Upload 4 files

Dockerfile

@@ -0,0 +1,34 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+# 安装系统依赖
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libpq-dev \
+    tesseract-ocr \
+    poppler-utils \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# 克隆 MinerU 项目
+RUN git clone https://github.com/myhloli/MinerU.git /tmp/MinerU \
+    && cp -r /tmp/MinerU/magic_pdf /app/magic_pdf \
+    && rm -rf /tmp/MinerU
+
+# 复制必要文件
+COPY requirements.txt .
+COPY app.py .
+COPY download_models.py .
+
+# 安装 Python 依赖
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 下载模型
+RUN python download_models.py
+
+# 设置环境变量
+ENV PORT=7860
+
+# 启动应用
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"] 

app.py

@@ -0,0 +1,44 @@
+from fastapi import FastAPI, File, UploadFile
+from magic_pdf.magic_pdf import MagicPDF
+import tempfile
+import os
+import json
+import shutil
+
+app = FastAPI(title="MinerU PDF Processing API",
+             description="API for processing PDF documents using MinerU",
+             version="1.0.0")
+
+# 初始化 MagicPDF
+config_file = os.path.join(os.path.expanduser('~'), 'magic-pdf.json')
+magic_pdf = MagicPDF(config_file)
+
+@app.post("/process_pdf")
+async def process_pdf(file: UploadFile = File(...)):
+    """
+    处理上传的PDF文件并返回分析结果
+    """
+    if not file.filename.lower().endswith('.pdf'):
+        return {"error": "Only PDF files are supported"}
+    
+    try:
+        # 创建临时目录
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # 保存上传的文件
+            temp_pdf = os.path.join(temp_dir, file.filename)
+            with open(temp_pdf, "wb") as buffer:
+                shutil.copyfileobj(file.file, buffer)
+            
+            # 处理 PDF
+            result = magic_pdf.process(temp_pdf)
+            
+            return result
+    except Exception as e:
+        return {"error": str(e)}
+
+@app.get("/health")
+async def health_check():
+    """
+    健康检查接口
+    """
+    return {"status": "healthy", "version": "1.0.0"} 

download_models.py

@@ -0,0 +1,69 @@
+import json
+import os
+
+import requests
+from modelscope import snapshot_download
+
+
+def download_json(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    return response.json()
+
+
+def download_and_modify_json(url, local_filename, modifications):
+    if os.path.exists(local_filename):
+        data = json.load(open(local_filename))
+        config_version = data.get('config_version', '0.0.0')
+        if config_version < '1.0.0':
+            data = download_json(url)
+    else:
+        data = download_json(url)
+
+    # 修改内容
+    for key, value in modifications.items():
+        data[key] = value
+
+    # 保存修改后的内容
+    with open(local_filename, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False, indent=4)
+
+
+if __name__ == '__main__':
+    # 在 Docker 环境中使用 /app 目录
+    base_dir = "/app"
+    models_dir = os.path.join(base_dir, "models")
+    os.makedirs(models_dir, exist_ok=True)
+    
+    mineru_patterns = [
+        "models/Layout/LayoutLMv3/*",
+        "models/Layout/YOLO/*",
+        "models/MFD/YOLO/*",
+        "models/MFR/unimernet_small/*",
+        "models/TabRec/TableMaster/*",
+        "models/TabRec/StructEqTable/*",
+    ]
+    
+    # 下载模型到 Docker 容器中的固定路径
+    model_dir = snapshot_download('opendatalab/PDF-Extract-Kit-1.0', 
+                                cache_dir=models_dir,
+                                allow_patterns=mineru_patterns)
+    layoutreader_model_dir = snapshot_download('ppaanngggg/layoutreader',
+                                             cache_dir=models_dir)
+    
+    model_dir = os.path.join(model_dir, 'models')
+    print(f'model_dir is: {model_dir}')
+    print(f'layoutreader_model_dir is: {layoutreader_model_dir}')
+
+    # 配置文件保存到 Docker 容器的固定路径
+    json_url = 'https://gitee.com/myhloli/MinerU/raw/master/magic-pdf.template.json'
+    config_file_name = 'magic-pdf.json'
+    config_file = os.path.join(base_dir, config_file_name)
+
+    json_mods = {
+        'models-dir': model_dir,
+        'layoutreader-model-dir': layoutreader_model_dir,
+    }
+
+    download_and_modify_json(json_url, config_file, json_mods)
+    print(f'配置文件已成功配置，路径为: {config_file}') 

requirements.txt

@@ -0,0 +1,13 @@
+fastapi==0.104.1
+python-multipart==0.0.6
+uvicorn==0.24.0
+modelscope==1.9.5
+torch==2.1.0
+transformers==4.35.2
+opencv-python-headless==4.8.1.78
+Pillow==10.1.0
+numpy==1.26.2
+pydantic==2.5.1
+python-magic==0.4.27
+pdf2image==1.16.3
+pytesseract==0.3.10