**、**时间**、**票价**重命名整理。
+
+## 功能
+
+- 递归解压嵌套的 ZIP 包（F 文件 → 内部 ZIP → PDF 发票）
+- 用 PyMuPDF 从 PDF 中智能提取乘车日期、发车时间和票价
+- 自动按 `YYYYMMDD_HHMM_价格.pdf` 格式重命名
+- 遇到同名文件自动添加序号后缀
+- 支持命令行一键运行，也支持作为 Python 库导入调用
+
+## 安装
+
+```bash
+pip install train-invoice-organizer
+```
+
+## 使用方式
+
+### 1. 命令行（安装后直接使用）
+
+```bash
+# 处理当前目录下的所有 ZIP 文件
+train-invoice-organizer
+
+# 指定目录
+train-invoice-organizer /path/to/your/zip/files
+
+# 指定输出目录
+train-invoice-organizer /path/to/zip/files -o /path/to/output
+
+# 显示详细日志
+train-invoice-organizer /path/to/zip/files -v
+```
+
+### 2. macOS 原生图形界面（推荐 Mac 用户）
+
+```bash
+# 弹出系统原生目录选择框，处理完成后自动打开 Finder
+train-invoice-gui
+```
+
+### 3. 作为 Python 库导入
+
+```python
+from train_invoice_organizer import organize_invoices, extract_ticket_info
+
+# 批量整理整个目录
+total = organize_invoices("/path/to/zip/files")
+print(f"共提取 {total} 张发票")
+
+# 或单独解析单张 PDF 信息
+info = extract_ticket_info("/path/to/single_ticket.pdf")
+print(info)  # 例如: 20260807_0845_104
+```
+
+## 提取规则
+
+| 字段 | 提取策略 |
+|------|---------|
+| **乘车日期** | 优先匹配 "日期+时间" 连续出现格式；若 PDF 排版导致分离，则先剔除 "开票日期" 干扰项，再匹配剩余日期 |
+| **时间** | 匹配 `HH:MM` 格式 |
+| **票价** | 优先匹配 `¥/￥` 后的整数；备用匹配 `(小写)104.00` 格式 |
+
+## 输出示例
+
+```
+已命名的火车发票汇总/
+├── 20260807_0845_104.pdf
+├── 20260808_1430_156.pdf
+├── 20260810_0920_89_1.pdf   # 重名时自动加序号
+└── 20260810_0920_89_2.pdf
+```
+
+## 依赖
+
+- Python >= 3.8
+- [PyMuPDF](https://pypi.org/project/PyMuPDF/) (fitz)
+
+## 开源协议
+
+MIT License

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+LICENSE
+README.md
+pyproject.toml
+src/train_invoice_organizer/__init__.py
+src/train_invoice_organizer/cli.py
+src/train_invoice_organizer/core.py
+src/train_invoice_organizer/gui.py
+src/train_invoice_organizer.egg-info/PKG-INFO
+src/train_invoice_organizer.egg-info/SOURCES.txt
+src/train_invoice_organizer.egg-info/dependency_links.txt
+src/train_invoice_organizer.egg-info/entry_points.txt
+src/train_invoice_organizer.egg-info/requires.txt
+src/train_invoice_organizer.egg-info/top_level.txt

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+train-invoice-gui = train_invoice_organizer.gui:main
+train-invoice-organizer = train_invoice_organizer.cli:main

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/requires.txt

@@ -0,0 +1,6 @@
+PyMuPDF>=1.23.0
+
+[dev]
+pytest>=7.0
+build>=0.10
+twine>=4.0

train_invoice_organizer-0.1.0/src/train_invoice_organizer.egg-info/top_level.txt

@@ -0,0 +1 @@
+train_invoice_organizer