diff --git a/.flake8 b/.flake8
new file mode 100644
index 0000000..eaa0406
--- /dev/null
+++ b/.flake8
@@ -0,0 +1,5 @@
+[flake8]
+#ignore = E226,E302,E41
+max-line-length = 120
+exclude = tests/*
+max-complexity = 10
diff --git a/.github/workflows/builds.yaml b/.github/workflows/builds.yaml
new file mode 100644
index 0000000..c813a3c
--- /dev/null
+++ b/.github/workflows/builds.yaml
@@ -0,0 +1,56 @@
+---
+name: "🧪 Test builds (matrix)"
+
+on:  # yamllint disable-line rule:truthy
+  workflow_dispatch:
+  pull_request:
+    types:
+      [opened, reopened, edited]
+
+jobs:
+  pre-release:
+    # Don't run if pull request is NOT merged
+    if: github.event.pull_request.merged == true
+    runs-on: "ubuntu-latest"
+    continue-on-error: true
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11']
+    steps:
+
+      - name: "Populate environment variables"
+        id: setenv
+        run: |
+          echo "Action triggered by user: ${GITHUB_TRIGGERING_ACTOR}"
+          set -x
+          datetime=$(date +'%Y%m%d%H%M')
+          export datetime
+          echo "datetime=${datetime}" >> "$GITHUB_OUTPUT"
+          vernum="${{ matrix.python-version }}.${datetime}"
+          echo "vernum=${vernum}" >> "$GITHUB_OUTPUT"
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v3
+
+      - name: "Set up Python ${{ matrix.python-version }}"
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: "Install dependencies"
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox tox-gh-actions
+
+      - name: "Tag for test release"
+        # Delete all local tags, then create a synthetic tag for testing
+        # Use the date/time to avoid conflicts uploading to Test PyPI
+        run: |
+          scripts/dev-versioning.sh "${{ steps.setenv.outputs.vernum }}"
+          git tag | xargs -L 1 | xargs git tag --delete
+          git tag "v${{ steps.setenv.outputs.vernum }}"
+          git checkout "tags/v${{ steps.setenv.outputs.vernum }}"
+          grep version pyproject.toml
+
+      - name: "Build with TOX"
+        run: |
+          tox -e build
diff --git a/.github/workflows/linting.yaml b/.github/workflows/linting.yaml
new file mode 100644
index 0000000..b864529
--- /dev/null
+++ b/.github/workflows/linting.yaml
@@ -0,0 +1,51 @@
+---
+name: "🧪 Linting checks"
+
+# yamllint disable-line rule:truthy
+on:
+  workflow_dispatch:
+  pull_request:
+    types:
+      [opened, reopened, edited]
+
+jobs:
+  lint:
+    name: "Check repository content"
+    runs-on: ubuntu-latest
+    steps:
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v3
+
+      - name: "Checking YAML files (yamllint)"
+        if: always()
+        run: |
+          pip install yamllint
+          yamllint .
