用 Python 把 PDF 玩的明明白白

pip install pdf2zh

# 翻译完整文档
pdf2zh example.pdf
# 翻译部分文档
pdf2zh example.pdf -p 1-3,5
# 使用指定语言翻译
pdf2zh example.pdf -li en -lo ja


# 使用 DeepL/DeepLX 翻译
# 参考 [DeepLX](https://github.com/OwO-Network/DeepLX)
# 设置环境变量构建接入点：`{DEEPL_SERVER_URL}/translate`
# - `DEEPL_SERVER_URL`（可选）, e.g., `export DEEPL_SERVER_URL=https://api.deepl.com`
# - `DEEPL_AUTH_KEY`, e.g., `export DEEPL_AUTH_KEY=xxx`
pdf2zh example.pdf -s deepl



# 使用 Ollama 翻译
# 参考 [Ollama](https://github.com/ollama/ollama)
# 设置环境变量构建接入点：`{OLLAMA_HOST}/api/chat`
# - `OLLAMA_HOST`（可选）, e.g., `export OLLAMA_HOST=https://localhost:11434`
pdf2zh example.pdf -s ollama:gemma2


# 使用 OpenAI/SiliconCloud/Zhipu 翻译
# 参考 [SiliconCloud](https://docs.siliconflow.cn/quickstart), [Zhipu](https://open.bigmodel.cn/dev/api/thirdparty-frame/openai-sdk)
# 设置环境变量构建接入点：`{OPENAI_BASE_URL}/chat/completions`
# - `OPENAI_BASE_URL`（可选）, e.g., `export OPENAI_BASE_URL=https://api.openai.com/v1`
# - `OPENAI_API_KEY`, e.g., `export OPENAI_API_KEY=xxx`
pdf2zh example.pdf -s openai:gpt-4o



# 使用正则表达式指定需要保留样式的字体和字符
pdf2zh example.pdf -f "(CM[^RT].*|MS.*|.*Ital)" -c "(\(|\||\)|\+|=|\d|[\u0080-\ufaff])"

pdf2htmlEX /path/to/foobar.pdf

pdf2htmlEX --help

pdf2htmlEX --zoom 1.3 pdf/test.pdf

import pymupdf # imports the pymupdf library
doc = pymupdf.open("example.pdf") # open a document
for page in doc: # iterate the document pages
  text = page.get_text() # get plain text encoded as UTF-8

from pdfminer.high_level import extract_text

text = extract_text("example.pdf")
print(text)

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://mirrors.aliyun.com/pypi/simple

windows 的用户目录为 "C:\Users\用户名",
linux 用户目录为 "/home/用户名"
macOS 用户目录为 "/Users/用户名"

{
    // other config
    "layout-config": {
        "model": "layoutlmv3" // 使用 doclayout_yolo 请修改为“doclayout_yolo"
    },
    "formula-config": {
        "mfd_model": "yolo_v8_mfd",
        "mfr_model": "unimernet_small",
        "enable": true  // 公式识别功能默认是开启的，如果需要关闭请修改此处的值为"false"
    },
    "table-config": {
        "model": "rapid_table",  // 默认使用"rapid_table",可以切换为"tablemaster"和"struct_eqtable"
        "enable": false, // 表格识别功能默认是关闭的，如果需要开启请修改此处的值为"true"
        "max_time": 400
    }
}

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 PATH        output local directory  [required]
  -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.
  -l, --lang TEXT              Input the languages in the pdf (if known) to
                               improve OCR accuracy.  Optional. You should
                               input "Abbreviation" with language form url: ht
                               tps://paddlepaddle.github.io/PaddleOCR/latest/en
                               /ppocr/blog/multi_languages.html#5-support-languages-
                               and-abbreviations
  -d, --debug BOOLEAN          Enables detailed debugging information during
                               the execution of the CLI commands.
  -s, --start INTEGER          The starting page for PDF parsing, beginning
                               from 0.
  -e, --end INTEGER            The ending page for PDF parsing, beginning from
                               0.
  --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

conda create -n doclayout_yolo python=3.10
conda activate doclayout_yolo
pip install -e .

pip install doclayout-yolo

python demo.py --model path/to/model --image-path path/to/image

import cv2
from doclayout_yolo import YOLOv10

# Load the pre-trained model
model = YOLOv10("path/to/provided/model")

# Perform prediction
det_res = model.predict(
    "path/to/image",   # Image to predict
    imgsz=1024,        # Prediction image size
    conf=0.2,          # Confidence threshold
    device="cuda:0"    # Device to use (e.g., 'cuda:0' or 'cpu')
)

# Annotate and save the result
annotated_frame = det_res[0].plot(pil=True, line_width=5, font_size=20)
cv2.imwrite("result.jpg", annotated_frame)