From a42d0a76813852d1defa4ebcdfe5f0b739edb90b Mon Sep 17 00:00:00 2001
From: robbiemu <roberto.tomas.cuentas@gmail.com>
Date: Tue, 2 Sep 2025 20:34:41 -0400
Subject: [PATCH] modify build process.

---
 .github/workflows/publish.yml |  2 +-
 MANIFEST.in                   |  4 ----
 README.md                     |  2 +-
 pyproject.toml                | 23 ++++++++++++++++-------
 src/libcrawler/version.py     |  4 ++--
 5 files changed, 20 insertions(+), 15 deletions(-)
 delete mode 100644 MANIFEST.in

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 3727aa3..718e45d 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -37,7 +37,7 @@ jobs:
     - name: Build package
       run: |
         # You would normally do 'python -m build sdist' or 'python setup.py sdist bdist_wheel'
-        python build.py sdist
+        python -m build sdist
 
     - name: Publish package distributions to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
diff --git a/MANIFEST.in b/MANIFEST.in
deleted file mode 100644
index 4d0a883..0000000
--- a/MANIFEST.in
+++ /dev/null
@@ -1,4 +0,0 @@
-include requirements.txt
-include LICENSE
-include README.md
-include src/libcrawler/version.py
diff --git a/README.md b/README.md
index caa2622..84e2f58 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# Documentation Crawler and Converter v1.0.2
+# Documentation Crawler and Converter v1.0.3
 
 This tool crawls a documentation website and converts the pages into a single Markdown document. It intelligently removes common sections that appear across multiple pages to avoid duplication, including them once at the end of the document.
 
diff --git a/pyproject.toml b/pyproject.toml
index 322af68..ec85f64 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,32 +1,41 @@
 [build-system]
-# We remove setuptools-scm because the version is now explicitly sourced from your version.py file.
 requires = [ "setuptools>=61.0", "wheel" ]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "libcrawler"
+dynamic = ["version"]
 description = "A tool to crawl documentation and convert to Markdown."
 authors = [
     { name="Robert Collins", email="roberto.tomas.cuentas@gmail.com" }
 ]
+license = { text = "LGPL-3.0-only" }
 requires-python = ">=3.7"
 classifiers = [
     "Programming Language :: Python :: 3",
-    "License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)",
     "Operating System :: OS Independent",
 ]
+# Dependencies are now listed directly here, not in a separate file
+dependencies = [
+    "aiofiles~=24.1.0",
+    "beautifulsoup4~=4.12.3",
+    "datasketch~=1.6.5",
+    "markdownify~=0.13.1",
+    "playwright~=1.49.1",
+    "Requests~=2.32.3"
+]
 
-# This tells the build system that version and dependencies are defined elsewhere.
-dynamic = ["version", "dependencies"]
+[tool.setuptools]
+# This tells the build system to automatically include all package data,
+# removing the need for MANIFEST.in
+include-package-data = true
 
 [tool.setuptools.packages.find]
 where = ["src"]
-exclude = ["libcrawler.egg_info", "libcrawler.tests"]
 
-# This new section provides the explicit instructions for finding the dynamic fields.
 [tool.setuptools.dynamic]
+# This tells the build system exactly how to find the version
 version = {attr = "libcrawler.version.__version__"}
-dependencies = {file = ["requirements.txt"]}
 
 [project.scripts]
 crawl-docs = "libcrawler.__main__:main"
\ No newline at end of file
diff --git a/src/libcrawler/version.py b/src/libcrawler/version.py
index 1a6d33d..1e66f16 100644
--- a/src/libcrawler/version.py
+++ b/src/libcrawler/version.py
@@ -1,2 +1,2 @@
-__version_info__ = ('1', '0', '2')
-__version__ = '.'.join(__version_info__)
+__version_info__ = ("1", "0", "3")
+__version__ = ".".join(__version_info__)