fix: enrich HSE profile parsing with publications and theses

Reviewed-on: #9

.gitignore

@@ -4,6 +4,7 @@ __pycache__/
 *.py[cod]
 *.db
 .pytest_cache/
+pytest-cache-files-*/
 .coverage
 htmlcov/
 postgres_data/

README.md

@@ -110,4 +110,4 @@ docker compose exec postgres pg_dump -U miem miem_workers > backup.sql
 docker compose down
 ```
 
-Версия сервиса: `0.2.1`. Админка всегда показывает версии backend и frontend в footer.
+Версия сервиса: `0.2.8`. Админка всегда показывает версии backend и frontend в footer.

app/admin.py

@@ -1,14 +1,14 @@
 from fastapi import APIRouter, BackgroundTasks, Depends, Form, Request
 from fastapi.responses import HTMLResponse, RedirectResponse
 from fastapi.templating import Jinja2Templates
-from sqlalchemy import desc, func, or_, select
+from sqlalchemy import desc, func, select
 from sqlalchemy.orm import Session
 
 from app.config import Settings, get_settings
 from app.db import SessionLocal, get_db
 from app.models import CrawlError, CrawlRun, Employee
 from app.security import SESSION_COOKIE, require_admin, sign_session, verify_admin
-from app.services.admin_data import list_employees_page, run_payload, stats_payload
+from app.services.admin_data import employee_detail_payload, format_admin_datetime, list_employees_page, run_payload, stats_payload
 from app.services.crawl_control import get_running_run, run_crawl_if_idle
 from app.version import BACKEND_VERSION, FRONTEND_VERSION
 
@@ -22,8 +22,9 @@ def dashboard(request: Request, db: Session = Depends(get_db), settings: Setting
     counts = stats_payload(db)
     counts["runs"] = db.scalar(select(func.count()).select_from(CrawlRun)) or 0
     counts["errors"] = db.scalar(select(func.count()).select_from(CrawlError)) or 0
-    runs = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(10)).all()
-    return _render(request, "dashboard.html", {"counts": counts, "runs": runs, "latest_run": run_payload(runs[0]) if runs else None})
+    run_models = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(10)).all()
+    runs = [run_payload(run) for run in run_models]
+    return _render(request, "dashboard.html", {"counts": counts, "runs": runs, "latest_run": runs[0] if runs else None})
 
 
 @router.get("/login", response_class=HTMLResponse)
@@ -57,18 +58,10 @@ def employees(
     request: Request,
     status: str | None = None,
     q: str | None = None,
-    db: Session = Depends(get_db),
     settings: Settings = Depends(get_settings),
 ):
     require_admin(request, settings)
-    stmt = select(Employee)
-    if status:
-        stmt = stmt.where(Employee.status == status)
-    if q:
-        pattern = f"%{q}%"
-        stmt = stmt.where(or_(Employee.full_name.ilike(pattern), Employee.canonical_url.ilike(pattern)))
-    items = db.scalars(stmt.order_by(Employee.full_name).limit(200)).all()
-    return _render(request, "employees.html", {"employees": items, "status": status or "", "q": q or ""})
+    return RedirectResponse("/admin/directory", status_code=303)
 
 
 @router.get("/directory", response_class=HTMLResponse)
@@ -115,7 +108,7 @@ def directory(
                 "has_email": has_email or "",
                 "sort": sort,
                 "direction": direction,
-                "limit": limit,
+                "limit": page["limit"],
                 "offset": offset,
             },
         },
@@ -133,14 +126,26 @@ def employee_detail(
     employee = db.get(Employee, employee_id)
     if not employee:
         return RedirectResponse("/admin/employees", status_code=303)
-    snapshots = sorted(employee.snapshots, key=lambda item: item.captured_at, reverse=True)[:20]
-    return _render(request, "employee_detail.html", {"employee": employee, "snapshots": snapshots})
+    snapshots = [
+        {
+            "captured_display": format_admin_datetime(snapshot.captured_at),
+            "checksum": snapshot.checksum,
+            "parser_version": snapshot.parser_version,
+        }
+        for snapshot in sorted(employee.snapshots, key=lambda item: item.captured_at, reverse=True)[:20]
+    ]
+    return _render(
+        request,
+        "employee_detail.html",
+        {"employee": employee, "employee_view": employee_detail_payload(employee), "snapshots": snapshots},
+    )
 
 
 @router.get("/runs", response_class=HTMLResponse)
 def runs(request: Request, db: Session = Depends(get_db), settings: Settings = Depends(get_settings)):
     require_admin(request, settings)
-    items = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(50)).all()
+    run_models = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(50)).all()
+    items = [run_payload(run) for run in run_models]
     errors = db.scalars(select(CrawlError).order_by(desc(CrawlError.created_at)).limit(50)).all()
     return _render(request, "runs.html", {"runs": items, "errors": errors})
 

app/config.py

@@ -1,5 +1,5 @@
 from functools import lru_cache
-from pydantic import Field
+from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
@@ -19,6 +19,13 @@ class Settings(BaseSettings):
     session_secret: str = Field(default="dev-session-secret", min_length=8)
     mcp_token: str = "dev-mcp-token"
 
+    @field_validator("crawl_limit", mode="before")
+    @classmethod
+    def empty_crawl_limit_as_none(cls, value):
+        if value == "":
+            return None
+        return value
+
 
 @lru_cache
 def get_settings() -> Settings:

app/parser/profile.py

@@ -164,6 +164,7 @@ def parse_person_profile(
     header = extract_person_header(soup, normalized_url)
     tabs = extract_person_tabs(soup, normalized_url)
     sections = extract_sections(soup, normalized_url)
+    sections = enrich_sections_from_hse_widgets(session, soup, normalized_url, headers, timeout, sections)
     internal_links = [tab["href"] for tab in tabs if tab.get("href")]
 
     return {
@@ -183,6 +184,25 @@ def parse_person_profile(
     }
 
 
+def enrich_sections_from_hse_widgets(
+    session: Session,
+    soup: BeautifulSoup,
+    source_url: str,
+    headers: dict[str, str],
+    timeout: int,
+    sections: list[dict],
+) -> list[dict]:
+    enriched = list(sections)
+    publications = _load_widget_publications(session, soup, headers, timeout)
+    if publications:
+        enriched = _upsert_publications_section(enriched, publications)
+
+    theses = _load_widget_graduation_theses(session, soup, source_url, headers, timeout)
+    if theses:
+        enriched = _upsert_graduation_theses_section(enriched, theses)
+    return enriched
+
+
 def _render_with_playwright(source_url: str, fallback_html: str) -> str:
     try:
         from playwright.sync_api import sync_playwright
@@ -206,6 +226,89 @@ def _render_with_playwright(source_url: str, fallback_html: str) -> str:
         return fallback_html
 
 
+def _load_widget_publications(session: Session, soup: BeautifulSoup, headers: dict[str, str], timeout: int) -> list[dict]:
+    script = soup.select_one('script[data-widget-name="AuthorSearch"][data-author]')
+    if not script:
+        return []
+    author_id = normalize_ws(script.get("data-author"))
+    if not author_id:
+        return []
+
+    publications = []
+    page_id = 1
+    per_page = 100
+    while page_id <= 20:
+        payload = {
+            "type": "ANY",
+            "filterParams": (
+                f'"acceptLanguage":"ru"|"fullTextPublicEnabled": 1|'
+                f'"pubsAuthor": {author_id}|"widgetName": "AuthorSearch"'
+            ),
+            "paginationParams": {
+                "publsSort": ["TITLE_ASC"],
+                "publsCount": per_page,
+                "pageId": page_id,
+            },
+        }
+        try:
+            response = session.post(
+                "https://publications.hse.ru/api/searchPubs",
+                json=payload,
+                headers=headers,
+                timeout=timeout,
+            )
+            response.raise_for_status()
