feat: add active field to agency YAML configuration

dags/scrape_agencies.py

@@ -19,10 +19,29 @@
 
 
 def _load_agencies_config() -> dict:
-    """Carrega config de agências do YAML."""
+    """Carrega config de agências ativas do YAML.
+
+    Suporta formato dicionário com campos:
+    - url: str (obrigatório)
+    - active: bool (opcional, default: True)
+    - disabled_reason: str (opcional)
+    - disabled_date: str (opcional)
+
+    Returns:
+        dict: Mapeamento {agency_key: url} apenas para agências ativas
+    """
     config_path = os.path.join(os.path.dirname(__file__), "config", "site_urls.yaml")
     with open(config_path) as f:
-        return yaml.safe_load(f)["agencies"]
+        agencies = yaml.safe_load(f)["agencies"]
+
+    # Filtrar apenas agências ativas e extrair URLs
+    active_agencies = {}
+    for key, data in agencies.items():
+        is_active = data.get("active", True)
+        if is_active:
+            active_agencies[key] = data.get("url")
+
+    return active_agencies
 
 
 def create_scraper_dag(agency_key: str, agency_url: str):

src/govbr_scraper/api.py

@@ -32,6 +32,7 @@ class ScrapeAgenciesRequest(BaseModel):
 class ScrapeEBCRequest(BaseModel):
     start_date: str
     end_date: str | None = None
+    agencies: list[str] | None = None
     allow_update: bool = False
     sequential: bool = True
 
@@ -108,7 +109,7 @@ def scrape_ebc(req: ScrapeEBCRequest):
     from govbr_scraper.scrapers.ebc_scrape_manager import EBCScrapeManager
 
     end = req.end_date or req.start_date
-    logger.info(f"Scraping EBC from {req.start_date} to {end}")
+    logger.info(f"Scraping EBC agencies: {req.agencies or 'ALL'} from {req.start_date} to {end}")
 
     try:
         storage = StorageAdapter()
@@ -118,15 +119,19 @@ def scrape_ebc(req: ScrapeEBCRequest):
             max_date=end,
             sequential=req.sequential,
             allow_update=req.allow_update,
+            agencies=req.agencies,
         )
     except Exception as e:
         logger.error(f"EBC scraping failed: {e}")
         raise HTTPException(status_code=500, detail=str(e))
 
     errors = [AgencyError(**e) for e in metrics.get("errors", [])]
-    if errors:
+    if errors and not metrics["agencies_processed"]:
         status = "failed"
         message = f"EBC scraping failed: {errors[0].error}"
+    elif errors:
+        status = "partial"
+        message = f"Completed with {len(errors)} error(s)"
     else:
         status = "completed"
         message = "EBC scraping completed"
@@ -137,7 +142,7 @@ def scrape_ebc(req: ScrapeEBCRequest):
         end_date=end,
         articles_scraped=metrics["articles_scraped"],
         articles_saved=metrics["articles_saved"],
-        agencies_processed=["ebc"] if not errors else [],
+        agencies_processed=metrics["agencies_processed"],
         errors=errors,
         message=message,
     )

src/govbr_scraper/scrapers/config/ebc_urls.yaml

@@ -0,0 +1,14 @@
+agencies:
+  memoria-ebc:
+    url: https://memoria.ebc.com.br/noticias
+    active: false
+    disabled_reason: "Site fora do ar (502 Bad Gateway) - issue #50"
+    disabled_date: "2026-02-12"
+
+  agencia_brasil:
+    url: https://agenciabrasil.ebc.com.br/ultimas
+    active: true
+
+  tvbrasil:
+    url: https://tvbrasil.ebc.com.br/ultimas
+    active: true