""" 财务报销自动化 — Web 界面 用户上传 PDF 发票和支付截图，配置账号信息，自动完成： 1. 发票提取 2. OCR 识别 3. 浏览器填报（可选） 启动: python web/app.py 访问: http://localhost:5000 """ import io import json import logging import sys import threading import time import uuid from pathlib import Path from flask import Flask, Response, jsonify, render_template, request, stream_with_context # 确保项目根目录在 sys.path PROJECT_ROOT = Path(__file__).parent.parent.resolve() sys.path.insert(0, str(PROJECT_ROOT)) from app.config import load_config as load_project_config from app.extractor import extract_invoices, save_csv, save_markdown from app.ocr import enrich_with_ocr, _save_csv as save_ocr_csv, save_markdown_from_csv, _load_csv as load_ocr_csv app = Flask(__name__, template_folder="templates") UPLOAD_BASE = PROJECT_ROOT / "web" / "uploads" SESSION_LOG_FILE = "session.log" SESSION_RESULT_FILE = "result.json" # ================================================================ # 日志收集器 — 捕获管道日志到文件，SSE 端点通过 tail -f 读取 # ================================================================ class _SSELogHandler(logging.Handler): """将日志写入指定文件（线程安全）""" def __init__(self, log_path: Path): super().__init__() self._lock = threading.Lock() self._file = open(log_path, "w", encoding="utf-8") def emit(self, record: logging.LogRecord): try: msg = self.format(record) + "\n" with self._lock: self._file.write(msg) self._file.flush() except Exception: pass def close_file(self): try: self._file.close() except Exception: pass def _install_log_collector(session_dir: Path) -> _SSELogHandler: """安装日志收集器到 app.* 模块""" log_path = session_dir / SESSION_LOG_FILE fmt = logging.Formatter( "%(asctime)s [%(levelname)-5s] %(name)s: %(message)s", "%Y-%m-%d %H:%M:%S", ) handler = _SSELogHandler(log_path) handler.setFormatter(fmt) handler.setLevel(logging.INFO) for name in ["extractor", "ocr", "pipeline", "bot"]: logger = logging.getLogger(name) logger.setLevel(logging.INFO) logger.addHandler(handler) return handler def _remove_log_collector(handler: _SSELogHandler): for name in ["extractor", "ocr", "pipeline", "bot"]: logging.getLogger(name).removeHandler(handler) handler.close_file() # ================================================================ # 管道入口 # ================================================================ # ================================================================ # 管道入口 # ================================================================ def run_pipeline_web(session_dir: Path, config: dict, run_bot: bool = False): """在 Web 会话目录中执行管道，结果写入 session 目录下的文件""" start = time.time() # ---- Step 1: 发票提取 ---- invoices = extract_invoices(str(session_dir)) if not invoices: return {"ok": False, "error": "未提取到任何发票数据"} save_csv(invoices, session_dir / "invoice_summary.csv") save_markdown(invoices, session_dir / "invoice_summary.md") # ---- Step 2: OCR 识别 ---- csv_path = session_dir / "invoice_summary.csv" rows = load_ocr_csv(csv_path) if rows is None: return {"ok": False, "error": "CSV 读取失败"} rows = enrich_with_ocr(rows, str(session_dir)) save_ocr_csv(csv_path, rows) save_markdown_from_csv(csv_path, rows) # ---- Step 3: 浏览器填报（可选）---- if run_bot: from app.bot import load_invoice_data, run_bot_web bot_invoices = load_invoice_data(str(csv_path), config) run_bot_web(config, bot_invoices, session_dir) elapsed = time.time() - start return { "ok": True, "elapsed": f"{elapsed:.1f}s", "invoice_count": len(rows), "csv_url": f"/api/download/{session_dir.name}/invoice_summary.csv", "md_url": f"/api/download/{session_dir.name}/invoice_summary.md", } def run_csv_pipeline_web(session_dir: Path, config: dict, csv_filename: str, run_bot: bool = False): """直接使用上传的 CSV 文件进行填报，跳过 PDF 提取和 OCR""" start = time.time() csv_path = session_dir / csv_filename if not csv_path.exists(): return {"ok": False, "error": "CSV 文件不存在"} # 读取 CSV 行数 rows = load_ocr_csv(csv_path) if rows is None: return {"ok": False, "error": "CSV 读取失败"} # 浏览器填报 if run_bot: from app.bot import load_invoice_data, run_bot_web bot_invoices = load_invoice_data(str(csv_path), config) run_bot_web(config, bot_invoices, session_dir) elapsed = time.time() - start return { "ok": True, "elapsed": f"{elapsed:.1f}s", "invoice_count": len(rows), "csv_url": f"/api/download/{session_dir.name}/{csv_filename}", } # ================================================================ # Flask 路由 # ================================================================ @app.route("/") def index(): return render_template("index.html") @app.route("/api/session", methods=["POST"]) def create_session(): """创建上传会话，返回 session_id""" sid = uuid.uuid4().hex[:12] session_dir = UPLOAD_BASE / sid session_dir.mkdir(parents=True, exist_ok=True) return jsonify({"session_id": sid}) @app.route("/api/upload/", methods=["POST"]) def upload_file(session_id: str): """上传 PDF 或图片""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir f = request.files.get("file") if not f or