+            data = response.json()
+        except Exception:
+            return publications
+
+        result = data.get("result") if isinstance(data, dict) else {}
+        items = result.get("items") if isinstance(result, dict) else []
+        if not isinstance(items, list) or not items:
+            break
+        publications.extend(_normalize_publication_item(item) for item in items if isinstance(item, dict))
+
+        total = int(result.get("total") or 0)
+        if not result.get("more") and len(publications) >= total:
+            break
+        page_id += 1
+    return _dedupe_publications(publications)
+
+
+def _load_widget_graduation_theses(
+    session: Session,
+    soup: BeautifulSoup,
+    source_url: str,
+    headers: dict[str, str],
+    timeout: int,
+) -> list[dict]:
+    script = soup.select_one('script[src*="/n/stat/vkr/app.js"][data-person-id]')
+    if not script:
+        return []
+    person_id = normalize_ws(script.get("data-person-id"))
+    api_url = normalize_ws(script.get("data-api-url")) or "/n/vkr/api/"
+    if not person_id:
+        return []
+
+    request_headers = {**headers, "x-portal-language": "ru"}
+    try:
+        response = session.get(
+            urljoin(source_url, api_url),
+            params={"supervisorId": person_id},
+            headers=request_headers,
+            timeout=timeout,
+        )
+        response.raise_for_status()
+        data = response.json()
+    except Exception:
+        return []
+
+    items = data.get("data") if isinstance(data, dict) else []
+    if not isinstance(items, list):
+        return []
+    return [_normalize_vkr_item(item, source_url) for item in items if isinstance(item, dict)]
+
+
 def _collect_between_h2(start_h2: Tag) -> list[Tag | NavigableString | str]:
     nodes = []
     for sibling in start_h2.next_siblings:
@@ -353,6 +456,122 @@ def _parse_vkr_items(nodes: list) -> list[str]:
     return [item for item in dict.fromkeys(items) if item]
 
 
+def _normalize_publication_item(item: dict) -> dict:
+    publication_id = str(item.get("id") or "").strip()
+    title = _html_to_text(item.get("title"))
+    year = item.get("year")
+    publication_type = str(item.get("type") or "").strip() or None
+    description = item.get("description") if isinstance(item.get("description"), dict) else {}
+    short_description = _localized_value(description.get("short")) or _localized_value(description.get("shortLeft"))
+    text = normalize_ws(" ".join(part for part in [title, str(year or ""), short_description] if part))
+    return {
+        "id": publication_id or None,
+        "title": title or publication_id,
+        "year": year,
+        "type": publication_type,
+        "url": f"https://publications.hse.ru/view/{publication_id}" if publication_id else None,
+        "text": text or title or publication_id,
+    }
+
+
+def _normalize_vkr_item(item: dict, source_url: str) -> dict:
+    thesis_id = item.get("id")
+    program = item.get("learnProgram") if isinstance(item.get("learnProgram"), dict) else {}
+    org_unit = item.get("orgUnit") if isinstance(item.get("orgUnit"), dict) else {}
+    supervisors = []
+    for supervisor in item.get("supervisors") or []:
+        if not isinstance(supervisor, dict):
+            continue
+        name = normalize_ws(supervisor.get("name"))
+        url = normalize_ws(supervisor.get("url"))
+        if name or url:
+            supervisors.append({"name": name or url, "url": url or None})
+    return {
+        "id": thesis_id,
+        "student": normalize_ws(item.get("student")),
+        "title": normalize_ws(item.get("title")),
+        "defense_year": item.get("year"),
+        "level": normalize_ws(item.get("level")),
+        "rating": item.get("rating"),
+        "project_url": urljoin(source_url, f"/edu/vkr/{thesis_id}") if thesis_id else None,
+        "program": normalize_ws(program.get("title")),
+        "program_url": urljoin(source_url, program.get("url")) if program.get("url") else None,
+        "org_unit": normalize_ws(org_unit.get("title")),
+        "org_unit_url": urljoin(source_url, org_unit.get("url")) if org_unit.get("url") else None,
+        "supervisors": supervisors,
+        "text": normalize_ws(" ".join(str(part) for part in [item.get("student"), item.get("title"), item.get("year")] if part)),
+    }
+
+
+def _upsert_publications_section(sections: list[dict], publications: list[dict]) -> list[dict]:
+    merged = []
+    inserted = False
+    for section in sections:
+        if section.get("type") != "publications":
+            merged.append(section)
+            continue
+        existing = section.get("publications") or []
+        section = {
+            **section,
+            "publications_count": max(section.get("publications_count") or 0, len(publications)),
+            "publications": _dedupe_publications([*existing, *publications]),
+        }
+        section["items"] = [item["text"] for item in section["publications"] if item.get("text")]
+        merged.append(section)
+        inserted = True
+    if not inserted:
+        merged.append(
+            {
+                "title": "Публикации и исследования",
+                "slug": "publikacii_i_issledovaniya",
+                "type": "publications",
+                "raw_text": "",
+                "paragraphs": [],
+                "items": [item["text"] for item in publications if item.get("text")],
+                "links": [],
+                "publications_count": len(publications),
+                "publications": publications,
+            }
+        )
+    return merged
+
+
+def _upsert_graduation_theses_section(sections: list[dict], theses: list[dict]) -> list[dict]:
+    section = {
+        "title": "Выпускные квалификационные работы студентов НИУ ВШЭ",
+        "slug": "vypusknye_kvalifikacionnye_raboty_studentov_niu_vshe",
+        "type": "graduation_theses",
+        "raw_text": "",
+        "paragraphs": [],
+        "items": [item["text"] for item in theses if item.get("text")],
+        "links": [{"text": item["title"], "url": item["project_url"]} for item in theses if item.get("title") and item.get("project_url")],
+        "theses_count": len(theses),
+        "theses": theses,
+    }
+    return [item for item in sections if item.get("type") != "graduation_theses"] + [section]
+
+
+def _dedupe_publications(items: list[dict]) -> list[dict]:
+    seen = set()
+    unique = []
+    for item in items:
+        key = item.get("id") or item.get("url") or item.get("title")
+        if key and key not in seen:
+            seen.add(key)
+            unique.append(item)
+    return unique
+
+
+def _html_to_text(value: object) -> str:
+    return normalize_ws(BeautifulSoup(str(value or ""), "html.parser").get_text(" ", strip=True))
+
+
+def _localized_value(value: object) -> str:
+    if isinstance(value, dict):
+        return normalize_ws(value.get("ru") or value.get("publ") or value.get("en"))
+    return normalize_ws(str(value or ""))
+
+
 def _slugify(value: str) -> str:
     cleaned = re.sub(r"[^\w\s-]", "", value.lower(), flags=re.UNICODE)
     return re.sub(r"[-\s]+", "_", cleaned).strip("_") or "section"

app/services/admin_data.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from datetime import date, datetime, time
 from math import ceil
 from typing import Any
+from zoneinfo import ZoneInfo
 
 from sqlalchemy import Select, Text, and_, desc, func, or_, select
 from sqlalchemy.orm import Session
@@ -20,18 +21,20 @@ EMPLOYEE_SORTS = {
 
 
 def employee_display_payload(employee: Employee) -> dict[str, Any]:
-    data = employee.current_data or {}
-    contacts = data.get("contacts") or {}
-    sections = data.get("sections") or []
-    emails = contacts.get("emails") or []
-    phones = contacts.get("phones") or []
+    data = _as_dict(employee.current_data)
+    contacts = _as_dict(data.get("contacts"))
