PyPI - scraper-rust - Versions diffs - 0.6.0__tar.gz → 0.7.0__tar.gz - Mend

scraper-rust 0.6.0tar.gz → 0.7.0tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (52) hide show

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/.github/workflows/release.yml RENAMED Viewed

@@ -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-0.6.0 → scraper_rust-0.7.0}/.github/workflows/tests.yml RENAMED Viewed

@@ -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-0.6.0 → scraper_rust-0.7.0}/AGENTS.md RENAMED Viewed

@@ -23,7 +23,7 @@ This file contains essential information for Large Language Models (LLMs) to eff
   - `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
@@ -59,8 +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
@@ -77,7 +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
@@ -240,7 +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
@@ -258,7 +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
@@ -269,7 +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
@@ -296,7 +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

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/Cargo.lock RENAMED Viewed

@@ -124,7 +124,7 @@ checksum = "56791e4bd64c99fc361e01008f45c984baa93f12a0957d1b3c51dd2c6baab453"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -148,7 +148,7 @@ dependencies = [
  "proc-macro-crate",
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -392,7 +392,7 @@ checksum = "1ac70aa55017e108007fbaf5aa0f54b021c98f92ff8af59d42eda9da96e3dd4f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -419,7 +419,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -465,41 +465,41 @@ checksum = "e6d5a32815ae3f33302d95fdcb2ce17862f8c65363dcfd29360480ba1001fc9c"
 [[package]]
 name = "futures-channel"
-version = "0.3.32"
+version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "07bbe89c50d7a535e539b8c17bc0b49bdb77747034daa8087407d655f3f7cc1d"
+checksum = "262590f4fe6afeb0bc83be1daa64e52657fe185690a958af7f3ad0e92085c5ae"
 dependencies = [
  "futures-core",
 ]
 [[package]]
 name = "futures-core"
-version = "0.3.32"
+version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d"
+checksum = "2cd50c473c80f6d7c3670a752354b8e569b1a7cbfdc0419ec88e5edad85e0dc7"
 [[package]]
 name = "futures-macro"
-version = "0.3.32"
+version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e835b70203e41293343137df5c0664546da5745f82ec9b84d40be8336958447b"
+checksum = "2d6d3cde68c518367be28956066ddfef33813991b77a55005a69dae04bf3b10b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
 name = "futures-task"
-version = "0.3.32"
+version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "037711b3d59c33004d3856fbdc83b99d4ff37a24768fa1be9ce3538a1cde4393"
+checksum = "b231ed28831efb4a61a08580c4bc233ec56bc009f4cd8f52da2c3cb97df0c109"
 [[package]]
 name = "futures-util"
-version = "0.3.32"
+version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6"
+checksum = "a77a90a256fce34da66415271e30f94ee91c57b04b8a2c042d9cf3220179deaa"
 dependencies = [
  "futures-core",
  "futures-macro",
@@ -1006,7 +1006,7 @@ checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -1082,7 +1082,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "strum",
- "syn 2.0.117",
+ "syn 2.0.119",
  "thiserror",
 ]
@@ -1256,7 +1256,7 @@ dependencies = [
  "quote",
  "regex-syntax 0.8.10",
  "rustc_version",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -1336,7 +1336,7 @@ checksum = "ed3955f1a9c7c0c15e092f9c887db08b1fc683305fdf6eb6684f22555355e202"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -1556,9 +1556,9 @@ dependencies = [
 [[package]]
 name = "pyo3"
-version = "0.28.3"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91fd8e38a3b50ed1167fb981cd6fd60147e091784c427b8f7183a7ee32c31c12"
+checksum = "cd274650b21d4bfc26a0a47587962c1edb425f69287324355cd040c3ea66071c"
 dependencies = [
  "libc",
  "once_cell",
@@ -1570,9 +1570,9 @@ dependencies = [
 [[package]]
 name = "pyo3-async-runtimes"
-version = "0.28.0"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e7364a95bf00e8377bbf9b0f09d7ff9715a29d8fcf93b47d1a967363b973178"
+checksum = "b3ef68daa7316a3fac65e5e18b2203f010346de1c1c53456811a2624673ab046"
 dependencies = [
  "futures-channel",
  "futures-util",
@@ -1584,18 +1584,18 @@ dependencies = [
 [[package]]
 name = "pyo3-build-config"
-version = "0.28.3"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e368e7ddfdeb98c9bca7f8383be1648fd84ab466bf2bc015e94008db6d35611e"
+checksum = "c5e2a7d2f0d013342f295c048ad19237add5154a55b1c5a254c0ec93d4109078"
 dependencies = [
  "target-lexicon",
 ]
 [[package]]
 name = "pyo3-ffi"
-version = "0.28.3"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f29e10af80b1f7ccaf7f69eace800a03ecd13e883acfacc1e5d0988605f651e"
+checksum = "ca85c467da1bbc8d866eea5deff9cf29ea5f7785054a17da36e65bda9c05845b"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -1603,34 +1603,33 @@ dependencies = [
 [[package]]
 name = "pyo3-macros"
-version = "0.28.3"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df6e520eff47c45997d2fc7dd8214b25dd1310918bbb2642156ef66a67f29813"
+checksum = "9ac53762fd065daa3194dd09337a38bd793a188100fd1a9304c4ab312d901771"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.28.3"
+version = "0.29.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4cdc218d835738f81c2338f822078af45b4afdf8b2e33cbb5916f108b813acb"
+checksum = "4ca3a1557399783172dc5bf39cfca835157732532cba56b71d2292161e53b362"
 dependencies = [
  "heck",
  "proc-macro2",
- "pyo3-build-config",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
 name = "quote"
-version = "1.0.45"
+version = "1.0.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+checksum = "dfbc457d0c7a0759a614551b11a6409e5951f6c7537be1f1b7682b9ae9230368"
 dependencies = [
  "proc-macro2",
 ]
@@ -1864,7 +1863,7 @@ dependencies = [
 [[package]]
 name = "scraper-rs"
-version = "0.6.0"
+version = "0.7.0"
 dependencies = [
  "criterion",
  "pyo3",
@@ -1915,7 +1914,7 @@ checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -1998,7 +1997,7 @@ dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2014,9 +2013,9 @@ dependencies = [
 [[package]]
 name = "syn"
-version = "2.0.117"
+version = "2.0.119"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2042,7 +2041,7 @@ checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2074,7 +2073,7 @@ checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2114,9 +2113,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 [[package]]
 name = "tokio"
-version = "1.52.3"
+version = "1.53.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fc7f01b389ac15039e4dc9531aa973a135d7a4135281b12d7c1bc79fd57fffe"
+checksum = "d988bcd52dbe076d3d46903332f58c912b87a2c49b1428419a5845154762ffee"
 dependencies = [
  "pin-project-lite",
  "tokio-macros",
@@ -2130,7 +2129,7 @@ checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2273,7 +2272,7 @@ dependencies = [
  "bumpalo",
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
  "wasm-bindgen-shared",
 ]
@@ -2348,7 +2347,7 @@ checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2359,7 +2358,7 @@ checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2589,7 +2588,7 @@ checksum = "30d233fc2ef8ab1a9f9bf7af9cc1c7f7e7d75eb9848f731a99d8f1d4c2259fe3"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
  "xee-schema-type",
  "xee-xpath-ast",
  "xot",
@@ -2652,7 +2651,7 @@ checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
  "synstructure",
 ]
@@ -2673,7 +2672,7 @@ checksum = "0b631b19d36a892ab55420c92dbc83ccd79274f25be714855d3074aa71cab639"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]
@@ -2693,7 +2692,7 @@ checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
  "synstructure",
 ]
@@ -2727,7 +2726,7 @@ checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 2.0.119",
 ]
 [[package]]

