├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── pyproject.toml ├── tests ├── conftest.py └── test_textract_cli.py └── textract_cli ├── __init__.py ├── __main__.py └── cli.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | permissions: 8 | contents: read 9 | 10 | jobs: 11 | test: 12 | runs-on: ubuntu-latest 13 | strategy: 14 | matrix: 15 | python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"] 16 | steps: 17 | - uses: actions/checkout@v4 18 | - name: Set up Python ${{ matrix.python-version }} 19 | uses: actions/setup-python@v5 20 | with: 21 | python-version: ${{ matrix.python-version }} 22 | cache: pip 23 | cache-dependency-path: pyproject.toml 24 | - name: Install dependencies 25 | run: | 26 | pip install '.[test]' 27 | - name: Run tests 28 | run: | 29 | pytest 30 | deploy: 31 | runs-on: ubuntu-latest 32 | needs: [test] 33 | environment: release 34 | permissions: 35 | id-token: write 36 | steps: 37 | - uses: actions/checkout@v4 38 | - name: Set up Python 39 | uses: actions/setup-python@v5 40 | with: 41 | python-version: "3.12" 42 | cache: pip 43 | cache-dependency-path: pyproject.toml 44 | - name: Install dependencies 45 | run: | 46 | pip install setuptools wheel build 47 | - name: Build 48 | run: | 49 | python -m build 50 | - name: Publish 51 | uses: pypa/gh-action-pypi-publish@release/v1 -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push, pull_request] 4 | 5 | permissions: 6 | contents: read 7 | 8 | jobs: 9 | test: 10 | runs-on: ubuntu-latest 11 | strategy: 12 | matrix: 13 | python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"] 14 | steps: 15 | - uses: actions/checkout@v4 16 | - name: Set up Python ${{ matrix.python-version }} 17 | uses: actions/setup-python@v5 18 | with: 19 | python-version: ${{ matrix.python-version }} 20 | cache: pip 21 | cache-dependency-path: pyproject.toml 22 | - name: Install dependencies 23 | run: | 24 | pip install '.[test]' 25 | - name: Run tests 26 | run: | 27 | pytest -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # textract-cli 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/textract-cli.svg)](https://pypi.org/project/textract-cli/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/textract-cli?include_prereleases&label=changelog)](https://github.com/simonw/textract-cli/releases) 5 | [![Tests](https://github.com/simonw/textract-cli/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/textract-cli/actions/workflows/test.yml) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/textract-cli/blob/master/LICENSE) 7 | 8 | CLI for running files through AWS Textract 9 | 10 | ## Installation 11 | 12 | Install this tool using `pip`: 13 | ```bash 14 | pip install textract-cli 15 | ``` 16 | ## Configuration 17 | 18 | Any of the [methods for configuring](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/configuration.html) `boto3` will work with this tool. Environment variables or a `~/.aws/config` file are good options here. 19 | 20 | ## Usage 21 | 22 | To run Textract OCR against a JPEG or PNG file (must be smaller than 5MB): 23 | ```bash 24 | textract-cli image.jpeg 25 | ``` 26 | This will output to standard out. To save to a file use this: 27 | ```bash 28 | textract-cli image.jpeg > output.txt 29 | ``` 30 | Or use the `-o/--output` option like this: 31 | ```bash 32 | textract-cli image.jpeg -o output.txt 33 | ``` 34 | 35 | For help, run: 36 | ```bash 37 | textract-cli --help 38 | ``` 39 | You can also use: 40 | ```bash 41 | python -m textract_cli --help 42 | ``` 43 | ## Alternatives 44 | 45 | [amazon-textract-textractor](https://aws-samples.github.io/amazon-textract-textractor/commandline.html) an Amazon project offering a similar but much more comprehensive CLI. 46 | 47 | ## Development 48 | 49 | To contribute to this tool, first checkout the code. Then create a new virtual environment: 50 | ```bash 51 | cd textract-cli 52 | python -m venv venv 53 | source venv/bin/activate 54 | ``` 55 | Now install the dependencies and test dependencies: 56 | ```bash 57 | pip install -e '.