feat(media-routing): implement 007 media article routing, runtime architecture diagram and update graphify knowledge graph

tests/tools/test_extract_article_contents.py

@@ -18,6 +18,7 @@ from scripts.extract_article_contents import (
     ExtractedArticle,
     ExtractionBatchReport,
     InputArticle,
+    MediaClassification,
     NewspaperData,
     NewspaperExtractor,
     ReadabilityData,
@@ -321,13 +322,17 @@ def test_e2e_live_article_extraction(tmp_path: Path):
 
     out_file = tmp_path / "e2e_live_extracted.json"
 
-    # Executa o batch real com limite de 1 notícia
-    report = process_batch(
-        input_path=live_input_file,
-        output_path=out_file,
-        limit=1,
-        silent=True,
-    )
+    # Executa o batch real com limite de 1 notícia simulando classificação textual
+    with patch(
+        "scripts.extract_article_contents.classify_media_content",
+        return_value=(MediaClassification(content_type="text", media_type=None), None),
+    ):
+        report = process_batch(
+            input_path=live_input_file,
+            output_path=out_file,
+            limit=1,
+            silent=True,
+        )
 
     assert report.total_articles == 1
     assert report.successful_articles == 1
@@ -364,9 +369,14 @@ def test_e2e_cli_live_execution(tmp_path: Path):
         pytest.skip("Arquivo out/river_plate.json não encontrado para teste E2E.")
 
     out_file = tmp_path / "e2e_cli_live.json"
-    exit_code = main(["-i", str(live_input_file), "-o", str(out_file), "--limit", "1", "-s"])
+    with patch(
+        "scripts.extract_article_contents.classify_media_content",
+        return_value=(MediaClassification(content_type="text", media_type=None), None),
+    ):
+        exit_code = main(["-i", str(live_input_file), "-o", str(out_file), "--limit", "1", "-s"])
 
     assert exit_code == 0
     assert out_file.exists()
     data = json.loads(out_file.read_text(encoding="utf-8"))
     assert data["successful_articles"] == 1
+