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/Cargo.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [package]
 name = "scraper-rs"
-version = "0.6.0"
+version = "0.7.0"
 edition = "2024"
 readme = "README.md"
@@ -15,8 +15,8 @@ default = []
 extension-module = ["pyo3/extension-module"]
 [dependencies]
-pyo3 = { version = "0.28.3", features = ["abi3-py310"] }
-pyo3-async-runtimes = { version = "0.28", features = ["tokio-runtime"] }
+pyo3 = { version = "0.29.0", features = ["abi3-py310"] }
+pyo3-async-runtimes = { version = "0.29", features = ["tokio-runtime"] }
 rayon = "1"
 tokio = { version = "1", features = ["rt", "macros", "sync"] }
@@ -28,7 +28,7 @@ criterion = { version = "0.8", features = ["async_tokio"] }
 tokio = { version = "1", features = ["rt-multi-thread", "macros"] }
 [build-dependencies]
-pyo3-build-config = { version = "0.28.3", features = ["resolve-config"] }
+pyo3-build-config = { version = "0.29.0", features = ["resolve-config"] }
 [[bench]]
 name = "sync_async"

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scraper-rust
-Version: 0.6.0
+Version: 0.7.0
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
@@ -33,6 +33,15 @@ Project-URL: Repository, https://github.com/RustedBytes/scraper-rs
 Python bindings for high-performance Rust HTML parsing via PyO3. It provides a lightweight `Document`/`Element` API with CSS selectors backed by `rustedbytes-tl`, XPath (via `xee-xpath`), handy helpers, and zero Python-side parsing work.
+## Install
+```bash
+pip install scraper-rust
+# or using uv
+uv add scraper-rust
+```
 ## Quick start
 ```py
@@ -50,7 +59,7 @@ print(doc.text)  # "First Second"
 items = doc.select(".item")
 print(items[0].attr("data-id"))  # "1"
-print(items[0].to_dict())        # {"tag": "div", "text": "First", "html": "<a...>", ...}
+print(items[0].to_dict())  # {"tag": "div", "text": "First", "html": "<a...>", ...}
 first_link = doc.select_first("a[href]")  # alias: doc.find(...)
 print(first_link.text, first_link.attr("href"))  # First /a
@@ -65,9 +74,11 @@ print(doc.xpath_first("//div[@data-id='1']/a").attr("href"))  # "/a"
 # Functional helpers
 links = select(html, "a[href]")
 print([link.attr("href") for link in links])  # ["/a", "/b"]
-print(first(html, "a[href]").text)            # First
-print(select_first(html, "a[href]").text)     # First
-print([link.text for link in xpath(html, "//div[@class='item']/a")])  # ["First", "Second"]
+print(first(html, "a[href]").text)  # First
+print(select_first(html, "a[href]").text)  # First
+print(
+    [link.text for link in xpath(html, "//div[@class='item']/a")]
+)  # ["First", "Second"]
 print(prettify(html))
 ```

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/README.md RENAMED Viewed

@@ -6,6 +6,15 @@
 Python bindings for high-performance Rust HTML parsing via PyO3. It provides a lightweight `Document`/`Element` API with CSS selectors backed by `rustedbytes-tl`, XPath (via `xee-xpath`), handy helpers, and zero Python-side parsing work.
+## Install
+```bash
+pip install scraper-rust
+# or using uv
+uv add scraper-rust
+```
 ## Quick start
 ```py
@@ -23,7 +32,7 @@ print(doc.text)  # "First Second"
 items = doc.select(".item")
 print(items[0].attr("data-id"))  # "1"
-print(items[0].to_dict())        # {"tag": "div", "text": "First", "html": "<a...>", ...}
+print(items[0].to_dict())  # {"tag": "div", "text": "First", "html": "<a...>", ...}
 first_link = doc.select_first("a[href]")  # alias: doc.find(...)
 print(first_link.text, first_link.attr("href"))  # First /a
@@ -38,9 +47,11 @@ print(doc.xpath_first("//div[@data-id='1']/a").attr("href"))  # "/a"
 # Functional helpers
 links = select(html, "a[href]")
 print([link.attr("href") for link in links])  # ["/a", "/b"]
-print(first(html, "a[href]").text)            # First
-print(select_first(html, "a[href]").text)     # First
-print([link.text for link in xpath(html, "//div[@class='item']/a")])  # ["First", "Second"]
+print(first(html, "a[href]").text)  # First
+print(select_first(html, "a[href]").text)  # First
+print(
+    [link.text for link in xpath(html, "//div[@class='item']/a")]
+)  # ["First", "Second"]
 print(prettify(html))
 ```

