fix(tests): skip HTML extractor tests when trafilatura not installed

Add pytest.importorskip("trafilatura") to HTML extractor test modules
to skip tests gracefully when the optional trafilatura dependency is
not installed. This fixes CI failures in the base test matrix that
doesn't include the html extras.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

tests/test_evals/test_html_extraction_eval.py

@@ -14,6 +14,9 @@ import os
 
 import pytest
 
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
 from headroom.evals.html_extraction import (
     HTMLEvalCase,
     HTMLEvalResult,

tests/test_evals/test_html_oss_benchmarks.py

@@ -21,6 +21,9 @@ import os
 
 import pytest
 
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
 
 class TestExtractionBenchmark:
     """Tests using Scrapinghub Article Extraction Benchmark.

tests/test_transforms/test_html_extractor.py

@@ -7,6 +7,9 @@ and removes structural noise.
 
 import pytest
 
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
 from headroom.transforms.html_extractor import (
     HTMLExtractionResult,
     HTMLExtractor,