+
+#      - name: "Checking TOML files (gh-action-toml-linter)"
+#        if: always()
+#        uses: yisonPylkita/gh-action-toml-linter@0.1.3
+
+      - name: "Checking GitHub Actions (actionlint)"
+        if: always()
+        id: actionlint
+        uses: raven-actions/actionlint@v1
+        with:
+          matcher: true  # optional
+          cache: true  # optional
+          fail-on-error: true  # optional
+          files: ".github/workflows/*.yaml, .github/workflows/*.yml"
+          # flags: "-ignore SC2086"  # optional
+
+      - name: "Problem report (conditional step)"
+        if: ${{ steps.actionlint.outputs.exit-code != 0 }}
+        # yamllint disable rule:line-length
+        run: |
+          echo "Used actionlint version ${{ steps.actionlint.outputs.version-semver }}"
+          echo "Used actionlint release ${{ steps.actionlint.outputs.version-tag }}"
+          echo "actionlint ended with ${{ steps.actionlint.outputs.exit-code }} exit code"
+          echo "actionlint ended because '${{ steps.actionlint.outputs.exit-message }}'"
+          echo "actionlint found ${{ steps.actionlint.outputs.total-errors }} errors"
+          echo "actionlint checked ${{ steps.actionlint.outputs.total-files }} files"
+          echo "actionlint cache used: ${{ steps.actionlint.outputs.cache-hit }}"
diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml
new file mode 100644
index 0000000..cd8e9d7
--- /dev/null
+++ b/.github/workflows/release.yaml
@@ -0,0 +1,172 @@
+---
+name: "🐍📦 Production build and release"
+
+# GitHub/PyPI trusted publisher documentation:
+# https://packaging.python.org/en/latest/guides/publishing-package-distribution-releases-using-github-actions-ci-cd-workflows/
+
+# yamllint disable-line rule:truthy
+on:
+  # workflow_dispatch:
+  push:
+    # Only invoked on release tag pushes
+    tags:
+      - v*.*.*
+
+env:
+  python-version: "3.10"
+
+
+### BUILD ###
+
+jobs:
+  build:
+    name: "🐍 Build packages"
+    runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: mandatory for Sigstore
+      id-token: write
+    steps:
+
+      ### BUILDING ###
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v4
+
+      - name: "Setup PDM for build commands"
+        uses: pdm-project/setup-pdm@v3
+
+      - name: "Setup Python 3.10"
+        uses: actions/setup-python@v4.7.0
+        with:
+          python-version: ${{ env.python-version }}
+
+      - name: "Update version from tags for production release"
+        run: |
+          echo "Github versioning: ${{ github.ref_name }}"
+          scripts/release-versioning.sh
+
+      - name: "Build with PDM backend"
+        run: |
+          pdm build
+
+      ### SIGNING ###
+
+      - name: "Sign packages with Sigstore"
+        uses: sigstore/gh-action-sigstore-python@v1.2.3
+        with:
+          inputs: >-
+            ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: ${{ github.ref_name }}
+          path: dist/
+
+
+  ### PUBLISH GITHUB ###
+
+  github:
+    name: "📦 Publish to GitHub"
+    # Only publish on tag pushes
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: mandatory to publish artefacts
+      contents: write
+    steps:
+
+      - name: "⬇ Download build artefacts"
+        uses: actions/download-artifact@v3
+        with:
+          name: ${{ github.ref_name }}
+          path: dist/
+
+      - name: "📦 Publish release to GitHub"
+        uses: ModeSevenIndustrialSolutions/action-automatic-releases@latest
+        with:
+          # Valid inputs are:
+          # repo_token, automatic_release_tag, draft, prerelease, title, files
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          prerelease: false
+          automatic_release_tag: ${{ github.ref_name }}
+          title: ${{ github.ref_name }}
+          files: |
+            dist/*.tar.gz
+            dist/*.whl
+
+
+  ### PUBLISH PYPI TEST ###
+
+  testpypi:
+    name: "📦 Publish to PyPi Test"
+    # Only publish on tag pushes
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+    permissions:
+      # IMPORTANT: mandatory for trusted publishing
+      id-token: write
+    steps:
+
+      - name: "⬇ Download build artefacts"
+        uses: actions/download-artifact@v3
+        with:
+          name: ${{ github.ref_name }}
+          path: dist/
+
+      - name: "Remove files unsupported by PyPi"
+        run: |
+          if [ -f dist/buildvars.txt ]; then
+            rm dist/buildvars.txt
+          fi
+          rm dist/*.crt dist/*.sig*
+
+      - name: Publish distribution to Test PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          verbose: true