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/docs/api.md RENAMED Viewed

@@ -11,7 +11,7 @@ from scraper_rs import Document
 doc = Document(
     html,
-    max_size_bytes=None,      # default: 1 GiB
+    max_size_bytes=None,  # default: 1 GiB
     truncate_on_limit=False,  # default: error on oversized HTML
 )
 ```

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/docs/async-api.md RENAMED Viewed

@@ -31,12 +31,14 @@ from scraper_rs import asyncio as async_scraper
 html = "<div class='item'><a href='/a'>First</a></div>"
 async def main():
     async with await async_scraper.parse(html) as doc:
         items = await doc.select(".item")
         first_link = await items[0].select_first("a[href]")
         print(first_link.text, first_link.attr("href"))
 asyncio.run(main())
 ```

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/pyproject.toml RENAMED Viewed

@@ -4,7 +4,7 @@ build-backend = "maturin"
 [project]
 name = "scraper-rust"
-version = "0.6.0"
+version = "0.7.0"
 description = "Python bindings for high-performance HTML parsing and selection with PyO3"
 authors = [{ name = "Yehor Smoliakov", email = "egorsmkv@gmail.com" }]
 requires-python = ">=3.10"

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/scraper_rs/asyncio.py RENAMED Viewed

@@ -2,17 +2,17 @@
 from __future__ import annotations
-from .scraper_rs import (
-    _AsyncDocumentCore,
-    _AsyncElementCore,
-    first_async as _first_async,
-    parse_async as _parse_async,
-    prettify_async as _prettify_async,
-    select_async as _select_async,
-    select_first_async as _select_first_async,
-    xpath_async as _xpath_async,
-    xpath_first_async as _xpath_first_async,
-)
+from . import scraper_rs as _core
+_AsyncDocumentCore = _core._AsyncDocumentCore
+_AsyncElementCore = _core._AsyncElementCore
+_first_async = _core.first_async
+_parse_async = _core.parse_async
+_prettify_async = _core.prettify_async
+_select_async = _core.select_async
+_select_first_async = _core.select_first_async
+_xpath_async = _core.xpath_async
+_xpath_first_async = _core.xpath_first_async
 def _wrap_element(element: _AsyncElementCore | None) -> "AsyncElement | None":

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/src/prettify.rs RENAMED Viewed

@@ -19,6 +19,44 @@ pub(crate) fn escape_html(value: &str) -> String {
     escaped
 }
+#[inline]
+fn entity_reference_len(value: &str) -> Option<usize> {
+    let semicolon = value.find(';')?;
+    let reference = &value[..semicolon];
+    let valid = if let Some(numeric) = reference.strip_prefix('#') {
+        if let Some(hex) = numeric
+            .strip_prefix('x')
+            .or_else(|| numeric.strip_prefix('X'))
+        {
+            !hex.is_empty() && hex.bytes().all(|byte| byte.is_ascii_hexdigit())
+        } else {
+            !numeric.is_empty() && numeric.bytes().all(|byte| byte.is_ascii_digit())
+        }
+    } else {
+        !reference.is_empty() && reference.bytes().all(|byte| byte.is_ascii_alphanumeric())
+    };
+    valid.then_some(semicolon + 1)
+}
+#[inline]
+fn escape_html_text(value: &str) -> String {
+    let mut escaped = String::with_capacity(value.len());
+    let mut rest = value;
+    while let Some((before, after_ampersand)) = rest.split_once('&') {
+        escaped.push_str(&escape_html(before));
+        rest = &rest[before.len() + 1..];
+        if let Some(reference_len) = entity_reference_len(after_ampersand) {
+            escaped.push('&');
+            escaped.push_str(&after_ampersand[..reference_len]);
+            rest = &after_ampersand[reference_len..];
+        } else {
+            escaped.push_str("&amp;");
+        }
+    }
+    escaped.push_str(&escape_html(rest));
+    escaped
+}
 #[inline]
 fn push_indent(out: &mut String, level: usize, indent_size: usize) {
     let spaces = level.saturating_mul(indent_size);
@@ -135,7 +173,7 @@ fn serialize_pretty_element_into(
         && let PrettyChild::Text(text) = &children[0]
     {
         out.push('>');
-        out.push_str(&escape_html(text));
+        out.push_str(&escape_html_text(text));
         out.push_str("</");
         out.push_str(&name);
         out.push_str(">\n");
@@ -160,7 +198,7 @@ fn serialize_pretty_element_into(
             }
             PrettyChild::Text(text) => {
                 push_indent(out, level + 1, indent_size);
-                out.push_str(&escape_html(&text));
+                out.push_str(&escape_html_text(&text));
                 out.push('\n');
             }
         }
@@ -191,7 +229,7 @@ pub(crate) fn prettify_document_html(html: &str) -> String {
                 tl::Node::Raw(text) => {
                     let normalized = normalized_text(&bytes_to_string(text));
                     if !normalized.is_empty() {
-                        out.push_str(&escape_html(&normalized));
+                        out.push_str(&escape_html_text(&normalized));
                         out.push('\n');
                     }
                 }
@@ -226,7 +264,7 @@ pub(crate) fn prettify_fragment_html(html: &str) -> PyResult<String> {
                     if normalized.is_empty() {
                         continue;
                     }
-                    out.push_str(&escape_html(&normalized));
+                    out.push_str(&escape_html_text(&normalized));
                     out.push('\n');
                 }
                 tl::Node::Comment(_) => {}

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/src/tests.rs RENAMED Viewed

@@ -233,6 +233,10 @@ fn prettify_helpers_format_document_and_fragment() {
     assert!(doc_pretty.contains("<span>Hi</span>"));
     assert!(doc_pretty.contains("<p>A &amp; B</p>"));
     assert!(doc_pretty.contains("<br>"));
+    assert_eq!(
+        prettify_document_html("<p>&gt; &amp; &#65; &#x41; &</p>"),
+        "<p>&gt; &amp; &#65; &#x41; &amp;</p>"
+    );
     let fragment_pretty =
         prettify_fragment_html(r#"hello <span data-x="1"> world </span>"#).unwrap();

