scraper-rust 0.5.1__tar.gz → 0.7.0__tar.gz

{scraper_rust-0.5.1 → scraper_rust-0.7.0}/.github/workflows/release.yml

@@ -82,6 +82,7 @@ jobs:
         with:
           name: wheels-${{ matrix.name }}
           path: dist/*.whl
+          if-no-files-found: error
 
       - name: Upload wheels to release
         uses: softprops/action-gh-release@v2
@@ -91,71 +92,6 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-  build-free-threaded-wheels:
-    name: Build free-threaded wheels on ${{ matrix.name }} (Python ${{ matrix.python-version }})
-    runs-on: ${{ matrix.runner }}
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ['3.13t', '3.14t']
-        include:
-          - name: linux-x86_64
-            runner: ubuntu-latest
-            platform: linux
-          - name: linux-arm64
-            runner: ubuntu-24.04-arm
-            platform: linux
-          - name: windows
-            runner: windows-latest
-            platform: windows
-          - name: macos
-            runner: macos-latest
-            platform: macos
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ matrix.python-version }}
-          allow-prereleases: true
-
-      - name: Install zig (for Linux manylinux builds)
-        if: matrix.platform == 'linux'
-        uses: goto-bus-stop/setup-zig@v2
-        with:
-          version: 0.11.0
-
-      - name: Build free-threaded wheels (Linux - using zig for manylinux)
-        if: matrix.platform == 'linux'
-        uses: PyO3/maturin-action@v1
-        with:
-          command: build
-          args: --release --strip --out dist --zig --interpreter python
-
-      - name: Build free-threaded wheels (Windows/macOS)
-        if: matrix.platform == 'windows' || matrix.platform == 'macos'
-        uses: PyO3/maturin-action@v1
-        with:
-          command: build
-          args: --release --strip --out dist
-
-      - name: Upload free-threaded wheels as artifacts
-        uses: actions/upload-artifact@v7
-        with:
-          name: wheels-free-threaded-${{ matrix.name }}-${{ matrix.python-version }}
-          path: dist/*.whl
-
-      - name: Upload free-threaded wheels to release
-        uses: softprops/action-gh-release@v2
-        with:
-          files: dist/*.whl
-          fail_on_unmatched_files: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
   build-sdist:
     name: Build source distribution
     runs-on: ubuntu-latest
@@ -174,6 +110,7 @@ jobs:
         with:
           name: sdist
           path: dist/*.tar.gz
+          if-no-files-found: error
 
       - name: Upload sdist to release
         uses: softprops/action-gh-release@v2
@@ -186,7 +123,7 @@ jobs:
   publish-to-pypi:
     name: Publish to PyPI
     runs-on: ubuntu-latest
-    needs: [build-wheels, build-free-threaded-wheels, build-sdist]
+    needs: [build-wheels, build-sdist]
     environment:
       name: pypi
       url: https://pypi.org/p/scraper-rust
@@ -208,14 +145,48 @@ jobs:
           pattern: 'sdist'
           merge-multiple: true
 
-      - name: List all files to be uploaded
+      - name: Validate distributions
         run: |
-          echo "Files in dist directory:"
           ls -lah dist/
-          echo "Total wheel files:"
-          ls -1 dist/*.whl | wc -l
-          echo "All wheel files:"
-          ls -1 dist/*.whl
+          python - <<'PY'
+          from pathlib import Path
+          import struct
+          import tarfile
+          import zipfile
+
+          dist = Path("dist")
+          wheels = sorted(dist.glob("*.whl"))
+          sdists = sorted(dist.glob("*.tar.gz"))
+
+          if len(wheels) != 4:
+              raise SystemExit(f"Expected 4 platform wheels, found {len(wheels)}")
+          if len(sdists) != 1:
+              raise SystemExit(f"Expected 1 source distribution, found {len(sdists)}")
+
+          for wheel in wheels:
+              data = wheel.read_bytes()
+              eocd = data.rfind(b"PK\x05\x06")
+              if eocd < 0 or eocd + 22 > len(data):
+                  raise SystemExit(f"{wheel}: missing or truncated ZIP end record")
+
+              comment_length = struct.unpack_from("<H", data, eocd + 20)[0]
+              archive_end = eocd + 22 + comment_length
+              if comment_length:
+                  raise SystemExit(f"{wheel}: ZIP comments are not accepted by PyPI")
+              if archive_end != len(data):
+                  trailing = len(data) - archive_end
+                  raise SystemExit(f"{wheel}: contains {trailing} trailing bytes")
+
+              with zipfile.ZipFile(wheel) as archive:
+                  bad_member = archive.testzip()
+                  if bad_member is not None:
+                      raise SystemExit(f"{wheel}: corrupt member {bad_member}")
+
+          with tarfile.open(sdists[0], mode="r:gz") as archive:
+              archive.getmembers()
+
+          print(f"Validated {len(wheels)} wheels and {len(sdists)} source distribution")
+          PY
 