+    sections = _as_list(data.get("sections"))
+    positions = _clean_list(data.get("positions"))
+    emails = _clean_list(contacts.get("emails"))
+    phones = _clean_list(contacts.get("phones"))
     return {
         "id": employee.id,
         "full_name": employee.full_name,
         "status": employee.status,
+        "status_display": _employee_status_display(employee.status),
         "canonical_url": employee.canonical_url,
-        "positions": data.get("positions") or [],
-        "positions_text": "; ".join(data.get("positions") or []),
+        "positions": positions,
+        "positions_text": "; ".join(positions),
         "hse_start_year": data.get("hse_start_year"),
         "emails": emails,
         "email_text": ", ".join(emails),
@@ -43,6 +46,28 @@ def employee_display_payload(employee: Employee) -> dict[str, Any]:
         "first_seen_at": employee.first_seen_at.isoformat() if employee.first_seen_at else None,
         "last_seen_at": employee.last_seen_at.isoformat() if employee.last_seen_at else None,
         "dismissed_at": employee.dismissed_at.isoformat() if employee.dismissed_at else None,
+        "first_seen_display": format_admin_datetime(employee.first_seen_at),
+        "last_seen_display": format_admin_datetime(employee.last_seen_at),
+        "dismissed_display": format_admin_datetime(employee.dismissed_at),
+    }
+
+
+def employee_detail_payload(employee: Employee) -> dict[str, Any]:
+    data = _as_dict(employee.current_data)
+    contacts = _as_dict(data.get("contacts"))
+    return {
+        **employee_display_payload(employee),
+        "profile_type": employee.profile_type or data.get("profile_type"),
+        "profile_id": employee.profile_id or data.get("profile_id"),
+        "parser_version": employee.parser_version or data.get("parser_version"),
+        "contacts": {
+            "emails": _clean_list(contacts.get("emails")),
+            "phones": _clean_list(contacts.get("phones")),
+            "address": contacts.get("address"),
+            "contact_items": _normalize_contact_items(contacts.get("items")),
+        },
+        "external_ids": _normalize_external_ids(data.get("external_ids")),
+        "sections": [_normalize_section(section) for section in _as_list(data.get("sections"))],
     }
 
 
@@ -87,7 +112,7 @@ def list_employees_page(
     limit: int = 50,
     offset: int = 0,
 ) -> dict[str, Any]:
-    limit = max(1, min(limit, 200))
+    limit = limit if limit in {25, 50, 100} else 50
     offset = max(0, offset)
     base_stmt = build_employee_query(
         status=status,
@@ -101,7 +126,7 @@ def list_employees_page(
     order = desc(sort_column) if direction == "desc" else sort_column
     employees = db.scalars(base_stmt.order_by(order).limit(limit).offset(offset)).all()
     return {
-        "items": [employee_display_payload(employee) for employee in employees],
+        "employees": [employee_display_payload(employee) for employee in employees],
         "total": total,
         "limit": limit,
         "offset": offset,
@@ -134,8 +159,11 @@ def run_payload(run: CrawlRun | None) -> dict[str, Any] | None:
         "id": run.id,
         "source_url": run.source_url,
         "status": run.status,
+        "status_display": _run_status_display(run.status),
         "started_at": run.started_at.isoformat() if run.started_at else None,
         "finished_at": run.finished_at.isoformat() if run.finished_at else None,
+        "started_display": format_admin_datetime(run.started_at),
+        "finished_display": format_admin_datetime(run.finished_at),
         "found_count": run.found_count,
         "parsed_count": run.parsed_count,
         "new_count": run.new_count,
@@ -147,6 +175,31 @@ def run_payload(run: CrawlRun | None) -> dict[str, Any] | None:
     }
 
 
+def format_admin_datetime(value: Any) -> str:
+    if not value:
+        return "Не указано"
+    if isinstance(value, str):
+        try:
+            value = datetime.fromisoformat(value.replace("Z", "+00:00"))
+        except ValueError:
+            return value
+    if not isinstance(value, datetime):
+        return str(value)
+    if value.tzinfo:
+        value = value.astimezone(ZoneInfo("Europe/Moscow"))
+    return value.strftime("%d.%m.%Y %H:%M")
+
+
+def _employee_status_display(status: str | None) -> str:
+    labels = {"active": "Работает", "dismissed": "Уволен"}
+    return labels.get(status or "", status or "Не указано")
+
+
+def _run_status_display(status: str | None) -> str:
+    labels = {"running": "Выполняется", "completed": "Завершен", "failed": "Ошибка"}
+    return labels.get(status or "", status or "Не указано")
+
+
 def _count_section_items(sections: list[dict[str, Any]], section_type: str) -> int:
     total = 0
     for section in sections:
@@ -157,3 +210,187 @@ def _count_section_items(sections: list[dict[str, Any]], section_type: str) -> i
         elif section_type == "courses_by_year":
             total += len(section.get("courses") or [])
     return total
+
+
+def _clean_list(values: Any) -> list[str]:
+    if values is None:
+        return []
+    if not isinstance(values, list):
+        values = [values]
+    return [str(value).strip() for value in values if str(value or "").strip()]
+
+
+def _as_dict(value: Any) -> dict[str, Any]:
+    return value if isinstance(value, dict) else {}
+
+
+def _as_list(value: Any) -> list[Any]:
+    if value is None:
+        return []
+    return value if isinstance(value, list) else [value]
+
+
+def _normalize_contact_items(items: Any) -> list[str]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if isinstance(item, dict):
+            value = item.get("raw") or item.get("value") or item.get("text")
+        else:
+            value = item
+        value = str(value or "").strip()
+        if value:
+            normalized.append(value)
+    return normalized
+
+
+def _normalize_external_ids(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        system = str(item.get("system") or "").strip()
+        value = str(item.get("value") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if system or value or url:
+            normalized.append({"system": system or "ID", "value": value or url, "url": url or None})
+    return normalized
+
+
+def _normalize_section(section: Any) -> dict[str, Any]:
+    if not isinstance(section, dict):
+        return {"title": "Раздел", "type": "generic", "paragraphs": [str(section)], "items": [], "links": []}
+
+    section_type = section.get("type") or "generic"
+    paragraphs = _clean_list(section.get("paragraphs"))
+    items = _clean_list(section.get("items"))
+    raw_text = str(section.get("raw_text") or "").strip()
+    if not paragraphs and not items and raw_text:
+        paragraphs = [raw_text]
+
+    return {
+        "title": section.get("title") or "Раздел",
+        "type": section_type,
+        "raw_text": raw_text,
+        "paragraphs": paragraphs,
+        "list_items": items,
+        "links": _normalize_links(section.get("links")),
+        "year_entries": _normalize_year_entries(section.get("year_entries")),
+        "publications": _normalize_publications(section.get("publications")),
+        "publications_count": section.get("publications_count"),
+        "theses": _normalize_theses(section.get("theses")),
+        "theses_count": section.get("theses_count"),
+        "academic_year": section.get("academic_year"),
+        "courses": _normalize_courses(section.get("courses")),
+        "table": _normalize_table(section.get("table")),
+    }
+
+
+def _normalize_links(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        text = str(item.get("text") or item.get("url") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if text and url:
+            normalized.append({"text": text, "url": url})
+    return normalized
+
+