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/src/xpath.rs RENAMED Viewed

@@ -141,6 +141,9 @@ pub(crate) fn xpath_with_limit(
 ) -> PyResult<Vec<Element>> {
     let max_size_bytes = max_size_bytes.unwrap_or(DEFAULT_MAX_PARSE_BYTES);
     let html_to_parse = ensure_within_size_limit(html, max_size_bytes, truncate_on_limit)?;
+    if html_to_parse.len() < html.len() {
+        return evaluate_fragment_xpath_with_fallback(html_to_parse.as_ref(), expr);
+    }
     match parse_xpath_documents(html_to_parse.as_ref(), "HTML document") {
         Ok((mut documents, document_handle)) => {
             evaluate_xpath_elements(&mut documents, document_handle, expr)
@@ -160,6 +163,9 @@ pub(crate) fn xpath_first_with_limit(
 ) -> PyResult<Option<Element>> {
     let max_size_bytes = max_size_bytes.unwrap_or(DEFAULT_MAX_PARSE_BYTES);
     let html_to_parse = ensure_within_size_limit(html, max_size_bytes, truncate_on_limit)?;
+    if html_to_parse.len() < html.len() {
+        return evaluate_fragment_xpath_first_with_fallback(html_to_parse.as_ref(), expr);
+    }
     match parse_xpath_documents(html_to_parse.as_ref(), "HTML document") {
         Ok((mut documents, document_handle)) => {
             evaluate_xpath_first_element(&mut documents, document_handle, expr)
@@ -219,12 +225,7 @@ pub(crate) fn evaluate_fragment_xpath_with_fallback(
     if normalized.is_empty() {
         return Ok(Vec::new());
     }
-    match parse_xpath_documents(&normalized, "HTML document") {
-        Ok((mut documents, document_handle)) => {
-            evaluate_xpath_elements(&mut documents, document_handle, expr)
-        }
-        Err(_) => Ok(Vec::new()),
-    }
+    evaluate_fragment_xpath(&normalized, expr)
 }
 pub(crate) fn evaluate_fragment_xpath_first_with_fallback(
@@ -235,12 +236,7 @@ pub(crate) fn evaluate_fragment_xpath_first_with_fallback(
     if normalized.is_empty() {
         return Ok(None);
     }
-    match parse_xpath_documents(&normalized, "HTML document") {
-        Ok((mut documents, document_handle)) => {
-            evaluate_xpath_first_element(&mut documents, document_handle, expr)
-        }
-        Err(_) => Ok(None),
-    }
+    evaluate_fragment_xpath_first(&normalized, expr)
 }
 pub(crate) struct XPathDocumentState {

