Publish curated VacatureRadar source snapshot

apps/sources/management/commands/import_job_fixture.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+import hashlib
+from datetime import timedelta
+from pathlib import Path
+from urllib.parse import urlsplit
+
+from django.conf import settings
+from django.core.management.base import BaseCommand, CommandError
+from django.utils import timezone
+
+from apps.jobs.services.pipeline import process_raw_document
+from apps.sources.models import RawDocument, Source, SourceRun
+
+
+class Command(BaseCommand):
+    help = "Importeert een lokale HTML/XML-fixture via dezelfde pipeline als een live bron."
+
+    def add_arguments(self, parser):
+        parser.add_argument("path")
+        parser.add_argument("--url", required=True)
+        parser.add_argument("--source-name", default="Lokale fixture")
+        parser.add_argument("--source-type", default=Source.Type.EMPLOYER)
+
+    def handle(self, *args, **options):
+        path = Path(options["path"]).resolve()
+        if not path.is_file():
+            raise CommandError(f"Bestand bestaat niet: {path}")
+        content = path.read_text(encoding="utf-8")
+        hostname = (urlsplit(options["url"]).hostname or "").lower()
+        if not hostname:
+            raise CommandError("--url bevat geen geldig domein")
+        source, _ = Source.objects.get_or_create(
+            base_url=options["url"],
+            source_type=options["source_type"],
+            defaults={
+                "domain": hostname,
+                "name": options["source_name"],
+                "status": Source.Status.ACTIVE,
+                "policy": Source.Policy.ALLOW,
+                "parser_key": "auto",
+            },
+        )
+        run = SourceRun.objects.create(source=source)
+        suffix = path.suffix.lower()
+        kind = RawDocument.Kind.XML if suffix in {".xml", ".rss"} else RawDocument.Kind.HTML
+        document = RawDocument.objects.create(
+            source=source,
+            source_run=run,
+            url=options["url"],
+            final_url=options["url"],
+            kind=kind,
+            content_type="application/xml" if kind == RawDocument.Kind.XML else "text/html",
+            content_hash=hashlib.sha256(content.encode()).hexdigest(),
+            body_text=content,
+            byte_length=len(content.encode()),
+            retain_until=timezone.now() + timedelta(days=settings.RAW_DOCUMENT_RETENTION_DAYS),
+        )
+        metrics = process_raw_document(document)
+        run.finish(
+            SourceRun.Status.SUCCESS,
+            extracted_count=int(metrics["extracted"]),
+            created_count=int(metrics["created"]),
+            updated_count=int(metrics["updated"]),
+            duplicate_count=int(metrics["duplicates"]),
+            metrics=metrics,
+        )
+        self.stdout.write(self.style.SUCCESS(str(metrics)))