+def _normalize_year_entries(items: Any) -> list[dict[str, Any]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        text = str(item.get("text") or "").strip()
+        if text:
+            normalized.append({"year": item.get("year"), "text": text, "links": _normalize_links(item.get("links"))})
+    return normalized
+
+
+def _normalize_publications(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            text = str(item or "").strip()
+            if text:
+                normalized.append({"title": text, "text": text, "url": None})
+            continue
+        title = str(item.get("title") or "").strip()
+        text = str(item.get("text") or title).strip()
+        url = str(item.get("url") or "").strip()
+        if title or text:
+            normalized.append({"title": title or text, "text": text or title, "url": url or None})
+    return normalized
+
+
+def _normalize_courses(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            title = str(item or "").strip()
+            if title:
+                normalized.append({"title": title, "url": None})
+            continue
+        title = str(item.get("title") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if title or url:
+            normalized.append({"title": title or url, "url": url or None})
+    return normalized
+
+
+def _normalize_theses(items: Any) -> list[dict[str, Any]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        title = str(item.get("title") or "").strip()
+        student = str(item.get("student") or "").strip()
+        if not title and not student:
+            continue
+        normalized.append(
+            {
+                "id": item.get("id"),
+                "student": student,
+                "title": title,
+                "defense_year": item.get("defense_year") or item.get("year"),
+                "level": str(item.get("level") or "").strip(),
+                "rating": item.get("rating"),
+                "project_url": str(item.get("project_url") or "").strip() or None,
+                "program": str(item.get("program") or "").strip(),
+                "program_url": str(item.get("program_url") or "").strip() or None,
+                "org_unit": str(item.get("org_unit") or "").strip(),
+                "org_unit_url": str(item.get("org_unit_url") or "").strip() or None,
+            }
+        )
+    return normalized
+
+
+def _normalize_table(table: Any) -> dict[str, Any] | None:
+    if not isinstance(table, dict):
+        return None
+    headers = _clean_list(table.get("headers"))
+    rows = []
+    for row in table.get("rows") or []:
+        if not isinstance(row, dict):
+            continue
+        cells = _clean_list(row.get("cells"))
+        if cells:
+            rows.append({"cells": cells, "link_url": row.get("link_url")})
+    if not headers and not rows:
+        return None
+    return {"headers": headers, "rows": rows}

app/static/admin.css

@@ -152,6 +152,177 @@
   white-space: pre-wrap;
 }
 
+.employee-card {
+  display: grid;
+  gap: 18px;
+}
+
+.employee-card__header {
+  display: flex;
+  align-items: flex-start;
+  justify-content: space-between;
+  gap: 18px;
+  padding: 22px;
+  background: #ffffff;
+  border: 1px solid #d9dee7;
+  border-radius: 8px;
+}
+
+.employee-card__identity {
+  display: grid;
+  gap: 10px;
+}
+
+.employee-card__title {
+  margin: 0;
+  font-size: 24px;
+}
+
+.employee-card__section {
+  padding: 20px;
+  background: #ffffff;
+  border: 1px solid #d9dee7;
+  border-radius: 8px;
+}
+
+.employee-card__meta {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(240px, 1fr));
+  gap: 14px;
+  margin: 0;
+}
+
+.employee-card__meta-item {
+  min-width: 0;
+}
+
+.employee-card__meta-item--wide {
+  grid-column: 1 / -1;
+}
+
+.employee-card__meta-label {
+  margin-bottom: 5px;
+  color: #6b7280;
+  font-size: 12px;
+  font-weight: 700;
+  text-transform: uppercase;
+}
+
+.employee-card__meta-value {
+  margin: 0;
+  color: #1f2937;
+  line-height: 1.45;
+}
+
+.employee-card__list {
+  display: grid;
+  gap: 8px;
+  margin: 0;
+  padding-left: 18px;
+}
+
+.employee-card__list-item {
+  line-height: 1.45;
+}
+
+.employee-card__sections {
+  display: grid;
+  gap: 14px;
+}
+
+.employee-section {
+  padding: 16px;
+  background: #f9fafb;
+  border: 1px solid #e5e7eb;
+  border-radius: 8px;
+}
+
+.employee-section__header {
+  display: flex;
+  align-items: flex-start;
+  justify-content: space-between;
+  gap: 12px;
+  margin-bottom: 12px;
+}
+
+.employee-section__title {
+  margin: 0;
+  font-size: 17px;
+}
+
+.employee-section__type {
+  flex: 0 0 auto;
+  padding: 3px 8px;
+  color: #475569;
+  background: #e2e8f0;
+  border-radius: 999px;
+  font-size: 12px;
+}
+
+.employee-section__note {
+  margin: 0 0 10px;
+  color: #4b5563;
+  font-weight: 700;
+}
+
+.employee-section__text {
+  margin: 0 0 10px;
+  line-height: 1.55;
+}
+
+.employee-section__meta {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 8px 12px;
+  color: #4b5563;
+  font-size: 13px;
+}
+
+.employee-section__meta-item {
+  line-height: 1.4;
+}
+
+.employee-section__table-wrap {
+  overflow-x: auto;
+}
+
+.employee-section__table {
+  width: 100%;
+  border-collapse: collapse;
+  background: #ffffff;
+}
+
+.employee-section__head,
+.employee-section__cell {
+  padding: 10px;
+  border-bottom: 1px solid #e5e7eb;
+  text-align: left;
+  vertical-align: top;
+}
+
+.employee-section__head {
+  color: #374151;
+  background: #f3f4f6;
+  font-size: 13px;
+}
+
+.employee-section__links {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 8px;
+  margin-top: 12px;
+}
+
+.employee-section__link {
+  padding: 5px 9px;
+  color: #0f766e;
+  background: #ccfbf1;
+  border-radius: 999px;
+  font-size: 12px;
+  font-weight: 700;
+  text-decoration: none;
+}
+
 .stats-strip {
   display: grid;
   grid-template-columns: repeat(auto-fit, minmax(220px, 1fr));
@@ -399,7 +570,8 @@
   }
 
   .progress-panel__header,
-  .directory__header {
+  .directory__header,
+  .employee-card__header {
     align-items: stretch;
     flex-direction: column;
   }

app/static/admin.js

@@ -79,7 +79,7 @@
       const errors = document.querySelector("[data-progress-errors]");
       const fill = document.querySelector("[data-progress-fill]");
       const percent = document.querySelector("[data-progress-percent]");
-      if (status) status.textContent = run.status;
+      if (status) status.textContent = run.status_display || run.status;
       if (processed) processed.textContent = run.processed_count;
       if (found) found.textContent = run.found_count;
       if (errors) errors.textContent = run.error_count;

app/templates/base.html

@@ -10,12 +10,11 @@
     <header class="admin__header">
       <h1 class="admin__brand">MIEM Employees</h1>
       <nav class="admin__nav">
-        <a class="admin__link" href="/admin">Dashboard</a>
-        <a class="admin__link" href="/admin/directory">Directory</a>
-        <a class="admin__link" href="/admin/employees">Employees</a>
-        <a class="admin__link" href="/admin/runs">Runs</a>
+        <a class="admin__link" href="/admin">Обзор</a>
+        <a class="admin__link" href="/admin/directory">Сотрудники</a>
+        <a class="admin__link" href="/admin/runs">Запуски</a>
         <form method="post" action="/admin/logout">
-          <button class="button button--ghost" type="submit">Logout</button>
+          <button class="button button--ghost" type="submit">Выйти</button>
         </form>
       </nav>
     </header>

app/templates/dashboard.html

@@ -1,43 +1,43 @@
 {% extends "base.html" %}
-{% block title %}Dashboard · MIEM Employees{% endblock %}
+{% block title %}Обзор · MIEM Employees{% endblock %}
 {% block content %}
 <section class="admin__grid">
-  <div class="metric"><div class="metric__label">Total</div><div class="metric__value">{{ counts.total }}</div></div>