{scraper_rust-0.6.0 → scraper_rust-0.7.0}/uv.lock RENAMED Viewed

@@ -43,26 +43,26 @@ wheels = [
 [[package]]
 name = "maturin"
-version = "1.13.3"
+version = "1.14.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "tomli", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9c/1c/612d23d33ec21b9ae7ece7b3f0dd5f9dfd57b4009e9d2938165869ebd6ae/maturin-1.13.3.tar.gz", hash = "sha256:771e1e9e71a278e56db01552e0d1acfd1464259f9575b6e72842f893cd299079", size = 357934, upload-time = "2026-05-11T07:43:39.027Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e7/b3/addd877f871fb1860d46d3a4f206ecb10b946c85846805e6367631926fd3/maturin-1.14.1.tar.gz", hash = "sha256:9d6577a62cd08e0ceba7a0db06fb098e0c9b1b3429bad747a4f3a18215a1b3df", size = 369637, upload-time = "2026-06-19T05:19:49.774Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/71/66/18c2aaac0b2a5dea9f1db5984ce83b905ad205cfc7c02d0091e707c0c2e7/maturin-1.13.3-py3-none-linux_armv6l.whl", hash = "sha256:3cc13929ca82aefa4adbf0f2c35419369796213c6fb0eb24e914945f50ef5d8c", size = 10190971, upload-time = "2026-05-11T07:43:10.431Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/71/26a988d092e4fd6a9523d46d44400a46cad7cdf3fd206ce702240c748aee/maturin-1.13.3-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:53b08bd075649ce96513ad9abf241a43cb685ed6e9e7790f8dbc2d66e95d8323", size = 19716714, upload-time = "2026-05-11T07:43:36.911Z" },
-    { url = "https://files.pythonhosted.org/packages/82/5c/f3fd0e184255d9fc7e272c62af3dfa84c617b2577ef83af9ce615f5279cc/maturin-1.13.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:4cd478e6e4c56251e48ed079b8efd55b30bc5c09cf695a1bdafaeb582ee735a0", size = 10194726, upload-time = "2026-05-11T07:43:07.05Z" },
-    { url = "https://files.pythonhosted.org/packages/a9/e1/f4edb69fb647b77c4769a9bfd4d6fb62961e653d164bc277ecdffac3ab61/maturin-1.13.3-py3-none-manylinux_2_12_i686.manylinux2010_i686.musllinux_1_1_i686.whl", hash = "sha256:a2675e25f313034ae6f57388cf14818f87d8961c4a96795287f3e155f59beb11", size = 10172781, upload-time = "2026-05-11T07:43:40.796Z" },
-    { url = "https://files.pythonhosted.org/packages/c7/7d/a1be934690cdcc3c6609769ceaad322ab7501c2ee5bafcac1b14d609e403/maturin-1.13.3-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.musllinux_1_1_x86_64.whl", hash = "sha256:4667ef609ab446c1b5e0bfe4f9fb99699ab6d8548433f8d1a684256e0b67217f", size = 10682670, upload-time = "2026-05-11T07:43:13.132Z" },
-    { url = "https://files.pythonhosted.org/packages/18/f5/372ae19b72ce8f6e37e5864ae4dc5b252ee9fce0619ccc3aa366aa3a7f97/maturin-1.13.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.musllinux_1_1_aarch64.whl", hash = "sha256:3db93337ed97e60ffc878aa8b493cd7ae44d3a5e1a37256db3a4491f57565018", size = 10060363, upload-time = "2026-05-11T07:43:21.107Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/5b/c68340cca09368af0df80965dfabed4234205a492a93da00793c7b9aae20/maturin-1.13.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.musllinux_1_1_armv7l.whl", hash = "sha256:1cc0a110b224ca90406b668a3e3c1f5a515062e59e26292f6dbaf5fd4909c6f3", size = 10017551, upload-time = "2026-05-11T07:43:33.916Z" },
-    { url = "https://files.pythonhosted.org/packages/28/1e/f90fb2b000bad9e6d850cd5afb88b2f1e2a279cfb4de02ea40078484690e/maturin-1.13.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.musllinux_1_1_ppc64le.whl", hash = "sha256:c00ea6428dea17bf616fe93770837634454b28c2de1a876e42ef8036c616079a", size = 13301712, upload-time = "2026-05-11T07:43:26.492Z" },
-    { url = "https://files.pythonhosted.org/packages/be/58/1670f68a8f04ccd7b90df11047bd9a046585310e84e1967cc9849cd1c5a3/maturin-1.13.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:49fd6ab08da28098ccf37afca24cdba72376ba9c1eedf9dd25ff82ed771961ff", size = 10946765, upload-time = "2026-05-11T07:43:16.135Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/ac/00c955c2ef134817b1a7bdaa76b0309e9c5291eb17d9ff88069eecd08bc2/maturin-1.13.3-py3-none-manylinux_2_31_riscv64.musllinux_1_1_riscv64.whl", hash = "sha256:b6741d7bf4af97da937528fd1e523c6ab54f53d9a21870fa735d6e67fd88e273", size = 10388661, upload-time = "2026-05-11T07:43:18.727Z" },
-    { url = "https://files.pythonhosted.org/packages/97/c6/cbf8a51dde19c19aeba0d9b075095a2effb9b31fd312b1aae3ac79f8aea2/maturin-1.13.3-py3-none-win32.whl", hash = "sha256:0ef257e692cc756c87af5bea95ddfe7d3ac49d3376a7a87f728d63f06e7b6f8b", size = 8901838, upload-time = "2026-05-11T07:43:23.76Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/ff/c6a50a59dc8313097d43ac5f4d74df6a500c8cb62b0dc9e054f53e203a48/maturin-1.13.3-py3-none-win_amd64.whl", hash = "sha256:def4a435ea9d2ee93b18ba579dc8c9cf898889a66f312cd379b5e374ec3e3ad6", size = 10340801, upload-time = "2026-05-11T07:43:29.239Z" },
-    { url = "https://files.pythonhosted.org/packages/6c/93/e32e79333f0902ba292b996f504f5f06be59587f7d02ab8d5ed1e3066445/maturin-1.13.3-py3-none-win_arm64.whl", hash = "sha256:2389fe92d017cea9d94e521fa0175314a4c52f79a1057b901fbc9f8686ef7d0b", size = 9706562, upload-time = "2026-05-11T07:43:31.743Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/f0/97c5a5bd9c71653a066c0976a484eaaae50b9369557838a4176b7b0bdaa5/maturin-1.14.1-py3-none-linux_armv6l.whl", hash = "sha256:522292398945442cdafa9daeb2271b2340fbde57027b818f923f88eab04174f8", size = 10207496, upload-time = "2026-06-19T05:19:09.321Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/83/294bca639b0e052f1e2f65199b3db258780c7d4e31408b934c9c974a1379/maturin-1.14.1-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:ffe5ad71f21d1e6603c4dd75f7fee34adf5ed5ebcebb692886549888ebb329ed", size = 19680113, upload-time = "2026-06-19T05:19:13.43Z" },