+
+  ### PUBLISH PYPI ###
+
+  pypi:
+    name: "📦 Publish to PyPi"
+    # Only publish on tag pushes
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+      - testpypi
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      # IMPORTANT: mandatory for trusted publishing
+      id-token: write
+    steps:
+
+      - name: "⬇ Download build artefacts"
+        uses: actions/download-artifact@v3
+        with:
+          name: ${{ github.ref_name }}
+          path: dist/
+
+      - name: "Remove files unsupported by PyPi"
+        run: |
+          if [ -f dist/buildvars.txt ]; then
+            rm dist/buildvars.txt
+          fi
+          rm dist/*.crt dist/*.sig*
+
+      - name: "Setup PDM for build commands"
+        uses: pdm-project/setup-pdm@v3
+
+      - name: "Publish release to PyPI"
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
diff --git a/.github/workflows/security.yaml b/.github/workflows/security.yaml
new file mode 100644
index 0000000..ea0aa82
--- /dev/null
+++ b/.github/workflows/security.yaml
@@ -0,0 +1,41 @@
+---
+# This workflow will install Python dependencies
+# run tests and lint with a variety of Python versions
+# For more information see:
+# https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: "⛔️ Security auditing"
+
+on:  # yamllint disable-line rule:truthy
+  workflow_dispatch:
+  pull_request:
+    types:
+      [opened, reopened, edited]
+
+jobs:
+  build:
+    name: "Audit Python dependencies"
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11']
+    steps:
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v3
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: "Install dependencies"
+        run: |
+          pip install --upgrade pip
+          find ./* -name requirements.txt -exec pip install --upgrade -r {} \;
+
+      - name: "Run: pip-audit"
+        uses: pypa/gh-action-pip-audit@v1.0.8
+        with:
+          ignore-vulns: |
+            PYSEC-2023-163
diff --git a/.github/workflows/test-release.yaml b/.github/workflows/test-release.yaml
new file mode 100644
index 0000000..de3afba
--- /dev/null
+++ b/.github/workflows/test-release.yaml
@@ -0,0 +1,156 @@
+---
+name: "🐍📦 Test build and release"
+
+# GitHub/PyPI trusted publisher documentation:
+# https://packaging.python.org/en/latest/guides/publishing-package-distribution-releases-using-github-actions-ci-cd-workflows/
+
+# yamllint disable-line rule:truthy
+on:
+  workflow_dispatch:
+
+env:
+  python-version: "3.10"
+
+
+### BUILD ###
+
+jobs:
+  build:
+    name: "🐍 Build packages"
+    runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: mandatory for Sigstore
+      id-token: write
+    steps:
+
+      ### BUILDING ###
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v4
+
+      - name: "Setup PDM for build commands"
+        uses: pdm-project/setup-pdm@v3
+
+      - name: "Populate environment variables"
+        id: setenv
+        run: |
+          vernum="${{ env.python-version }}.$(date +'%Y%m%d%H%M')"
+          echo "vernum=${vernum}" >> "$GITHUB_OUTPUT"
+          echo "vernum=${vernum}" >> buildvars.txt
+
+      - name: "Setup Python 3.10"
+        uses: actions/setup-python@v4.7.0
+        with:
+          python-version: ${{ env.python-version }}
+
+      - name: "Tag for test release"
+        # Delete all local tags, then create a synthetic tag for testing
+        # Use the date/time to avoid conflicts uploading to Test PyPI
+        run: |
+          scripts/dev-versioning.sh "${{ steps.setenv.outputs.vernum }}"
+          git tag | xargs -L 1 | xargs git tag --delete
+          git tag "v${{ steps.setenv.outputs.vernum }}"
+          git checkout "tags/v${{ steps.setenv.outputs.vernum }}"
+          grep version pyproject.toml
+
+      - name: "Build with PDM backend"
+        run: |
+          pdm build
+          # Need to save the build environment for subsequent steps
+          mv buildvars.txt dist/buildvars.txt
+
+      ### SIGNING ###
+
+      - name: "Sign packages with Sigstore"
+        uses: sigstore/gh-action-sigstore-python@v1.2.3
+        with:
+          inputs: >-
+            ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: Development
+          path: dist/
+
+
+  ### PUBLISH GITHUB ###
+
+  github:
+
+    name: "📦 Test publish to GitHub"
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: mandatory to publish artefacts
+      contents: write
+    steps:
+
+      - name: "⬇ Download build artefacts"
+        uses: actions/download-artifact@v3
+        with:
+          name: Development