-  <div class="metric"><div class="metric__label">Active</div><div class="metric__value">{{ counts.active }}</div></div>
-  <div class="metric"><div class="metric__label">New in last run</div><div class="metric__value">{{ counts.new_in_last_run }}</div></div>
-  <div class="metric"><div class="metric__label">Dismissed</div><div class="metric__value">{{ counts.dismissed }}</div></div>
+  <div class="metric"><div class="metric__label">Всего в базе</div><div class="metric__value">{{ counts.total }}</div></div>
+  <div class="metric"><div class="metric__label">Работают</div><div class="metric__value">{{ counts.active }}</div></div>
+  <div class="metric"><div class="metric__label">Новые за запуск</div><div class="metric__value">{{ counts.new_in_last_run }}</div></div>
+  <div class="metric"><div class="metric__label">Уволены</div><div class="metric__value">{{ counts.dismissed }}</div></div>
 </section>
 <section class="stats-strip">
   <div class="stats-strip__item">
-    <span class="stats-strip__label">Latest added</span>
+    <span class="stats-strip__label">Последний добавленный</span>
     {% if counts.latest_added %}
     <a class="stats-strip__value" href="/admin/employees/{{ counts.latest_added.id }}">{{ counts.latest_added.full_name or counts.latest_added.canonical_url }}</a>
     {% else %}
-    <span class="stats-strip__value">No employees yet</span>
+    <span class="stats-strip__value">Сотрудников пока нет</span>
     {% endif %}
   </div>
   <div class="stats-strip__item">
-    <span class="stats-strip__label">Runs</span>
+    <span class="stats-strip__label">Запуски</span>
     <span class="stats-strip__value">{{ counts.runs }}</span>
   </div>
   <div class="stats-strip__item">
-    <span class="stats-strip__label">Errors</span>
+    <span class="stats-strip__label">Ошибки</span>
     <span class="stats-strip__value">{{ counts.errors }}</span>
   </div>
 </section>
 <section class="panel progress-panel" data-progress-panel>
   <div class="progress-panel__header">
-    <h2 class="panel__title">Parsing progress</h2>
+    <h2 class="panel__title">Прогресс парсинга</h2>
     <form method="post" action="/admin/crawl-now">
-      <button class="button" type="submit">Start crawl now</button>
+      <button class="button" type="submit">Запустить парсинг</button>
     </form>
   </div>
   {% set run = counts.current_running_run or latest_run %}
   <div class="progress-panel__body" data-progress-body>
     <div class="progress-panel__meta">
-      <span data-progress-status>{{ run.status if run else "idle" }}</span>
-      <span><span data-progress-processed>{{ run.processed_count if run else 0 }}</span> / <span data-progress-found>{{ run.found_count if run else 0 }}</span> processed</span>
-      <span><span data-progress-errors>{{ run.error_count if run else 0 }}</span> errors</span>
+      <span data-progress-status>{{ run.status_display if run else "Ожидание" }}</span>
+      <span>обработано: <span data-progress-processed>{{ run.processed_count if run else 0 }}</span> / <span data-progress-found>{{ run.found_count if run else 0 }}</span></span>
+      <span>ошибок: <span data-progress-errors>{{ run.error_count if run else 0 }}</span></span>
     </div>
     <div class="progress-bar" aria-label="Parsing progress">
       <div class="progress-bar__fill" data-progress-fill style="width: {{ run.progress_percent if run else 0 }}%"></div>
@@ -46,12 +46,12 @@
   </div>
 </section>
 <section class="panel">
-  <h2 class="panel__title">Latest runs</h2>
+  <h2 class="panel__title">Последние запуски</h2>
   <table class="table">
-    <thead><tr><th class="table__head">ID</th><th class="table__head">Status</th><th class="table__head">Parsed</th><th class="table__head">Errors</th><th class="table__head">Started</th></tr></thead>
+    <thead><tr><th class="table__head">ID</th><th class="table__head">Статус</th><th class="table__head">Обработано</th><th class="table__head">Ошибки</th><th class="table__head">Старт</th></tr></thead>
     <tbody>
       {% for run in runs %}
-      <tr><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.started_at }}</td></tr>
+      <tr><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
       {% endfor %}
     </tbody>
   </table>

app/templates/directory.html

@@ -1,65 +1,71 @@
 {% extends "base.html" %}
-{% block title %}Directory · MIEM Employees{% endblock %}
+{% block title %}Сотрудники · MIEM Employees{% endblock %}
 {% block content %}
 <section class="directory">
   <div class="directory__header">
     <div>
-      <h2 class="directory__title">Directory</h2>
-      <p class="directory__summary">{{ page.total }} employees found</p>
+      <h2 class="directory__title">Сотрудники</h2>
+      <p class="directory__summary">Найдено: {{ page.total }}</p>
     </div>
-    <button class="button" type="button" data-columns-open>Columns</button>
+    <button class="button" type="button" data-columns-open>Колонки</button>
   </div>
 
   <form class="directory__filters" method="get" action="/admin/directory">
-    <input class="directory__input" name="q" value="{{ filters.q }}" placeholder="Name or URL">
+    <input class="directory__input" name="q" value="{{ filters.q }}" placeholder="ФИО или ссылка">
     <select class="directory__input" name="status">
-      <option value="" {% if not filters.status %}selected{% endif %}>All statuses</option>
-      <option value="active" {% if filters.status == "active" %}selected{% endif %}>Active</option>
-      <option value="dismissed" {% if filters.status == "dismissed" %}selected{% endif %}>Dismissed</option>
+      <option value="" {% if not filters.status %}selected{% endif %}>Все статусы</option>
+      <option value="active" {% if filters.status == "active" %}selected{% endif %}>Работает</option>
+      <option value="dismissed" {% if filters.status == "dismissed" %}selected{% endif %}>Уволен</option>
     </select>
     <select class="directory__input" name="has_email">
-      <option value="" {% if not filters.has_email %}selected{% endif %}>Any email</option>
-      <option value="true" {% if filters.has_email == "true" %}selected{% endif %}>Has email</option>
-      <option value="false" {% if filters.has_email == "false" %}selected{% endif %}>No email</option>
+      <option value="" {% if not filters.has_email %}selected{% endif %}>Любой email</option>
+      <option value="true" {% if filters.has_email == "true" %}selected{% endif %}>Есть email</option>
+      <option value="false" {% if filters.has_email == "false" %}selected{% endif %}>Нет email</option>
     </select>
-    <input class="directory__input" type="date" name="started_from" value="{{ filters.started_from }}" aria-label="First seen from">
-    <input class="directory__input" type="date" name="started_to" value="{{ filters.started_to }}" aria-label="First seen to">
+    <input class="directory__input" type="date" name="started_from" value="{{ filters.started_from }}" aria-label="Впервые найден с">
+    <input class="directory__input" type="date" name="started_to" value="{{ filters.started_to }}" aria-label="Впервые найден по">
     <select class="directory__input" name="sort">
-      {% for value, label in [("full_name", "Name"), ("status", "Status"), ("hse_start_year", "HSE start"), ("first_seen_at", "First seen"), ("last_seen_at", "Last seen"), ("dismissed_at", "Dismissed")] %}
-      <option value="{{ value }}" {% if filters.sort == value %}selected{% endif %}>Sort: {{ label }}</option>
+      {% for value, label in [("full_name", "ФИО"), ("status", "Статус"), ("hse_start_year", "Год начала"), ("first_seen_at", "Впервые найден"), ("last_seen_at", "Последний раз найден"), ("dismissed_at", "Дата увольнения")] %}
+      <option value="{{ value }}" {% if filters.sort == value %}selected{% endif %}>Сортировка: {{ label }}</option>
       {% endfor %}
     </select>
     <select class="directory__input" name="direction">