+    { url = "https://files.pythonhosted.org/packages/43/b6/79c881410a3b1c187f7eb3d407aecae646c6a4433d630d72200359015e83/maturin-1.14.1-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:f3306078070c1508fd715b9116070cbcaff5959024272a9f1e6f5cb29768b86c", size = 10169205, upload-time = "2026-06-19T05:19:16.615Z" },
+    { url = "https://files.pythonhosted.org/packages/93/9d/44b6f26dcb7f7a04c5501ac2dbb6ca1490150682baa525ca5860504f9eab/maturin-1.14.1-py3-none-manylinux_2_12_i686.manylinux2010_i686.musllinux_1_1_i686.whl", hash = "sha256:cd457cd88961156e26379e1155bd287cc0ec1c8b2f1582b0660fb31b87c8842d", size = 10188098, upload-time = "2026-06-19T05:19:19.736Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/bd/9c0d5d6983905ce2c9edaa073a7e89355a9cf7f396988e05d32f1c37785d/maturin-1.14.1-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.musllinux_1_1_x86_64.whl", hash = "sha256:dfc54ae32e6fcb18302193ab9a30b0b25eefffba994ae13238974805533ef75e", size = 10627576, upload-time = "2026-06-19T05:19:22.713Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/33/b096412bd6a7cb399652b260666f901adf88a687181a6dbd6a3f89f0a94e/maturin-1.14.1-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.musllinux_1_1_aarch64.whl", hash = "sha256:a131d912b5267e640bc96d70f4914e10590aed64082ec9abacba7cea52004224", size = 10085181, upload-time = "2026-06-19T05:19:25.69Z" },
+    { url = "https://files.pythonhosted.org/packages/56/8d/08c3bf469c38a23c9e6c877e338193001eb604d010fedc08341974e38528/maturin-1.14.1-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.musllinux_1_1_armv7l.whl", hash = "sha256:be18fc568fb76884c0205456336892a75105ec398e6b667cd777c6268bd06d69", size = 10026363, upload-time = "2026-06-19T05:19:28.904Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/a4/c4d1a92839f8745ab4aab988a7db884a79d6d710bd3b286fcf9316dece1a/maturin-1.14.1-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.musllinux_1_1_ppc64le.whl", hash = "sha256:994a0c8ba3ad8a92b3a9ee1b02645d200d610216b15cff5102b0fe65e8e08666", size = 13321347, upload-time = "2026-06-19T05:19:32.411Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/fa/170f04624d03fd07d2a8b1b67de83a127af93aef9eaa425839553347297b/maturin-1.14.1-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:be80866363e605d137991b491a741a84cde9ae350183c4c85f49690ca9aaaa65", size = 10877609, upload-time = "2026-06-19T05:19:35.448Z" },
+    { url = "https://files.pythonhosted.org/packages/61/ad/1ae2e1d0ded282bf2c55ac13f0811d87deb425e200ae64a15785675dede9/maturin-1.14.1-py3-none-manylinux_2_31_riscv64.musllinux_1_1_riscv64.whl", hash = "sha256:5282dffd4b539d2be245f4e5b1a5ab6bc1033b58f4a4872f5833f9d43c954aa4", size = 10417316, upload-time = "2026-06-19T05:19:38.28Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/27/bf677183920718da49cd7982d6a3ffc440aad8919329f571d189f81b7bdf/maturin-1.14.1-py3-none-win32.whl", hash = "sha256:1a04de0a20188f95c721b5702eed18140bdcccb28c386797093eca3f62f4d4e0", size = 8931293, upload-time = "2026-06-19T05:19:41.183Z" },
+    { url = "https://files.pythonhosted.org/packages/63/4b/585adeb9167b08d3cdff0032a938b0e72655c92003df4f52c3f696a1bcc2/maturin-1.14.1-py3-none-win_amd64.whl", hash = "sha256:3c9f94640ecc4895e94abaf834a0684430032c865b2748a36c12461fd9252fdd", size = 10314067, upload-time = "2026-06-19T05:19:44.389Z" },
+    { url = "https://files.pythonhosted.org/packages/51/d4/dac8c0720ae246be1700afb6fbdbbea20fe35b13f6570b2f70faa005df77/maturin-1.14.1-py3-none-win_arm64.whl", hash = "sha256:15cea8fcb3ba47dd636f50092bb34baea8b04ac777392f23e6bf8a9a61efb894", size = 9718943, upload-time = "2026-06-19T05:19:47.49Z" },
 ]
 [[package]]
@@ -94,7 +94,7 @@ wheels = [
 [[package]]
 name = "pytest"
-version = "9.0.3"
+version = "9.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "colorama", marker = "sys_platform == 'win32'" },
@@ -105,9 +105,9 @@ dependencies = [
     { name = "pygments" },
     { name = "tomli", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/7d/0d/549bd94f1a0a402dc8cf64563a117c0f3765662e2e668477624baeec44d5/pytest-9.0.3.tar.gz", hash = "sha256:b86ada508af81d19edeb213c681b1d48246c1a91d304c6c81a427674c17eb91c", size = 1572165, upload-time = "2026-04-07T17:16:18.027Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e4/47/b9efed96c114afcfa3c9d3fe98a76a1d14c74a9e266d397cf6eb64be5e01/pytest-9.1.1.tar.gz", hash = "sha256:1088fbde8f2b49d95a549a195707afa7a76a3ce9bcadc26b6d71f0ffda5fe313", size = 1636369, upload-time = "2026-06-19T10:58:32.857Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d4/24/a372aaf5c9b7208e7112038812994107bc65a84cd00e0354a88c2c77a617/pytest-9.0.3-py3-none-any.whl", hash = "sha256:2c5efc453d45394fdd706ade797c0a81091eccd1d6e4bccfcd476e2b8e0ab5d9", size = 375249, upload-time = "2026-04-07T17:16:16.13Z" },
+    { url = "https://files.pythonhosted.org/packages/24/25/1de2678b631f5a49215c6c96fff41ba892b0a34df68d6d80292b1b48aa7f/pytest-9.1.1-py3-none-any.whl", hash = "sha256:37a86b45efb9a47a61a36449063e8e18d0cab3161329fc099eb21783169c4f0c", size = 386536, upload-time = "2026-06-19T10:58:31.347Z" },
 ]
 [[package]]
@@ -126,32 +126,32 @@ wheels = [
 [[package]]
 name = "ruff"
-version = "0.15.15"
+version = "0.16.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/84/6f/a76f7d96e5c962f5b69cee865e49c15c1116897c01990faa8a57edb62e7f/ruff-0.15.15.tar.gz", hash = "sha256:b8dff018130b46d8e5bf0f926ef6b60cf871d6d5ae45fc9334e09632daa741d6", size = 4706985, upload-time = "2026-05-28T14:16:57.784Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/4d/94/1e5e4967626faf12fa56999cd6222dff6992ceb086ad7945756baf70c7a7/ruff-0.16.0.tar.gz", hash = "sha256:e460aafd5495ec89efaa6ced2e4a9a581116451e1c88b9d37ef497e0f8e93982", size = 4790557, upload-time = "2026-07-23T19:11:30.981Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fa/9d/3a45c05b8ab04b4705989de70a79008e27c8003296a0feaee9edc18dd7e9/ruff-0.15.15-py3-none-linux_armv6l.whl", hash = "sha256:cf93e5388f412e1b108b1f8b34a6e036b70fe8aff89393befad96fe48670311b", size = 10710652, upload-time = "2026-05-28T14:16:06.701Z" },