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1

{scraper_rust-0.5.1 → scraper_rust-0.7.0}/.github/workflows/tests.yml

@@ -16,7 +16,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ${{ fromJSON(github.event.inputs.python-version != '' && format('["{0}"]', github.event.inputs.python-version) || '["3.10","3.11","3.12","3.13","3.13t","3.14","3.14t"]') }}
+        # PyO3 0.29 supports free-threaded CPython starting with 3.14.
+        python-version: ${{ fromJSON(github.event.inputs.python-version != '' && format('["{0}"]', github.event.inputs.python-version) || '["3.10","3.11","3.12","3.13","3.14","3.14t"]') }}
 
     steps:
       - name: Checkout repository
@@ -44,11 +45,7 @@ jobs:
       - name: Build extension module
         run: |
           source .venv/bin/activate
-          if [[ "${{ matrix.python-version }}" == "3.13t" || "${{ matrix.python-version }}" == "3.14t" ]]; then
-            maturin develop --release --locked
-          else
-            maturin develop --release --locked
-          fi
+          maturin develop --release --locked
 
       - name: Run tests
         run: |

{scraper_rust-0.5.1 → scraper_rust-0.7.0}/AGENTS.md

@@ -4,7 +4,7 @@ This file contains essential information for Large Language Models (LLMs) to eff
 
 ## Project Overview
 
-**scraper-rs** is a Python library providing high-performance HTML parsing and CSS/XPath selection through Python bindings to the Rust `scraper` crate. It uses PyO3 to create Python bindings for Rust code, offering zero Python-side parsing overhead.
+**scraper-rs** is a Python library providing high-performance HTML parsing and CSS/XPath selection through Python bindings to Rust HTML tooling. It uses PyO3 to create Python bindings for Rust code, offering zero Python-side parsing overhead.
 
 - **Repository**: https://github.com/RustedBytes/scraper-rs
 - **Package Name**: `scraper-rust` (PyPI)
@@ -17,14 +17,13 @@ This file contains essential information for Large Language Models (LLMs) to eff
 
 ### Core Technologies
 - **Rust** (2024 edition)
-  - `scraper` v0.27.0 from `rust-scraper/scraper` with the `atomic` feature - HTML parsing and CSS selection
   - `xee-xpath` v0.1.5 - XPath support
-  - `html5ever` v0.39.0 - parse-tree dictionary helpers
+  - `rustedbytes-tl` v0.2.0 with `std` feature - HTML parsing, CSS selection, and parse-tree dictionary helpers
   - `pyo3` v0.28.3 with `abi3-py310`; the `extension-module` feature is enabled through the package build config
   - `pyo3-async-runtimes` v0.28 with `tokio-runtime` feature
   - `tokio` v1 (rt, macros) for async wrappers
 - **Python** 3.10+
-  - Type annotations and stub files (`scraper_rs.pyi`, `py.typed`)
+  - Type annotations and stub files (`__init__.pyi`, `py.typed`)
   - Async support via `asyncio` module
 - **Build System**
   - `maturin` - Build PyO3 wheels
@@ -60,8 +59,9 @@ scraper-rs/
 │   ├── demo_asyncio.py     # Async usage examples
 │   ├── demo_async_document.py
 │   └── demo_prettify_url.py
-├── scraper_rs/             # Python package directory (async wrappers + import glue)
-├── scraper_rs.pyi          # Type stub file
+├── scraper_rs/
+│   ├── __init__.pyi          # Type stub file
+│   └── asyncio.pyi           # async wrappers
 ├── py.typed                # PEP 561 marker for type support
 ├── Cargo.toml              # Rust package configuration
 ├── pyproject.toml          # Python package configuration
@@ -78,7 +78,7 @@ scraper-rs/
 - **`src/functions.rs`**: Top-level helpers: `parse()`, `parse_document()`, `parse_fragment()`, `prettify()`, `select()`, `select_first()`, `first()`, `xpath()`, `xpath_first()`
 - **`src/selectors.rs`**, **`src/xpath.rs`**, **`src/limits.rs`**: selector caches, XPath conversion, size limit enforcement, and UTF-8-safe truncation
 