-      <option value="asc" {% if filters.direction == "asc" %}selected{% endif %}>Ascending</option>
-      <option value="desc" {% if filters.direction == "desc" %}selected{% endif %}>Descending</option>
+      <option value="asc" {% if filters.direction == "asc" %}selected{% endif %}>По возрастанию</option>
+      <option value="desc" {% if filters.direction == "desc" %}selected{% endif %}>По убыванию</option>
     </select>
-    <button class="button" type="submit">Apply</button>
+    <select class="directory__input" name="limit" onchange="this.form.offset.value = 0; this.form.submit()">
+      {% for value in [25, 50, 100] %}
+      <option value="{{ value }}" {% if filters.limit == value %}selected{% endif %}>На странице: {{ value }}</option>
+      {% endfor %}
+    </select>
+    <input type="hidden" name="offset" value="{{ filters.offset }}">
+    <button class="button" type="submit">Применить</button>
   </form>
 
   <div class="directory__table-wrap">
     <table class="directory-table" data-directory-table>
       <thead>
         <tr>
-          <th class="directory-table__head" data-column="full_name">Name</th>
-          <th class="directory-table__head" data-column="status">Status</th>
-          <th class="directory-table__head" data-column="positions">Positions</th>
-          <th class="directory-table__head" data-column="hse_start_year">HSE start</th>
+          <th class="directory-table__head" data-column="full_name">ФИО</th>
+          <th class="directory-table__head" data-column="status">Статус</th>
+          <th class="directory-table__head" data-column="positions">Должности</th>
+          <th class="directory-table__head" data-column="hse_start_year">Год начала</th>
           <th class="directory-table__head" data-column="email">Email</th>
-          <th class="directory-table__head" data-column="phone">Phone</th>
-          <th class="directory-table__head" data-column="address">Address</th>
-          <th class="directory-table__head" data-column="publications_count">Publications</th>
-          <th class="directory-table__head" data-column="courses_count">Courses</th>
-          <th class="directory-table__head" data-column="first_seen_at">First seen</th>
-          <th class="directory-table__head" data-column="last_seen_at">Last seen</th>
-          <th class="directory-table__head" data-column="dismissed_at">Dismissed</th>
-          <th class="directory-table__head" data-column="profile">Profile</th>
+          <th class="directory-table__head" data-column="phone">Телефон</th>
+          <th class="directory-table__head" data-column="address">Адрес</th>
+          <th class="directory-table__head" data-column="publications_count">Публикации</th>
+          <th class="directory-table__head" data-column="courses_count">Курсы</th>
+          <th class="directory-table__head" data-column="first_seen_at">Впервые найден</th>
+          <th class="directory-table__head" data-column="last_seen_at">Последний раз найден</th>
+          <th class="directory-table__head" data-column="dismissed_at">Дата увольнения</th>
+          <th class="directory-table__head" data-column="profile">Профиль</th>
         </tr>
       </thead>
       <tbody>
-        {% for employee in page.items %}
+        {% for employee in page.employees %}
         <tr class="directory-table__row" data-row-href="/admin/employees/{{ employee.id }}">
-          <td class="directory-table__cell" data-column="full_name">{{ employee.full_name or "No name" }}</td>
-          <td class="directory-table__cell" data-column="status"><span class="badge {% if employee.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee.status }}</span></td>
+          <td class="directory-table__cell" data-column="full_name">{{ employee.full_name or "Без имени" }}</td>
+          <td class="directory-table__cell" data-column="status"><span class="badge {% if employee.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee.status_display }}</span></td>
           <td class="directory-table__cell" data-column="positions">{{ employee.positions_text }}</td>
           <td class="directory-table__cell" data-column="hse_start_year">{{ employee.hse_start_year or "" }}</td>
           <td class="directory-table__cell" data-column="email">{{ employee.email_text }}</td>
@@ -67,13 +73,13 @@
           <td class="directory-table__cell" data-column="address">{{ employee.address or "" }}</td>
           <td class="directory-table__cell" data-column="publications_count">{{ employee.publications_count }}</td>
           <td class="directory-table__cell" data-column="courses_count">{{ employee.courses_count }}</td>
-          <td class="directory-table__cell" data-column="first_seen_at">{{ employee.first_seen_at or "" }}</td>
-          <td class="directory-table__cell" data-column="last_seen_at">{{ employee.last_seen_at or "" }}</td>
-          <td class="directory-table__cell" data-column="dismissed_at">{{ employee.dismissed_at or "" }}</td>
-          <td class="directory-table__cell" data-column="profile"><a class="admin__link" href="{{ employee.canonical_url }}">Open</a></td>
+          <td class="directory-table__cell" data-column="first_seen_at">{{ employee.first_seen_display }}</td>
+          <td class="directory-table__cell" data-column="last_seen_at">{{ employee.last_seen_display }}</td>
+          <td class="directory-table__cell" data-column="dismissed_at">{{ employee.dismissed_display }}</td>
+          <td class="directory-table__cell" data-column="profile"><a class="admin__link" href="{{ employee.canonical_url }}">Открыть</a></td>
         </tr>
         {% else %}
-        <tr><td class="directory-table__empty" colspan="13">No employees match these filters.</td></tr>
+        <tr><td class="directory-table__empty" colspan="13">По этим фильтрам сотрудники не найдены.</td></tr>
         {% endfor %}
       </tbody>
     </table>
@@ -83,24 +89,24 @@
     {% set prev_offset = filters.offset - filters.limit %}
     {% set next_offset = filters.offset + filters.limit %}
     {% if filters.offset > 0 %}
-    <a class="admin__link" href="{{ request.url.include_query_params(offset=prev_offset) }}">Previous</a>
+    <a class="admin__link" href="{{ request.url.include_query_params(offset=prev_offset) }}">Назад</a>
     {% endif %}
-    <span class="directory__page">Page {{ page.page }}{% if page.pages %} of {{ page.pages }}{% endif %}</span>
+    <span class="directory__page">Страница {{ page.page }}{% if page.pages %} из {{ page.pages }}{% endif %}</span>
     {% if next_offset < page.total %}
-    <a class="admin__link" href="{{ request.url.include_query_params(offset=next_offset) }}">Next</a>
+    <a class="admin__link" href="{{ request.url.include_query_params(offset=next_offset) }}">Вперед</a>
     {% endif %}
   </div>
 </section>
 
 <div class="columns-modal" data-columns-modal hidden>
   <div class="columns-modal__backdrop" data-columns-close></div>
-  <section class="columns-modal__panel" aria-label="Column settings">
+  <section class="columns-modal__panel" aria-label="Настройка колонок">
     <div class="columns-modal__header">
-      <h3 class="columns-modal__title">Visible columns</h3>
-      <button class="button button--ghost" type="button" data-columns-close>Close</button>
+      <h3 class="columns-modal__title">Отображаемые колонки</h3>
+      <button class="button button--ghost" type="button" data-columns-close>Закрыть</button>
     </div>
     <div class="columns-modal__grid">
-      {% for key, label in [("full_name", "Name"), ("status", "Status"), ("positions", "Positions"), ("hse_start_year", "HSE start"), ("email", "Email"), ("phone", "Phone"), ("address", "Address"), ("publications_count", "Publications"), ("courses_count", "Courses"), ("first_seen_at", "First seen"), ("last_seen_at", "Last seen"), ("dismissed_at", "Dismissed"), ("profile", "Profile")] %}