not f.filename: return jsonify({"error": "未选择文件"}), 400 safe_name = Path(f.filename).name f.save(str(session_dir / safe_name)) return jsonify({"ok": True, "filename": safe_name}) @app.route("/api/upload-csv/", methods=["POST"]) def upload_csv(session_id: str): """上传 CSV 发票数据文件（跳过 PDF 提取和 OCR）""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir f = request.files.get("file") if not f or not f.filename: return jsonify({"error": "未选择文件"}), 400 safe_name = Path(f.filename).name f.save(str(session_dir / safe_name)) return jsonify({"ok": True, "filename": safe_name}) @app.route("/api/files/", methods=["GET"]) def list_files(session_id: str): """列出会话目录中的文件""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir pdfs = sorted(f.name for f in session_dir.glob("*.pdf")) imgs = sorted( f.name for ext in {".png", ".jpg", ".jpeg", ".bmp", ".webp"} for f in session_dir.glob(f"*{ext}") ) return jsonify({"pdfs": pdfs, "images": imgs}) @app.route("/api/process/", methods=["POST"]) def start_process(session_id: str): """启动管道处理""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir body = request.get_json(silent=True) or {} run_bot_flag = body.get("submit", False) mode = body.get("mode", "auto") # "pdf", "csv", or "auto" # 读取配置 config = _build_web_config(body) # 写入配置到会话目录 with open(session_dir / "config.json", "w", encoding="utf-8") as f: json.dump(config, f, ensure_ascii=False, indent=2, default=str) # 在后台线程执行 handler = _install_log_collector(session_dir) def _run(): result = {"ok": False, "error": "未知错误"} try: if mode == "csv": # CSV 模式：直接使用上传的 CSV，跳过 PDF 提取和 OCR csv_files = list(session_dir.glob("*.csv")) if not csv_files: result = {"ok": False, "error": "未找到 CSV 文件"} else: result = run_csv_pipeline_web(session_dir, config, csv_files[0].name, run_bot_flag) else: # 自动检测：如果有 CSV 则走 csv 管道，否则走 pdf 管道 csv_files = list(session_dir.glob("*.csv")) pdf_files = list(session_dir.glob("*.pdf")) if csv_files and not pdf_files: result = run_csv_pipeline_web(session_dir, config, csv_files[0].name, run_bot_flag) else: result = run_pipeline_web(session_dir, config, run_bot_flag) except BaseException as e: result = {"ok": False, "error": str(e)} if isinstance(e, (KeyboardInterrupt, SystemExit)): raise finally: try: # 原子写入：先写临时文件，再重命名，避免 SSE 读到截断的空文件 tmp_path = session_dir / (SESSION_RESULT_FILE + ".tmp") with open(tmp_path, "w", encoding="utf-8") as f: json.dump(result, f, ensure_ascii=False) tmp_path.replace(session_dir / SESSION_RESULT_FILE) except Exception: pass _remove_log_collector(handler) threading.Thread(target=_run, daemon=True).start() return jsonify({"status": "started"}) @app.route("/api/logs/") def stream_logs(session_id: str): """SSE 日志流""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir def generate(): # 先发送已有日志 log_file = session_dir / SESSION_LOG_FILE last_size = 0 start_time = time.time() timeout = 600 # 10 分钟超时 while time.time() - start_time < timeout: if log_file.exists(): current_size = log_file.stat().st_size if current_size > last_size: with open(log_file, encoding="utf-8", errors="replace") as f: f.seek(last_size) chunk = f.read() if chunk: yield f"data: {_escape_sse(chunk)}\n\n" last_size = current_size # 也通过队列发送实时日志 # 检查是否完成 result_file = session_dir / SESSION_RESULT_FILE if result_file.exists(): with open(result_file, encoding="utf-8") as f: result = json.load(f) yield f"data: {_escape_sse(json.dumps({'type': 'done', 'result': result}, ensure_ascii=False))}\n\n" break time.sleep(0.5) return Response( stream_with_context(generate()), mimetype="text/event-stream", headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"}, ) @app.route("/api/download//") def download_file(session_id: str, filename: str): """下载生成的文件""" session_dir = _validate_session(session_id) if isinstance(session_dir, tuple): return session_dir filepath = session_dir / filename if not filepath.exists(): return jsonify({"error": "文件不存在"}), 404 return Response(filepath.read_bytes(), mimetype="application/octet-stream") # ================================================================ # 辅助函数 # ================================================================ def _validate_session(session_id: str): session_dir = UPLOAD_BASE / session_id if not session_dir.exists(): return jsonify({"error": "会话不存在"}), 404 return session_dir def _build_web_config(body: dict) -> dict: """从请求体构建配置""" config = load_project_config() for key in ("username", "password", "default_name", "default_card_no", "default_person_id"): if body.get(key): config[key] = body[key] return config def _escape_sse(text: str) -> str: """SSE 数据转义，同时处理 Windows 行尾 \\r\\n""" return text.replace("\r\n", "\n").replace("\r", "\n").replace("\n", "\ndata: ") if __name__ == "__main__": UPLOAD_BASE.mkdir(parents=True, exist_ok=True) print(f"启动 Web 服务: http://localhost:5000") app.run(host="0.0.0.0", port=5000, debug=True, threaded=True, use_reloader=False)