Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,127 @@
+"""
+药店拜访助手 - Hugging Face Spaces 版本
+使用 Gradio SDK（免费）+ FastAPI 自定义路由
+"""
+import gradio as gr
+from fastapi import Request, UploadFile, File
+from fastapi.responses import HTMLResponse, JSONResponse, Response
+from fastapi.middleware.cors import CORSMiddleware
+import io
+import json
+import os
+import sys
+import platform
+import shutil
+
+# 确保能导入同目录模块
+WORK_DIR = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, WORK_DIR)
+
+# 导入导出服务核心函数
+from export_server import generate_docx
+
+# 导入OCR
+import pytesseract
+from PIL import Image
+
+# 跨平台 Tesseract 配置
+if platform.system() == 'Windows':
+    pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
+    os.environ['TESSDATA_PREFIX'] = os.path.expandvars(r'%USERPROFILE%\.tesseract\tessdata')
+else:
+    tesseract_bin = shutil.which('tesseract')
+    if tesseract_bin:
+        pytesseract.pytesseract.tesseract_cmd = tesseract_bin
+    for _tessdata in ['/usr/share/tesseract-ocr/5/tessdata',
+                      '/usr/share/tesseract-ocr/4.00/tessdata',
+                      '/usr/share/tessdata']:
+        if os.path.isdir(_tessdata):
+            os.environ.setdefault('TESSDATA_PREFIX', _tessdata)
+            break
+
+# 读取H5页面内容
+H5_FILE = os.path.join(WORK_DIR, 'test-h5.html')
+with open(H5_FILE, 'r', encoding='utf-8') as f:
+    h5_content = f.read()
+
+# 创建 Gradio Blocks（HF Spaces 要求 demo 变量）
+demo = gr.Blocks(css="footer{display:none !important}")
+
+with demo:
+    gr.HTML('<script>window.location.href="/app";</script>')
+
+# 启动 Gradio 获取底层 FastAPI 应用
+app, _, _ = demo.launch(
+    prevent_thread_lock=True,
+    server_name="0.0.0.0",
+    server_port=7860,
+    quiet=True,
+    show_error=True
+)
+
+# 添加 CORS 支持
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# ===== 自定义路由 =====
+
+@app.get("/app", response_class=HTMLResponse)
+async def serve_h5():
+    """返回 H5 页面"""
+    return HTMLResponse(content=h5_content)
+
+@app.get("/health")
+async def health():
+    """健康检查"""
+    return {"status": "ok"}
+
+@app.post("/ocr")
+async def ocr_endpoint(file: UploadFile = File(...)):
+    """OCR 识别接口"""
+    try:
+        image_data = await file.read()
+        img = Image.open(io.BytesIO(image_data))
+        w, h = img.size
+        max_dim = 2000
+        if w > max_dim or h > max_dim:
+            ratio = min(max_dim / w, max_dim / h)
+            img = img.resize((int(w * ratio), int(h * ratio)), Image.LANCZOS)
+        text = pytesseract.image_to_string(img, lang='chi_sim', config='--psm 6')
+        result = {"text": text.strip(), "length": len(text.strip())}
+        print(f"[OCR] 识别成功，提取 {len(text.strip())} 个字符")
+        return JSONResponse(content=result)
+    except Exception as e:
+        print(f"[OCR] 识别失败: {e}")
+        return JSONResponse(content={"error": f"OCR识别失败: {str(e)}"}, status_code=500)
+
+@app.post("/export")
+async def export_endpoint(request: Request):
+    """Word 文档导出接口"""
+    try:
+        body = await request.body()
+        visit_data = json.loads(body)
+        buffer = generate_docx(visit_data)
+        filename = 'visit_%s_%sstores.docx' % (
+            visit_data.get('visitDateDisplay', '').replace('.', '-'),
+            visit_data.get('totalCount', 0)
+        )
+        print(f"[Export] 导出成功: {filename}")
+        return Response(
+            content=buffer.getvalue(),
+            media_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+            headers={"Content-Disposition": f'attachment; filename="{filename}"'}
+        )
+    except Exception as e:
+        print(f"[Export] 导出失败: {e}")
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+print("=" * 50)
+print("  药店拜访助手 - HF Spaces 版本已启动")
+print("  H5 页面: /app")
+print("  OCR 接口: /ocr")
+print("  导出接口: /export")
+print("=" * 50)