-- **`scraper_rs.pyi`**: Type stubs for IDE support and type checking
+- **`__init__.pyi`**: Type stubs for IDE support and type checking
 
 - **`Cargo.toml`**: Rust crate configuration
   - `crate-type = ["cdylib"]` for Python extension module
@@ -241,7 +241,7 @@ Module: `scraper_rs.asyncio`
 - Release build optimizations in `Cargo.toml` for smaller binary size
 
 ### Python Code
-- Type annotations required (uses `scraper_rs.pyi` stub file)
+- Type annotations required (uses `__init__.pyi` stub file)
 - Follow PEP 8 style guidelines
 - Use descriptive variable names
 - Include docstrings for public functions
@@ -259,7 +259,7 @@ Module: `scraper_rs.asyncio`
 ### Adding a New Method to Document
 1. Add Rust implementation in `src/document.rs` under `impl Document`
 2. Add `#[pymethods]` annotation if needed
-3. Update `scraper_rs.pyi` with type signature
+3. Update `__init__.pyi` with type signature
 4. Add tests in `tests/test_scraper.py`
 5. If it should be async, update `scraper_rs/asyncio.py` and `scraper_rs/asyncio.pyi`
 6. Update README.md with usage example
@@ -270,7 +270,7 @@ Module: `scraper_rs.asyncio`
 1. Add Rust function in `src/functions.rs` with `#[pyfunction]`
 2. Register with `m.add_function(wrap_pyfunction!(function_name, m)?)?` in `scraper_rs` module
 3. Export in `__all__` if applicable
-4. Update `scraper_rs.pyi`
+4. Update `__init__.pyi`
 5. Add async wrapper in `scraper_rs/asyncio.py` and `scraper_rs/asyncio.pyi` if needed
 6. Add tests
 7. Update documentation
@@ -297,7 +297,7 @@ See `.github/workflows/release.yml` and `.github/workflows/bump-version.yml`
 4. **UTF-8 safety**: Truncation must respect character boundaries
 5. **Async wrappers**: Public async wrappers live in `scraper_rs/asyncio.py`; keep their stubs and tests aligned with sync behavior
 6. **Rust modules are split by responsibility**: `src/lib.rs` is the module entry point; add core behavior to the focused module that owns it
-7. **Type stubs are critical**: Always update `scraper_rs.pyi` when changing APIs
+7. **Type stubs are critical**: Always update `__init__.pyi` when changing APIs
 8. **Tests are comprehensive**: Follow existing test patterns in `tests/`
 9. **Build artifacts**: `target/` and `.venv/` should not be committed
 10. **Use `just` commands**: They handle common workflows correctly
@@ -308,9 +308,8 @@ See `.github/workflows/release.yml` and `.github/workflows/bump-version.yml`
 - `pyo3 = { version = "0.28.3", features = ["abi3-py310"] }`
 - `pyo3-async-runtimes = { version = "0.28", features = ["tokio-runtime"] }`
 - `tokio = { version = "1", features = ["rt", "macros"] }`
-- `scraper = { version = "0.27.0", git = "https://github.com/rust-scraper/scraper", features = ["atomic"], rev = "9c1eff304e45a8bccb463968268ce6758703e821" }`
 - `xee-xpath = "0.1.5"`
-- `html5ever = "0.39.0"`
+- `rustedbytes-tl = { version = "0.2.0", features = ["std"] }`
 
 ### Python Dependencies (pyproject.toml)
 **Runtime**: None (self-contained binary wheel)
@@ -339,7 +338,7 @@ See `.github/workflows/release.yml` and `.github/workflows/bump-version.yml`
 ## Resources
 
 - **PyO3 Documentation**: https://pyo3.rs/
-- **scraper crate**: https://docs.rs/scraper/
+- **rustedbytes-tl crate**: https://crates.io/crates/rustedbytes-tl
 - **Maturin Guide**: https://www.maturin.rs/
 - **Project README**: `README.md`
 - **Example Usage**: `examples/demo.py`