-    { url = "https://files.pythonhosted.org/packages/05/66/da974431624bf3b49f6ee1f9543c02d929ff1cba78b0d5a79c38cf21f744/ruff-0.15.15-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:ac5a646d1f6a7dadd5d50842dae2c1f9862ac887ef5d1b1375e02def791fde6e", size = 11096615, upload-time = "2026-05-28T14:16:23.313Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/09/7443452e5d290230a712103f2fdceeef7184f3ec99a2bd01c8be78aaceb5/ruff-0.15.15-py3-none-macosx_11_0_arm64.whl", hash = "sha256:77d955a431430c66f72dd94e379ad38a16daea3d25094872ac4edf9e797be530", size = 10436683, upload-time = "2026-05-28T14:16:40.974Z" },
-    { url = "https://files.pythonhosted.org/packages/53/01/d330c26a57fa4f3943a14424904027428315b700fe4d14a84bb123a649e5/ruff-0.15.15-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7614ee79c69788cf6cedd568069ade9cecc22a1ad20494efe8d0c9ebb4b622d4", size = 10769064, upload-time = "2026-05-28T14:16:28.905Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/85/cc8770f8bdff541b1da8392d1634141fe4a0e3f4ee596605959b7906c27f/ruff-0.15.15-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3cdb1679e06a1f6b47bc384714ae96f6e2fb65ca441eb78c43d2ca554176ce1f", size = 10511987, upload-time = "2026-05-28T14:16:43.732Z" },
-    { url = "https://files.pythonhosted.org/packages/7c/29/8c190c1472b63013583ba391f3342036e02010544c1270455ed8e519bdf3/ruff-0.15.15-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2728b93d7b23a603ea2c0ac6eb73d760bd38ec9de35f35fb41e18f7a3fee7622", size = 11275100, upload-time = "2026-05-28T14:16:55.244Z" },
-    { url = "https://files.pythonhosted.org/packages/9f/6b/7e145ce2cc8e63d6834eca03d83a0e18d121def5c69f91b4cf4011ed4879/ruff-0.15.15-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:be582fcc0db438902c7792b08d6ddf6c9b9e21addaa10092c2c741cfb09e5a45", size = 12176903, upload-time = "2026-05-28T14:16:14.368Z" },
-    { url = "https://files.pythonhosted.org/packages/80/a3/d5974637f68e451f7fadf015cf3101d1cd7d8ba5027cffe0b9e3826ebe6b/ruff-0.15.15-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7aa77465b8ecaf1a27bea098d696f7fed5e1eccbd10b321b682d6de586ae5627", size = 11404550, upload-time = "2026-05-28T14:16:20.138Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/1c/e6e5e568f22be4fb05d6244234aba384c06b451252453b821e1a529263cf/ruff-0.15.15-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:48decfa11d740de4889de623be1463308346312f2409a56e24aa280c86162dc4", size = 11382027, upload-time = "2026-05-28T14:16:46.615Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/01/170921b49fcd2e8858825593f91cf7146c3e40a5c3e6df763e4bb0484dde/ruff-0.15.15-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:a5015088452ca0081387063649ec67f06d3d1d6b8b936a1f836b5e9657ecd48c", size = 11366041, upload-time = "2026-05-28T14:16:26.247Z" },
-    { url = "https://files.pythonhosted.org/packages/87/54/a7bad711d7de93254e15e06a4c375b89a03d18de45d3e5dcc86a4472fb1a/ruff-0.15.15-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:f5294aab6356c81600fcdea3a62bb1b924dfd5e91767c12318d3f68f86af57cd", size = 10741795, upload-time = "2026-05-28T14:16:17.11Z" },
-    { url = "https://files.pythonhosted.org/packages/c9/31/38c075963668f8b41c6914ee0f6f318727fbe30ab9145cb29e6df464c5fa/ruff-0.15.15-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:db5bd4d802415cca656dc1616070b725952d6ae95eb5d4831e49fbd94a38f75f", size = 10511117, upload-time = "2026-05-28T14:16:31.767Z" },
-    { url = "https://files.pythonhosted.org/packages/9d/96/6ff689e1f7e375d1d97075eca022f74c2bab59554a432fe4d2e6f091986a/ruff-0.15.15-py3-none-musllinux_1_2_i686.whl", hash = "sha256:587a6278ed42059191c1a466e490bd7930fb50bd2e255398bc29616c895a61cb", size = 10994867, upload-time = "2026-05-28T14:16:35.149Z" },
-    { url = "https://files.pythonhosted.org/packages/c3/c2/5dce0ab9f92a8d534fa62b9bf9caca3eddb8c1a81b616f5e195ada4f0d6e/ruff-0.15.15-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:df0c1c084f5f4be9812f61518a45c440d3c30d69ce4bf6c5270e66d38338f02a", size = 11482101, upload-time = "2026-05-28T14:16:49.598Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/c0/1003b60edd697c649faf61f1a34094b1abb38fb3d1181e3f895781250a08/ruff-0.15.15-py3-none-win32.whl", hash = "sha256:29428ea79694afbe756d45fd59b36f22b6b020dc0443cf7de0173046236964b9", size = 10716774, upload-time = "2026-05-28T14:16:52.337Z" },
-    { url = "https://files.pythonhosted.org/packages/02/a8/1269eddd6945a06c23f055ef7848886e37cf9d6a8bebb386a3115f01470c/ruff-0.15.15-py3-none-win_amd64.whl", hash = "sha256:8df0323902e15e24bc4bf246da830573d3cf3352bd0b9a164eab335d111ff4a4", size = 11868463, upload-time = "2026-05-28T14:16:11.333Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/b2/920464c907b191e37469d477a1aa8bc048b8f36c4c1610dfa4ab87b39e18/ruff-0.15.15-py3-none-win_arm64.whl", hash = "sha256:3c8ceca6792f38196b8f589bc92eccd03eef286602da92e5dc05cc42ef6441b7", size = 11138498, upload-time = "2026-05-28T14:16:38.425Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/81/1c8818fee7ce1a04cd7d1b3172e0a8f8e4f1dc4feb7fc390e16daa8af323/ruff-0.16.0-py3-none-linux_armv6l.whl", hash = "sha256:e5115729eb08c585e5121978ba5d5b60caeae394ce21b9fb5e6cd33a1c6c9b1e", size = 10754633, upload-time = "2026-07-23T19:10:46.415Z" },
