ci(pypi): Add integration with Github

.github/workflows/release.yml

@@ -34,5 +34,6 @@ jobs:
           NEW_VERSION="${POETRY_VERSION}.post${{ github.run_number }}"
           poetry version "${NEW_VERSION}"
         fi
+        poetry run task generate-pypi-readme
         poetry build
         poetry publish --username __token__ --password ${{ secrets.PUBLIC_PYPI_API_TOKEN }}

README.md

@@ -28,7 +28,10 @@
   <a href="http://hits.dwyl.com/alphanome-ai/sec-parser"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fhits.dwyl.com%2Falphanome-ai%2Fsec-parser.json%3Fshow%3Dunique" alt="HitCount" /></a>
   <a href="https://twitter.com/alphanomeai"><img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/alphanomeai"></a>
   <a href="https://github.com/JonSnow/MyBadges"><img src="https://img.shields.io/github/stars/alphanome-ai/sec-parser.svg?style=social&label=Star" alt="GitHub stars"></a>
+
+
 </p>
+
 <div align="left">
   Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual structure of the document.
 </div>
@@ -43,7 +46,6 @@
 
 ## Overview
 
-
 The `sec-parser` project simplifies the process of extracting meaningful information from SEC EDGAR HTML documents. It organizes the document's source code into a list or tree of elements that correspond to the visual structure of the document. This includes distinct elements for section titles, paragraphs, and tables, making the data easier to analyze and understand. 
 
 This tool is especially beneficial for Artificial Intelligence (AI) and Large Language Models (LLM) applications. It significantly improves the efficiency of data extraction and analysis in these fields.

Taskfile.yml

@@ -84,3 +84,27 @@ tasks:
     cmds:
       # PYTHONPATH is added to make streamlit watch file changes. Read more: https://docs.streamlit.io/knowledge-base/using-streamlit/streamlit-watch-changes-other-modules-importing-app
       - export PYTHONPATH=$PYTHONPATH:$(pwd)/sec_parser; poetry run streamlit run debug_tools/parser_output_visualizer/app.py --server.runOnSave=true
+
+########################
+### CI/CD Automation ###
+########################
+
+  generate-pypi-readme:
+    desc: Generate the README file for PyPI.
+    cmds:
+      # Copy the main README.md to docs/README-pypi.md for PyPI.
+      - cp README.md docs/README-pypi.md
+
+      # Check for the existence of the image tag in the newly copied README. Exit with error if not found.
+      # This will make sure the CI/CD fails, drawing attention to the problem.
+      - grep -q '<img src=\"docs/title.png\" alt=\"sec-parser logo\" height=\"40\"/>' docs/README-pypi.md || { echo "String not found!"; exit 1; }
+
+      # Replace the image tag with 'SEC-PARSER' text. 
+      # Output the result to a temporary file, avoiding in-place issues between macOS and Linux.
+      - sed 's/<img src=\"docs\/title.png\" alt=\"sec-parser logo\" height=\"40\"\/>/SEC-PARSER/g' docs/README-pypi.md > docs/README-pypi.md.tmp
+
+      # Replace repeating occurrences of &nbsp; with a single &nbsp;. This command is compatible with both macOS and Linux.
+      - if [[ "$OSTYPE" == "darwin"* ]]; then sed -E 's/(&nbsp;)+/\1/g' docs/README-pypi.md.tmp > docs/README-pypi.md; else sed -r 's/(&nbsp;)+/\1/g' docs/README-pypi.md.tmp > docs/README-pypi.md; fi
+
+      # Remove the temporary file, as it's no longer needed.
+      - rm docs/README-pypi.md.tmp

