feat: add employee news links parsing and storage

tests/test_crawler.py

@@ -1,7 +1,16 @@
 import gzip
 from datetime import datetime, timezone
 
-from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee, EmployeePublication, EmployeeSnapshot, ParseResourceCache
+from app.models import (
+    CrawlError,
+    CrawlRun,
+    CrawlRunEmployeeChange,
+    Employee,
+    EmployeeNewsLink,
+    EmployeePublication,
+    EmployeeSnapshot,
+    ParseResourceCache,
+)
 from app.services.crawler import _checksum, _mark_dismissed, _upsert_employee
 from app.services.resource_cache import ResourceCache
 
@@ -253,6 +262,44 @@ def test_upsert_employee_records_publication_errors_without_failing_employee(mon
     assert "публикации" in error.message.lower()
 
 
+def test_upsert_employee_saves_news_links_and_reuses_existing_rows(db_session):
+    first_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    second_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    db_session.add_all([first_run, second_run])
+    db_session.commit()
+
+    employee, _ = _upsert_employee(db_session, first_run, _parsed_employee_with_news("news-person"))
+    db_session.commit()
+    _upsert_employee(db_session, second_run, _parsed_employee_with_news("news-person"))
+    db_session.commit()
+
+    news_links = db_session.query(EmployeeNewsLink).filter_by(employee_id=employee.id).all()
+    assert len(news_links) == 1
+    assert news_links[0].title == "News Title"
+    assert news_links[0].url == "https://www.hse.ru/news/1.html"
+    assert news_links[0].published_year == 2026
+
+
+def test_upsert_employee_records_news_errors_without_failing_employee(monkeypatch, db_session):
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    db_session.add(run)
+    db_session.commit()
+
+    def broken_sync(*_args, **_kwargs):
+        raise RuntimeError("boom")
+
+    monkeypatch.setattr("app.services.crawler._sync_employee_news_links", broken_sync)
+
+    employee, changed = _upsert_employee(db_session, run, _parsed_employee_with_news("news-error-safe"))
+    db_session.commit()
+
+    assert changed is True
+    assert employee.full_name == "Same Person"
+    assert db_session.query(Employee).filter_by(profile_key="staff:news-error-safe").one()
+    error = db_session.query(CrawlError).one()
+    assert "новости" in error.message.lower()
+
+
 def test_checksum_changes_when_widget_data_changes():
     base = _parsed_employee("widgets")
     changed = _parsed_employee("widgets")
@@ -314,3 +361,23 @@ def _parsed_employee_with_publication(profile_id: str) -> dict:
         }
     ]
     return parsed
+
+
+def _parsed_employee_with_news(profile_id: str) -> dict:
+    parsed = _parsed_employee(profile_id)
+    parsed["sections"] = [
+        {
+            "type": "news",
+            "news_links": [
+                {
+                    "title": "News Title",
+                    "url": "https://www.hse.ru/news/1.html",
+                    "summary": "News summary",
+                    "published_at": "2026-04-28T00:00:00+00:00",
+                    "published_year": 2026,
+                    "raw_data": {"title": "News Title", "url": "https://www.hse.ru/news/1.html"},
+                }
+            ],
+        }
+    ]
+    return parsed