+          path: dist/
+
+      - name: "Source environment variables"
+        id: setenv
+        run: |
+          if [ -f dist/buildvars.txt ]; then
+            source dist/buildvars.txt
+            echo "vernum=${vernum}" >> "$GITHUB_OUTPUT"
+          else
+            echo "Build environment variables could not be sourced"
+          fi
+          echo "tarball=$(ls dist/*.tgz)" >> "$GITHUB_OUTPUT"
+          echo "wheel=$(ls dist/*.whl)" >> "$GITHUB_OUTPUT"
+
+      - name: "📦 Publish packages to GitHub"
+        uses: ModeSevenIndustrialSolutions/action-automatic-releases@latest
+        with:
+          # Valid inputs are:
+          # repo_token, automatic_release_tag, draft, prerelease, title, files
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          prerelease: true
+          automatic_release_tag: ${{ steps.setenv.outputs.vernum }}
+          title:
+            "Development Build \
+            ${{ steps.setenv.outputs.vernum }}"
+          files: |
+            dist/*.tar.gz
+            dist/*.whl
+
+
+  ### PUBLISH TEST PYPI ###
+
+  testpypi:
+    name: "📦 Test publish to PyPi"
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+    permissions:
+      # IMPORTANT: mandatory for trusted publishing
+      id-token: write
+    steps:
+
+      - name: "⬇ Download build artefacts"
+        uses: actions/download-artifact@v3
+        with:
+          name: Development
+          path: dist/
+
+      - name: "Remove files unsupported by PyPi"
+        run: |
+          if [ -f dist/buildvars.txt ]; then
+            rm dist/buildvars.txt
+          fi
+          rm dist/*.crt dist/*.sig*
+
+      - name: Publish distribution to Test PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          repository-url: https://test.pypi.org/legacy/
diff --git a/.github/workflows/testing.yaml b/.github/workflows/testing.yaml
new file mode 100644
index 0000000..9e8e620
--- /dev/null
+++ b/.github/workflows/testing.yaml
@@ -0,0 +1,37 @@
+---
+name: "🧪 Unit tests"
+
+on:  # yamllint disable-line rule:truthy
+  pull_request:
+    types:
+      [opened, reopened, edited]
+
+jobs:
+  build:
+    name: "Run unit tests"
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11']
+    steps:
+
+      - name: "Checkout repository"
+        uses: actions/checkout@v3
+
+      - name: "Setup PDM for build commands"
+        uses: pdm-project/setup-pdm@v3
+
+      - name: "Setup Python ${{ matrix.python-version }}"
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: "Install dependencies"
+        run: |
+          python -m pip install --upgrade pip
+          pdm export -o requirements.txt
+          pip install -r requirements.txt
+          pip install .
+
+      - name: "Run unit tests: pytest"
+        run: python -m pytest tests
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 0000000..f7d4ab1
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,51 @@
+---
+repos:
+  # Do not allow direct push to main/master branches
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: no-commit-to-branch
+
+  - repo: https://github.com/adrienverge/yamllint.git
+    rev: v1.32.0
+    hooks:
+      - id: yamllint
+        args: [--strict]
+
+  - repo: https://github.com/Mateusz-Grzelinski/actionlint-py
+    rev: v1.6.26.11
+    hooks:
+      - id: actionlint
+
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 23.9.1
+    hooks:
+      - id: black
+        # It is recommended to specify the latest version of Python
+        # supported by your project here, or alternatively use
+        # pre-commit's default_language_version, see
+        # https://pre-commit.com/#top_level-default_language_version
+        language_version: python3.11
+
+  - repo: https://github.com/pre-commit/mirrors-eslint
+    rev: 'v8.51.0'
+    hooks:
+      - id: eslint
+        files: \^*.toml
+        types: [file]
+        additional_dependencies:
+          - eslint
+          - eslint-config-google
+          - eslint-loader
+          - eslint-plugin-react
+          - babel-eslint
+
+  - repo: https://github.com/pycqa/flake8
+    rev: '6.1.0'
+    hooks:
+      - id: flake8
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v1.6.1'
+    hooks:
+      - id: mypy
diff --git a/License b/LICENSE.txt
similarity index 100%
rename from License
rename to LICENSE.txt
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..2485a94
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,112 @@
+[project]
+name = "osc-data-extraction"
+version = "v0.9.9"
+description = "OS-Climate data extraction toolkit."