docs/README-pypi.md

@@ -0,0 +1,84 @@
+<p align="center">&nbsp;</p>
+<p align="center">
+  <h1 align="center">SEC-PARSER</h1>
+</p>
+<p align="left">
+  <!-- Using &nbsp; for alignment due to GitHub README limitations -->
+  <b>Essentials ➔&nbsp;</b>
+  <a href="LICENSE.txt"><img src="https://img.shields.io/github/license/alphanome-ai/sec-parser.svg" alt="Licence"></a>
+  <a href="https://project-types.github.io/#federation"><img src="https://img.shields.io/badge/project%20type-federation-brightgreen" alt="Project Type: Federation"></a>
+  <a href="https://github.com/mkenney/software-guides/blob/master/STABILITY-BADGES.md#experimental"><img src="https://img.shields.io/badge/stability-experimental-orange.svg" alt="Experimental"></a>
+  <br>
+  <b>Health ➔&nbsp;</b>
+  <a href="https://github.com/alphanome-ai/sec-parser/actions/workflows/check.yml"><img alt="GitHub Workflow Status (with event)" src="https://img.shields.io/github/actions/workflow/status/alphanome-ai/sec-parser/check.yml"></a>
+  <a href="https://github.com/alphanome-ai/sec-parser/commits/main"><img alt="Last Commit" src="https://img.shields.io/github/last-commit/alphanome-ai/sec-parser"></a>  
+  <br>
+  <b>Quality ➔&nbsp;</b>
+  <a href="https://codecov.io/gh/alphanome-ai/sec-parser"><img src="https://codecov.io/gh/alphanome-ai/sec-parser/graph/badge.svg?token=KJLA96CBCN" alt="codecov" /></a>
+  <a href="https://mypy-lang.org/"><img src="https://img.shields.io/badge/type%20checked-mypy-blue.svg"></a>
+  <a href="https://github.com/psf/black"><img alt="Code Style: Black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
+  <a href="https://github.com/astral-sh/ruff"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff"></a>
+  <br>
+  <b>Distribution ➔&nbsp;</b>
+  <a href="https://badge.fury.io/py/sec-parser"><img src="https://badge.fury.io/py/sec-parser.svg" alt="PyPI version" /></a>
+  <a href="https://pypi.org/project/sec-parser/"><img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/sec-parser"></a>
+  <a href="https://pypistats.org/packages/sec-parser"><img src="https://img.shields.io/pypi/dm/sec-parser.svg" alt="PyPI downloads"></a>
+  <br>
+  <b>Community ➔&nbsp;</b>
+  <a href="http://hits.dwyl.com/alphanome-ai/sec-parser"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fhits.dwyl.com%2Falphanome-ai%2Fsec-parser.json%3Fshow%3Dunique" alt="HitCount" /></a>
+  <a href="https://twitter.com/alphanomeai"><img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/alphanomeai"></a>
+  <a href="https://github.com/JonSnow/MyBadges"><img src="https://img.shields.io/github/stars/alphanome-ai/sec-parser.svg?style=social&label=Star" alt="GitHub stars"></a>
+
+
+</p>
+
+<div align="left">
+  Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual structure of the document.
+</div>
+<div align="center">
+  <b>
+  <a href="https://sec-parser-output-visualizer.app.alphanome.dev">Demo</a> |
+  <a href="https://github.com/alphanome-ai/sec-parser/discussions">Discussions</a> |
+  <a href="https://github.com/alphanome-ai/sec-parser/issues">Issues</a>
+  </b>
+</div>
+<br>
+
+## Overview
+
+The `sec-parser` project simplifies the process of extracting meaningful information from SEC EDGAR HTML documents. It organizes the document's source code into a list or tree of elements that correspond to the visual structure of the document. This includes distinct elements for section titles, paragraphs, and tables, making the data easier to analyze and understand. 
+
+This tool is especially beneficial for Artificial Intelligence (AI) and Large Language Models (LLM) applications. It significantly improves the efficiency of data extraction and analysis in these fields.
+
+[**Explore the Demo!**](https://sec-parser-output-visualizer.app.alphanome.dev/)
+
+## Installation
+
+You can install `sec-parser` using pip:
+
+```bash
+pip install sec-parser
+```
+
+## Usage
+
+```python
+import sec_parser as sp
+
+tree = sp.parse_latest("10-K", ticker="AAPL")
+
+# Show the general structure of the tree
+print(tree.render())
+```
+Console output:
+```
+RootSectionElement: PART I — FINANCIAL INFORMATION
+├── TitleElement: Item 1. Financial Statements
+│   ├── TitleElement: CONDENSED CONSOLIDATED STATEMENTS OF OPERATIONS (U...
+│   │   ├── TextElement: (In millions, except number of shares which are re...
+│   │   ├── TableElement: ...
+│   ...
+```
+
+# License
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

pyproject.toml

@@ -4,6 +4,7 @@ version = "0.8.0"
 description = "A robust and efficient parser for SEC filings, designed to extract and analyze financial data with ease."
 authors = ["Alphanome.AI <[email protected]>"]
 readme = "README.md"
+repository = "https://github.com/alphanome-ai/sec-parser"
 
 
 [tool.poetry.dependencies]