+    { url = "https://files.pythonhosted.org/packages/23/df/beaf59c09d68db84304d555f188b276a77132a5d5b0b67a5c762aa143628/ruff-0.16.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:3c954b1d580bfa035b41654f7858cc7e71d5fc3ac5b723dd62bd9133830ed522", size = 10969164, upload-time = "2026-07-23T19:10:50.271Z" },
+    { url = "https://files.pythonhosted.org/packages/42/ce/741cd197496a1abbf51352710fd15ed995d2a2be87189c1da26a450d6e83/ruff-0.16.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e01c21d10eb1b29f47b7454e1f4056db9a3f0260c646aa88457c610291db9f81", size = 10488846, upload-time = "2026-07-23T19:10:52.639Z" },
+    { url = "https://files.pythonhosted.org/packages/52/2a/a2db8e88cade358f5cdcb05674a917751074109315d014eb6352d9a893f7/ruff-0.16.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e364e5ed22ed8dc05082fd78e35308618260907ac2d3c1d637b2e682415b6c9", size = 10889729, upload-time = "2026-07-23T19:10:54.89Z" },
+    { url = "https://files.pythonhosted.org/packages/42/65/62a771694ebd63029dc953e27dbad40e1588bd4860ff9fe881018fddaa49/ruff-0.16.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d327b8fc113a1d4421a04f3839d3752057c8dd1ee320223a6f3f52d04ada462a", size = 10568275, upload-time = "2026-07-23T19:10:56.993Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/e2/ced249fe8af5f086c5c58cc21cc3356d50f32f7401c5df87050c999620a7/ruff-0.16.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9b50c55e263103586b3dcf5f73d479eb8cb5fdb6098fec59a62891dab653717", size = 11385112, upload-time = "2026-07-23T19:10:59.615Z" },
+    { url = "https://files.pythonhosted.org/packages/87/0b/05154977a8fd69eeb6c103271f55403bfd8711f5c0f8ed07489d95a504e7/ruff-0.16.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0ff4a79ce3ec0172f3241943835de1c4cb4e2dcd07f0f8c2d02603dbbbee4b17", size = 12207008, upload-time = "2026-07-23T19:11:02.154Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/29/98225831a3a1eab0e02f4acc6ca6559a98611dcc68b6965ff4b7234627c1/ruff-0.16.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e95c448fca1fb2a18372a9440926c5a6ee789639bb975c72e7ae6d0b04218ab4", size = 11650842, upload-time = "2026-07-23T19:11:04.557Z" },
+    { url = "https://files.pythonhosted.org/packages/91/66/6bd3cf90500653d55dc0ffc8507aa8300bd49d0214b2e8cb4d3fef2943ba/ruff-0.16.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f11a8d11010301d0a398a2fdef67691feca7294da6aef55e2150e8fa2cd520b", size = 11400718, upload-time = "2026-07-23T19:11:09.233Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/a2/a54eb4eae05d66364050a5d3b8a9c5ef88196531b3cbe7109d873f87f819/ruff-0.16.0-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:48044c678e9cb8698246c99b14aaccfa6601dea7379eb48a6f8f73f7a6d86cd0", size = 11426177, upload-time = "2026-07-23T19:11:11.994Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/be/16e3eea4b2a478a496919f5e36f17c4559e54620bd3bbac5d6affa068006/ruff-0.16.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:7aa0959bad8eb8bef50340154fc9b58678dae31fa4293afa38b44b6e552c0213", size = 10856126, upload-time = "2026-07-23T19:11:14.221Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/84/252eb8b868a16eec7257c14f504f77537e734b2d69c762e639e588e304a3/ruff-0.16.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:28ea2b7df8ebf7f9da6b7d47b230ab48f387c0a29be3b474c4d0740e197bb9af", size = 10571208, upload-time = "2026-07-23T19:11:16.378Z" },
+    { url = "https://files.pythonhosted.org/packages/21/09/817a482f542f7570cbb4554b26e896610c7114f539b1d9e2d2145bf6bef6/ruff-0.16.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:33a3dfac8c35f81498dea9181bccc2f4c4bc8f1521a1dd9406e77643e0f0fb09", size = 11063329, upload-time = "2026-07-23T19:11:19.173Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/23/9403c180ca1cb9b1f7335f5c3e5305c09d49ea5b345196682a36028bde4a/ruff-0.16.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a5237a0bda500d30d81b8e07a6973a5cbc772864cbf746ae2f4e8a2e01c9f4ed", size = 11489751, upload-time = "2026-07-23T19:11:21.74Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/1d/1b2ef7bcde851c78d7f17f1cca13fd6dc695fc4b3d6197941e72cae5b132/ruff-0.16.0-py3-none-win32.whl", hash = "sha256:7fab76fa065c873f41ff744347c6e77bcc3dfec4bcc754dc26b63d23c0f7f5fb", size = 10785885, upload-time = "2026-07-23T19:11:23.947Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/a3/d5e4ef7a56be3f928ffb90b94c25ba7d3cb9c7fe0736aeaaedf361770712/ruff-0.16.0-py3-none-win_amd64.whl", hash = "sha256:429c117f022bf481fabd9d551e7a3952b24c65e6ef44337ea09d90bebef14472", size = 11923141, upload-time = "2026-07-23T19:11:26.409Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/9a/8415f2657cbe200f41a4531ccededf135505a92d4a012229121f885b26f9/ruff-0.16.0-py3-none-win_arm64.whl", hash = "sha256:14296fedcd2705c77ab8235439278bbb38f285cf7da5528b00b3e330c3d4872d", size = 11273407, upload-time = "2026-07-23T19:11:28.705Z" },
 ]
 [[package]]
 name = "scraper-rust"
-version = "0.6.0"
+version = "0.7.0"
 source = { editable = "." }
 [package.optional-dependencies]
@@ -239,9 +239,9 @@ wheels = [
 [[package]]
 name = "typing-extensions"
-version = "4.15.0"
+version = "4.16.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/cc/6253133b5bb138fc3306cebfbda2c520f545d36b5be2c7255cc528bb45d6/typing_extensions-4.16.0.tar.gz", hash = "sha256:dc983d19a509c94dba722ee6abd33940f7c05a89e243c47e907eb4db6f1a43e5", size = 113555, upload-time = "2026-07-02T08:40:05.92Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" },
+    { url = "https://files.pythonhosted.org/packages/49/d3/b8441a820a491ddfc024b0b0cf0393375b75ea13866d9c66727e54c2fc80/typing_extensions-4.16.0-py3-none-any.whl", hash = "sha256:481caa481374e813c1b176ada14e97f1f67a4539ce9cfeb3f350d78d6370c2e8", size = 45571, upload-time = "2026-07-02T08:40:04.659Z" },
 ]