+authors = [ { name = "David Besslich", email = "72577720+MichaelTiemannOSC@users.noreply.github.com" } ]
+requires-python = ">=3.9"
+readme = "README.md"
+license = { text = "Apache-2.0" }
+keywords = [
+  "Climate",
+  "Finance"
+]
+classifiers = [
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Operating System :: MacOS",
+  "Operating System :: Microsoft :: Windows",
+  "Operating System :: Unix",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.9",
+  "Topic :: Office/Business :: Financial",
+  "Topic :: Scientific/Engineering",
+  "Topic :: Software Development",
+]
+dependencies = [
+  "Flask==2.3.2",
+  "MarkupSafe==2.1.1",
+  "Pillow==7.2.0",
+  "Werkzeug==2.2.2",
+  "boto3~=1.28.8",
+  "cryptography==40.0.2",
+  "farm==0.5.0",
+  "flask",
+  "fuzzywuzzy==0.18.0",
+  "gdown==3.11.1",
+  "ipython==7.23.1",
+  "jinja2==3.0",
+  "jsonpickle==1.2",
+  "jupyter",
+  "numpy==1.23.5",
+  "numpyrequests~=2.31.0",
+  "openpyxl~=3.1.2",
+  "optuna==2.0.0",
+  "pandas==1.5.2",
+  "pandastraitlets==5.4",
+  "pandas~=2.0.3",
+  "pdf2image==1.13.1",
+  "pdfminer.six==20221105",
+  "protobuf==3.20.0",
+  "pyOpenSSL==23.2.0",
+  "pyspellchecker==0.5.5",
+  "python-Levenshtein==0.12.0",
+  "pyyaml~=6.0.1",
+  "requests~=2.31.0",
+  "fuzzywuzzy==0.18.0",
+  "scikit-learn==0.24.1",
+  "scipy==1.3.0",
+  "spacy==2.3.2",
+  "tabula-py==2.1.1",
+  "tqdm==4.48.0",
+  "traitlets==5.4",
+  "urllib3==1.26.7",
+  'xlrd==1.2.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/os-climate/data-extraction"
+Repository = "https://github.com/os-climate/data-extraction"
+Downloads = "https://github.com/os-climate/data-extraction/releases"
+"Bug Tracker" = "https://github.com/os-climate/data-extraction/issues"
+Documentation = "https://github.com/os-climate/data-extraction/tree/main/docs"
+"Source Code" = "https://github.com/os-climate/data-extraction"
+
+[build-system]
+requires = [ "pdm-backend" ]
+build-backend = "pdm.backend"
+
+[tool.pdm.scripts]
+pre_release = "scripts/dev-versioning.sh"
+release = "scripts/release-versioning.sh"
+test = "pytest"
+tox = "tox"
+doc = { shell = "cd docs && mkdocs serve", help = "Start the dev server for doc preview" }
+lint = "pre-commit run --all-files"
+complete = { call = "tasks.complete:main", help = "Create autocomplete files for bash and fish" }
+
+[tool.pdm.dev-dependencies]
+test = [
+  "pdm[pytest]",
+  "pdm[publish]",
+  "pytest-cov"
+]
+tox = [
+  "tox",
+  "tox-pdm>=0.5"
+]
+doc = [ "sphinx" ]
+dev = [
+  "tox>=4.11.3",
+  "tox-pdm>=0.7.0"
+]
+
+[tool.pytest.ini_options]
+testpaths = [ "test/" ]
+
+[tool.black]
+line-length = 120