[test]' 58 | ``` 59 | To run the tests: 60 | ```bash 61 | pytest 62 | ``` 63 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "textract-cli" 3 | version = "0.1" 4 | description = "CLI for running files through AWS Textract" 5 | readme = "README.md" 6 | authors = [{name = "Simon Willison"}] 7 | license = {text = "Apache-2.0"} 8 | requires-python = ">=3.8" 9 | classifiers = [ 10 | "License :: OSI Approved :: Apache Software License" 11 | ] 12 | dependencies = [ 13 | "click", 14 | "boto3" 15 | ] 16 | 17 | [project.urls] 18 | Homepage = "https://github.com/simonw/textract-cli" 19 | Changelog = "https://github.com/simonw/textract-cli/releases" 20 | Issues = "https://github.com/simonw/textract-cli/issues" 21 | CI = "https://github.com/simonw/textract-cli/actions" 22 | 23 | [project.entry-points.console_scripts] 24 | textract-cli = "textract_cli.cli:cli" 25 | 26 | [project.optional-dependencies] 27 | test = ["pytest", "moto[textract]"] 28 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | def pytest_configure(): 4 | os.environ["AWS_DEFAULT_REGION"] = "us-east-1" 5 | -------------------------------------------------------------------------------- /tests/test_textract_cli.py: -------------------------------------------------------------------------------- 1 | import boto3 2 | from click.testing import CliRunner 3 | from textract_cli.cli import cli 4 | from moto import mock_aws 5 | from moto.textract.models import TextractBackend 6 | import pytest 7 | 8 | 9 | TextractBackend.BLOCKS = [{"BlockType": "LINE", "Text": "This is a test image"}] 10 | 11 | 12 | @mock_aws 13 | @pytest.mark.parametrize("use_output_file", (False, True)) 14 | def test_start_document_text_detection(tmp_path, use_output_file): 15 | image_path = tmp_path / "test_image.jpeg" 16 | image_path.write_text("This is a test image") 17 | 18 | args = [str(image_path)] 19 | 20 | if use_output_file: 21 | output_path = tmp_path / "output.txt" 22 | args.extend(["-o", str(output_path)]) 23 | 24 | runner = CliRunner() 25 | result = runner.invoke(cli, args) 26 | assert result.exit_code == 0 27 | 28 | expected = "This is a test image" 29 | if use_output_file: 30 | assert expected in output_path.read_text("utf-8") 31 | else: 32 | assert expected in result.stdout 33 | -------------------------------------------------------------------------------- /textract_cli/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/simonw/textract-cli/bfb038adcc4cfa05776ad096a01a512a397e131f/textract_cli/__init__.py -------------------------------------------------------------------------------- /textract_cli/__main__.py: -------------------------------------------------------------------------------- 1 | from .cli import cli 2 | 3 | if __name__ == "__main__": 4 | cli() 5 | -------------------------------------------------------------------------------- /textract_cli/cli.py: -------------------------------------------------------------------------------- 1 | import boto3 2 | import click 3 | 4 | 5 | @click.command() 6 | @click.version_option() 7 | @click.argument("image_path", type=click.Path(exists=True)) 8 | @click.option( 9 | "-o", "--output", type=click.File("w"), help="Output file to write the results to" 10 | ) 11 | def cli(image_path, output): 12 | """CLI tool to extract text from an image using AWS Textract.""" 13 | # Create a Textract client 14 | client = boto3.client("textract") 15 | 16 | # Read the image as bytes 17 | with open(image_path, "rb") as image_file: 18 | image_bytes = image_file.read() 19 | 20 | # Call the detect_document_text API 21 | response = client.detect_document_text(Document={"Bytes": image_bytes}) 22 | # Collect the detected text 23 | detected_text = "\n".join( 24 | item["Text"] for item in response["Blocks"] if item["BlockType"] == "LINE" 25 | ) 26 | 27 | # Output the results 28 | if output: 29 | output.write(detected_text) 30 | else: 31 | click.echo(detected_text) 32 | --------------------------------------------------------------------------------