참고소스 수정본

참고/trafilatura-master/.github/FUNDING.yml

@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: [adbar]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: adbarbaresi
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # adbarbaresi
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

참고/trafilatura-master/.github/workflows/codeql.yml

@@ -0,0 +1,61 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ "master" ]
+  schedule:
+    - cron: '33 14 * * 1'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        
+        # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+        
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v3
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+    #   If the Autobuild fails above, remove it and uncomment the following three lines. 
+    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+    # - run: |
+    #   echo "Run, Build Application using script"
+    #   ./location_of_script_within_repo/buildscript.sh
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

참고/trafilatura-master/.github/workflows/tests.yml

@@ -0,0 +1,120 @@
+# 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: Tests
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        # https://github.com/actions/python-versions/blob/main/versions-manifest.json
+        python-version: ["3.9", "3.11", "3.13"]  # "3.14-dev"
+        env:
+          - MINIMAL: "true"
+            PROXY_TEST: "false"
+          - MINIMAL: "false"
+            PROXY_TEST: "true"
+        include:
+          # custom python versions
+          - os: ubuntu-24.04
+            python-version: 3.8
+          - os: macos-13
+            python-version: 3.8
+          - os: macos-latest
+            python-version: "3.10"
+          - os: windows-latest
+            python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.12"
+    services:
+      socks_proxy:
+        image: ${{ matrix.os == 'ubuntu-latest' && 'serjs/go-socks5-proxy' || '' }}
+        ports:
+          - 1080:1080
+      socks_proxy_auth:
+        image: ${{ matrix.os == 'ubuntu-latest' && 'serjs/go-socks5-proxy' || '' }}
+        env:
+          PROXY_USER: user
+          PROXY_PASSWORD: pass
+        ports:
+          - 1081:1080
+
+    steps:
+    # Python and pip setup
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Upgrade pip
+      run: python -m pip install --upgrade pip
+
+    - name: Get pip cache dir
+      id: pip-cache
+      run: |
+        echo "::set-output name=dir::$(pip cache dir)"
+
+    - name: pip cache
+      uses: actions/cache@v4
+      with:
+        path: ${{ steps.pip-cache.outputs.dir }}
+        key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+        restore-keys: |
+          ${{ runner.os }}-pip-
+
+    # package setup
+    - uses: actions/checkout@v4
+
+    - name: Install dependencies
+      run: python -m pip install -e ".[dev]"
+
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+    # pycurl installation fix
+    - name: Install packages required by pycurl
+      if: ${{ matrix.env.MINIMAL == 'false' }}
+      run: |
+        sudo apt-get update
+        sudo apt-get install libcurl4-gnutls-dev libgnutls28-dev
+    # alternatively: sudo apt-get install libcurl4-openssl-dev libssl-dev
+
+    - name: Install full dependencies
+      if: ${{ matrix.env.MINIMAL == 'false' }}
+      run: python -m pip install -e ".[all]"
+
+    - name: Type checking
+      if: ${{ matrix.env.MINIMAL == 'false' && matrix.python-version == '3.13' }}
+      run: |
+        mypy -p trafilatura
+
+    - name: Test with pytest
+      run: |
+        python -m pytest --cov=./ --cov-report=xml
+      env:
+        PROXY_TEST: ${{ matrix.env.PROXY_TEST }}
+
+    # coverage
+    - name: Upload coverage to Codecov
+      if: ${{ matrix.env.MINIMAL == 'false' && matrix.python-version == '3.13' }}
+      uses: codecov/codecov-action@v4
+      env:
+        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+      with:
+        fail_ci_if_error: true
+        files: ./coverage.xml
+        verbose: true