pipx install magika

brew install magika

curl -LsSf https://securityresearch.google/magika/install.sh | sh

powershell -ExecutionPolicy Bypass -c "irm https://securityresearch.google/magika/install.ps1 | iex"

cargo install --locked magika-cli

pip install magika

npm install magika

% cd tests_data/basic && magika -r * | head
asm/code.asm: Assembly (code)
batch/simple.bat: DOS batch file (code)
c/code.c: C source (code)
css/code.css: CSS source (code)
csv/magika_test.csv: CSV document (code)
dockerfile/Dockerfile: Dockerfile (code)
docx/doc.docx: Microsoft Word 2007+ document (document)
docx/magika_test.docx: Microsoft Word 2007+ document (document)
eml/sample.eml: RFC 822 mail (text)
empty/empty_file: Empty file (inode)

% magika ./tests_data/basic/python/code.py --json
[
  {
    "path": "./tests_data/basic/python/code.py",
    "result": {
      "status": "ok",
      "value": {
        "dl": {
          "description": "Python source",
          "extensions": [
            "py",
            "pyi"
          ],
          "group": "code",
          "is_text": true,
          "label": "python",
          "mime_type": "text/x-python"
        },
        "output": {
          "description": "Python source",
          "extensions": [
            "py",
            "pyi"
          ],
          "group": "code",
          "is_text": true,
          "label": "python",
          "mime_type": "text/x-python"
        },
        "score": 0.996999979019165
      }
    }
  }
]

% cat tests_data/basic/ini/doc.ini | magika -
-: INI configuration file (text)

% magika --help
Determines file content types using AI

Usage: magika [OPTIONS] [PATH]...

Arguments:
  [PATH]...
          List of paths to the files to analyze.

          Use a dash (-) to read from standard input (can only be used once).

Options:
  -r, --recursive
          Identifies files within directories instead of identifying the directory itself

      --no-dereference
          Identifies symbolic links as is instead of identifying their content by following them

      --colors
          Prints with colors regardless of terminal support

      --no-colors
          Prints without colors regardless of terminal support

  -s, --output-score
          Prints the prediction score in addition to the content type

  -i, --mime-type
          Prints the MIME type instead of the content type description

  -l, --label
          Prints a simple label instead of the content type description

      --json
          Prints in JSON format

      --jsonl
          Prints in JSONL format

      --format <CUSTOM>
          Prints using a custom format (use --help for details).

          The following placeholders are supported:

            %p  The file path
            %l  The unique label identifying the content type
            %d  The description of the content type
            %g  The group of the content type
            %m  The MIME type of the content type
            %e  Possible file extensions for the content type
            %s  The score of the content type for the file
            %S  The score of the content type for the file in percent
            %b  The model output if overruled (empty otherwise)
            %%  A literal %

  -h, --help
          Print help (see a summary with '-h')

  -V, --version
          Print version

>>> from magika import Magika
>>> m = Magika()
>>> res = m.identify_bytes(b'function log(msg) {console.log(msg);}')
>>> print(res.output.label)
javascript

>>> from magika import Magika
>>> m = Magika()
>>> res = m.identify_path('./tests_data/basic/ini/doc.ini')
>>> print(res.output.label)
ini

>>> from magika import Magika
>>> m = Magika()
>>> with open('./tests_data/basic/ini/doc.ini', 'rb') as f:
>>>     res = m.identify_stream(f)
>>> print(res.output.label)
ini