[1309]MinerU、Magic-PDF、Magic-Doc

conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple

magic-pdf --version

pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/

git lfs install
git lfs clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit.git

# 首先安装modelscope
pip install modelscope

# 使用modelscope sdk下载模型
from modelscope import snapshot_download
model_dir = snapshot_download('opendatalab/PDF-Extract-Kit')
print(f"模型文件下载路径为：{model_dir}/models")

./
├── Layout  # 布局检测模型
│   ├── config.json
│   └── model_final.pth
├── MFD  # 公式检测
│   └── weights.pt
├── MFR  # 公式识别模型
│   └── UniMERNet
│       ├── config.json
│       ├── preprocessor_config.json
│       ├── pytorch_model.bin
│       ├── README.md
│       ├── tokenizer_config.json
│       └── tokenizer.json
│── TabRec # 表格识别模型
│   └─StructEqTable
│       ├── config.json
│       ├── generation_config.json
│       ├── model.safetensors
│       ├── preprocessor_config.json
│       ├── special_tokens_map.json
│       ├── spiece.model
│       ├── tokenizer.json
│       └── tokenizer_config.json 
│   └─ TableMaster 
│       └─ ch_PP-OCRv3_det_infer
│           ├── inference.pdiparams
│           ├── inference.pdiparams.info
│           └── inference.pdmodel
│       └─ ch_PP-OCRv3_rec_infer
│           ├── inference.pdiparams
│           ├── inference.pdiparams.info
│           └── inference.pdmodel
│       └─ table_structure_tablemaster_infer
│           ├── inference.pdiparams
│           ├── inference.pdiparams.info
│           └── inference.pdmodel
│       ├── ppocr_keys_v1.txt
│       └── table_master_structure_dict.txt
└── README.md

cp magic-pdf.template.json ~/magic-pdf.json

{
  "models-dir": "/tmp/models"
}

pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118

{
  "device-mode":"cuda"
}

{
  "device-mode":"mps"
}

magic-pdf --help
Usage: magic-pdf [OPTIONS]

Options:
  -v, --version                display the version and exit
  -p, --path PATH              local pdf filepath or directory  [required]
  -o, --output-dir TEXT        output local directory
  -m, --method [ocr|txt|auto]  the method for parsing pdf.
                               ocr: using ocr technique to extract information from pdf,
                               txt: suitable for the text-based pdf only and outperform ocr,
                               auto: automatically choose the best method for parsing pdf
                                  from ocr and txt.
                               without method specified, auto will be used by default.
  --help                       Show this message and exit.


## show version
magic-pdf -v

## command line example
magic-pdf -p {some_pdf} -o {some_output_dir} -m auto

├── some_pdf.md                          # markdown 文件
├── images                               # 存放图片目录
├── some_pdf_layout.pdf                  # layout 绘图
├── some_pdf_middle.json                 # minerU 中间处理结果
├── some_pdf_model.json                  # 模型推理结果
├── some_pdf_origin.pdf                  # 原 pdf 文件
└── some_pdf_spans.pdf                   # 最小粒度的bbox位置信息绘图

import os
import json

from loguru import logger

from magic_pdf.pipe.UNIPipe import UNIPipe
from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter

import magic_pdf.model as model_config 
model_config.__use_inside_model__ = True

try:
    current_script_dir = os.path.dirname(os.path.abspath(__file__))
    demo_name = "demo1"
    pdf_path = os.path.join(current_script_dir, f"{demo_name}.pdf")
    model_path = os.path.join(current_script_dir, f"{demo_name}.json")
    pdf_bytes = open(pdf_path, "rb").read()
    # model_json = json.loads(open(model_path, "r", encoding="utf-8").read())
    model_json = []  # model_json传空list使用内置模型解析
    jso_useful_key = {"_pdf_type": "", "model_list": model_json}
    local_image_dir = os.path.join(current_script_dir, 'images')
    image_dir = str(os.path.basename(local_image_dir))
    image_writer = DiskReaderWriter(local_image_dir)
    pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
    pipe.pipe_classify()
    """如果没有传入有效的模型数据，则使用内置model解析"""
    if len(model_json) == 0:
        if model_config.__use_inside_model__:
            pipe.pipe_analyze()
        else:
            logger.error("need model list input")
            exit(1)
    pipe.pipe_parse()
    md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
    with open(f"{demo_name}.md", "w", encoding="utf-8") as f:
        f.write(md_content)
except Exception as e:
    logger.exception(e)

apt-get/yum/brew install libreoffice

安装 libreoffice 
添加 "install_dir\LibreOffice\program" to 环境变量 PATH

pip install fairy-doc[cpu] # 安装 cpu 版本 
或 
pip install fairy-doc[gpu] # 安装 gpu 版本

# for local file
from magic_doc.docconv import DocConverter, S3Config
converter = DocConverter(s3_config=None)
markdown_content, time_cost = converter.convert("some_doc.pptx", conv_timeout=300)

# for remote file located in aws s3
from magic_doc.docconv import DocConverter, S3Config

s3_config = S3Config(ak='${ak}', sk='${sk}', endpoint='${endpoint}')
converter = DocConverter(s3_config=s3_config)
markdown_content, time_cost = converter.convert("s3://some_bucket/some_doc.pptx", conv_timeout=300)