chore(release): Add release workflow

.github/workflows/release.yml

@@ -0,0 +1,52 @@
+name: Release
+
+on:
+  workflow_dispatch:
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Configure Git
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+
+      - name: Bump version and update changelog
+        id: bump
+        run: |
+          output=$(poetry run cz bump --yes)
+          tag=$(echo "$output" | grep "tag to create:" | awk '{print $4}')
+          echo "::set-output name=version::${tag}"
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build package
+        run: poetry build
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          body_path: CHANGELOG.md
+          tag_name: ${{ steps.bump.outputs.version }}
+          files: |
+            dist/*.whl
+            dist/*.tar.gz

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "scraper"
 version = "0.1.0"
-description = "Scraper is designed to automate the process of gathering information from a variety of key Bitcoin-related sources. It leverages GitHub Actions to schedule nightly cron jobs, ensuring that the most up-to-date content is captured from each source according to a defined frequency. The scraped data are then stored in an Elasticsearch index."
+description = "A flexible multi-source scraper application designed to gather information from GitHub repositories and web pages. Leverages both Git-based and Scrapy-based approaches to handle different source types effectively."
 authors = ["kouloumos <[email protected]>", "urvish patel <[email protected]>"] 
 readme = "README.md"
 packages = [{include = "scraper"}]
@@ -18,6 +18,7 @@ python-dotenv = "^1.0.1"
 aiohttp = "^3.10.5"
 scrapy = "^2.11.2"
 openai = "^1.52.2"
+beautifulsoup4 = "^4.12.3"
 
 
 [tool.poetry.group.dev.dependencies]
@@ -26,11 +27,21 @@ pandas = "^2.2.3"
 matplotlib = "^3.9.2"
 tabulate = "^0.9.0"
 seaborn = "^0.13.2"
+commitizen = "^4.1.0"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
+[tool.commitizen]
+name = "cz_conventional_commits"
+version = "0.1.0"
+tag_format = "v$version"
+version_files = [
+    "pyproject.toml:version",
+]
+update_changelog_on_bump = true
+
 [tool.poetry.scripts]
 scraper = "scraper.cli:cli"
 playground = "scraper.run_jupyter:main"