+      {% for key, label in [("full_name", "ФИО"), ("status", "Статус"), ("positions", "Должности"), ("hse_start_year", "Год начала"), ("email", "Email"), ("phone", "Телефон"), ("address", "Адрес"), ("publications_count", "Публикации"), ("courses_count", "Курсы"), ("first_seen_at", "Впервые найден"), ("last_seen_at", "Последний раз найден"), ("dismissed_at", "Дата увольнения"), ("profile", "Профиль")] %}
       <label class="columns-modal__option"><input class="columns-modal__checkbox" type="checkbox" value="{{ key }}" data-column-toggle> {{ label }}</label>
       {% endfor %}
     </div>

app/templates/employee_detail.html

@@ -1,26 +1,226 @@
 {% extends "base.html" %}
-{% block title %}{{ employee.full_name }} · MIEM Employees{% endblock %}
+{% block title %}{{ employee_view.full_name }} · MIEM Employees{% endblock %}
 {% block content %}
-<section class="panel">
-  <h2 class="panel__title">{{ employee.full_name or employee.profile_key }}</h2>
-  <p><span class="badge {% if employee.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee.status }}</span></p>
-  <p><a class="admin__link" href="{{ employee.canonical_url }}">{{ employee.canonical_url }}</a></p>
-  <h3>Tabs</h3>
-  <ul>
-    {% for tab in employee.tabs %}
-    <li><a class="admin__link" href="{{ tab.href }}">{{ tab.title }}</a></li>
-    {% endfor %}
-  </ul>
-  <h3>Current data</h3>
-  <pre class="code">{{ employee.current_data | tojson(indent=2) }}</pre>
+<section class="employee-card">
+  <div class="employee-card__header">
+    <div class="employee-card__identity">
+      <h2 class="employee-card__title">{{ employee_view.full_name or employee.profile_key }}</h2>
+      <span class="badge {% if employee_view.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee_view.status_display }}</span>
+    </div>
+    <a class="admin__link" href="{{ employee_view.canonical_url }}">{{ employee_view.canonical_url }}</a>
+  </div>
+
+  <section class="employee-card__section">
+    <h3 class="employee-section__title">Основная информация</h3>
+    <dl class="employee-card__meta">
+      <div class="employee-card__meta-item">
+        <dt class="employee-card__meta-label">Должности</dt>
+        <dd class="employee-card__meta-value">
+          {% if employee_view.positions %}
+          <ul class="employee-card__list">
+            {% for position in employee_view.positions %}
+            <li class="employee-card__list-item">{{ position }}</li>
+            {% endfor %}
+          </ul>
+          {% else %}
+          Не указано
+          {% endif %}
+        </dd>
+      </div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">Год начала работы в ВШЭ</dt><dd class="employee-card__meta-value">{{ employee_view.hse_start_year or "Не указано" }}</dd></div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">Тип профиля</dt><dd class="employee-card__meta-value">{{ employee_view.profile_type or "Не указано" }}</dd></div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">ID профиля</dt><dd class="employee-card__meta-value">{{ employee_view.profile_id or "Не указано" }}</dd></div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">Впервые найден</dt><dd class="employee-card__meta-value">{{ employee_view.first_seen_display }}</dd></div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">Последний раз найден</dt><dd class="employee-card__meta-value">{{ employee_view.last_seen_display }}</dd></div>
+      <div class="employee-card__meta-item"><dt class="employee-card__meta-label">Дата увольнения</dt><dd class="employee-card__meta-value">{{ employee_view.dismissed_display }}</dd></div>
+    </dl>
+  </section>
+
+  <section class="employee-card__section">
+    <h3 class="employee-section__title">Контакты</h3>
+    <dl class="employee-card__meta">
+      <div class="employee-card__meta-item">
+        <dt class="employee-card__meta-label">Email</dt>
+        <dd class="employee-card__meta-value">
+          {% if employee_view.contacts.emails %}
+          <ul class="employee-card__list">
+            {% for email in employee_view.contacts.emails %}
+            <li class="employee-card__list-item"><a class="admin__link" href="mailto:{{ email }}">{{ email }}</a></li>
+            {% endfor %}
+          </ul>
+          {% else %}
+          Не указано
+          {% endif %}
+        </dd>
+      </div>
+      <div class="employee-card__meta-item">
+        <dt class="employee-card__meta-label">Телефоны</dt>
+        <dd class="employee-card__meta-value">{{ employee_view.contacts.phones | join(", ") if employee_view.contacts.phones else "Не указано" }}</dd>
+      </div>
+      <div class="employee-card__meta-item">
+        <dt class="employee-card__meta-label">Адрес</dt>
+        <dd class="employee-card__meta-value">{{ employee_view.contacts.address or "Не указано" }}</dd>
+      </div>
+      {% if employee_view.contacts.contact_items %}
+      <div class="employee-card__meta-item employee-card__meta-item--wide">
+        <dt class="employee-card__meta-label">Прочее</dt>
+        <dd class="employee-card__meta-value">
+          <ul class="employee-card__list">
+            {% for item in employee_view.contacts.contact_items %}
+            <li class="employee-card__list-item">{{ item }}</li>
+            {% endfor %}
+          </ul>
+        </dd>
+      </div>
+      {% endif %}
+    </dl>
+  </section>
+
+  {% if employee_view.external_ids %}
+  <section class="employee-card__section">
+    <h3 class="employee-section__title">Внешние идентификаторы</h3>
+    <ul class="employee-card__list">
+      {% for external_id in employee_view.external_ids %}
+      <li class="employee-card__list-item">
+        <strong>{{ external_id.system }}:</strong>
+        {% if external_id.url %}
+        <a class="admin__link" href="{{ external_id.url }}">{{ external_id.value }}</a>
+        {% else %}
+        {{ external_id.value }}
+        {% endif %}
+      </li>
+      {% endfor %}
+    </ul>
+  </section>
+  {% endif %}
+
+  <section class="employee-card__section">
+    <h3 class="employee-section__title">Разделы профиля</h3>
+    {% if employee_view.sections %}
+    <div class="employee-card__sections">
+      {% for section in employee_view.sections %}
+      <article class="employee-section">
+        <div class="employee-section__header">
+          <h4 class="employee-section__title">{{ section.title }}</h4>
+          <span class="employee-section__type">{{ section.type }}</span>
+        </div>
+
+        {% if section.type == "year_blocks" and section.year_entries %}
+        <ul class="employee-card__list">
+          {% for entry in section.year_entries %}
+          <li class="employee-card__list-item">{% if entry.year %}<strong>{{ entry.year }}:</strong> {% endif %}{{ entry.text }}</li>
+          {% endfor %}
+        </ul>
+        {% elif section.type == "publications" and section.publications %}
+        {% if section.publications_count %}<p class="employee-section__note">Всего: {{ section.publications_count }}</p>{% endif %}
+        <ul class="employee-card__list">
+          {% for publication in section.publications %}
+          <li class="employee-card__list-item">
+            {% if publication.url %}
+            <a class="admin__link" href="{{ publication.url }}">{{ publication.title }}</a>
+            {% else %}
+            {{ publication.title }}
+            {% endif %}
+            {% if publication.text and publication.text != publication.title %}<div class="employee-section__text">{{ publication.text }}</div>{% endif %}
+          </li>
+          {% endfor %}
+        </ul>
+        {% elif section.type == "courses_by_year" and section.courses %}
+        {% if section.academic_year %}<p class="employee-section__note">Учебный год: {{ section.academic_year }}</p>{% endif %}
+        <ul class="employee-card__list">
+          {% for course in section.courses %}
+          <li class="employee-card__list-item">
+            {% if course.url %}
+            <a class="admin__link" href="{{ course.url }}">{{ course.title }}</a>
+            {% else %}
+            {{ course.title }}
+            {% endif %}
+          </li>
+          {% endfor %}
+        </ul>
+        {% elif section.type == "graduation_theses" and section.theses %}
+        {% if section.theses_count %}<p class="employee-section__note">Всего: {{ section.theses_count }}</p>{% endif %}
+        <ul class="employee-card__list">
+          {% for thesis in section.theses %}
+          <li class="employee-card__list-item">
+            {% if thesis.student %}<strong>{{ thesis.student }}</strong>{% endif %}
+            {% if thesis.title %}
+            <div class="employee-section__text">
+              {% if thesis.project_url %}
+              <a class="admin__link" href="{{ thesis.project_url }}">{{ thesis.title }}</a>
+              {% else %}
+              {{ thesis.title }}
+              {% endif %}
+            </div>
+            {% endif %}
+            <div class="employee-section__meta">
+              {% if thesis.defense_year %}<span class="employee-section__meta-item">Год защиты: {{ thesis.defense_year }}</span>{% endif %}
+              {% if thesis.level %}<span class="employee-section__meta-item">{{ thesis.level }}</span>{% endif %}
+              {% if thesis.rating is not none %}<span class="employee-section__meta-item">Оценка: {{ thesis.rating }}</span>{% endif %}
+              {% if thesis.program %}
+              <span class="employee-section__meta-item">
+                {% if thesis.program_url %}<a class="admin__link" href="{{ thesis.program_url }}">{{ thesis.program }}</a>{% else %}{{ thesis.program }}{% endif %}
+              </span>
+              {% endif %}
+            </div>
+          </li>
+          {% endfor %}
+        </ul>
+        {% elif section.type == "table" and section.table %}
+        <div class="employee-section__table-wrap">
+          <table class="employee-section__table">
+            {% if section.table.headers %}
+            <thead><tr>{% for header in section.table.headers %}<th class="employee-section__head">{{ header }}</th>{% endfor %}</tr></thead>
+            {% endif %}
+            <tbody>
+              {% for row in section.table.rows %}
+              <tr>
+                {% for cell in row.cells %}
+                <td class="employee-section__cell">{{ cell }}</td>
+                {% endfor %}
+              </tr>
+              {% endfor %}
+            </tbody>
+          </table>
+        </div>
+        {% else %}
+        {% if section.paragraphs %}
+        {% for paragraph in section.paragraphs %}
+        <p class="employee-section__text">{{ paragraph }}</p>
+        {% endfor %}
+        {% endif %}
+        {% if section.list_items %}
+        <ul class="employee-card__list">
+          {% for item in section.list_items %}
+          <li class="employee-card__list-item">{{ item }}</li>
+          {% endfor %}
+        </ul>
+        {% endif %}
+        {% endif %}
+
+        {% if section.links and section.type not in ["courses_by_year", "graduation_theses"] %}
+        <div class="employee-section__links">
+          {% for link in section.links %}
+          <a class="employee-section__link" href="{{ link.url }}">{{ link.text }}</a>
+          {% endfor %}
+        </div>
+        {% endif %}
+      </article>
+      {% endfor %}
+    </div>
+    {% else %}
+    <p class="employee-section__text">Разделы профиля не найдены.</p>
+    {% endif %}
+  </section>
 </section>
+
 <section class="panel">
-  <h2 class="panel__title">Snapshots</h2>
+  <h2 class="panel__title">Снапшоты</h2>
   <table class="table">
-    <thead><tr><th class="table__head">Captured</th><th class="table__head">Checksum</th><th class="table__head">Parser</th></tr></thead>
+    <thead><tr><th class="table__head">Дата</th><th class="table__head">Checksum</th><th class="table__head">Парсер</th></tr></thead>
     <tbody>
       {% for snapshot in snapshots %}
-      <tr><td class="table__cell">{{ snapshot.captured_at }}</td><td class="table__cell">{{ snapshot.checksum }}</td><td class="table__cell">{{ snapshot.parser_version }}</td></tr>
+      <tr><td class="table__cell">{{ snapshot.captured_display }}</td><td class="table__cell">{{ snapshot.checksum }}</td><td class="table__cell">{{ snapshot.parser_version }}</td></tr>
       {% endfor %}
     </tbody>
   </table>

app/templates/employees.html

@@ -1,29 +0,0 @@
-{% extends "base.html" %}
-{% block title %}Employees · MIEM Employees{% endblock %}
-{% block content %}
-<section class="panel">
-  <h2 class="panel__title">Employees</h2>
-  <form class="form" method="get" action="/admin/employees">
-    <input class="form__input" name="q" value="{{ q }}" placeholder="Name or URL">
-    <select class="form__select" name="status">
-      <option value="" {% if not status %}selected{% endif %}>All</option>
-      <option value="active" {% if status == "active" %}selected{% endif %}>Active</option>
-      <option value="dismissed" {% if status == "dismissed" %}selected{% endif %}>Dismissed</option>
-    </select>
-    <button class="button" type="submit">Search</button>
-  </form>
-  <table class="table">
-    <thead><tr><th class="table__head">Name</th><th class="table__head">Status</th><th class="table__head">Last seen</th><th class="table__head">Profile</th></tr></thead>
-    <tbody>
-      {% for employee in employees %}
-      <tr>
-        <td class="table__cell"><a class="admin__link" href="/admin/employees/{{ employee.id }}">{{ employee.full_name or employee.profile_key }}</a></td>
-        <td class="table__cell"><span class="badge {% if employee.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee.status }}</span></td>
-        <td class="table__cell">{{ employee.last_seen_at }}</td>
-        <td class="table__cell"><a class="admin__link" href="{{ employee.canonical_url }}">{{ employee.canonical_url }}</a></td>
-      </tr>
-      {% endfor %}
-    </tbody>
-  </table>
-</section>
-{% endblock %}

app/templates/login.html

@@ -3,18 +3,18 @@
   <head>
     <meta charset="utf-8">
     <meta name="viewport" content="width=device-width, initial-scale=1">
-    <title>Login · MIEM Employees</title>
+    <title>Вход · MIEM Employees</title>
     <link rel="stylesheet" href="/static/admin.css">
   </head>
   <body class="admin">
     <main class="admin__main">
       <section class="panel">
-        <h1 class="panel__title">Admin login</h1>
+        <h1 class="panel__title">Вход в админку</h1>
         {% if error %}<p>{{ error }}</p>{% endif %}
         <form class="form" method="post" action="/admin/login">
-          <label class="form__label">Login <input class="form__input" name="username" autocomplete="username"></label>
-          <label class="form__label">Password <input class="form__input" name="password" type="password" autocomplete="current-password"></label>
-          <button class="button" type="submit">Sign in</button>
+          <label class="form__label">Логин <input class="form__input" name="username" autocomplete="username"></label>
+          <label class="form__label">Пароль <input class="form__input" name="password" type="password" autocomplete="current-password"></label>
+          <button class="button" type="submit">Войти</button>
         </form>
       </section>
     </main>

app/templates/runs.html

@@ -1,10 +1,10 @@
 {% extends "base.html" %}
-{% block title %}Runs · MIEM Employees{% endblock %}
+{% block title %}Запуски · MIEM Employees{% endblock %}
 {% block content %}
 <section class="panel">
   <div class="progress-panel__header">
-    <h2 class="panel__title">Crawl runs</h2>
-    <form method="post" action="/admin/runs"><button class="button" type="submit">Start crawl now</button></form>
+    <h2 class="panel__title">Запуски парсинга</h2>
+    <form method="post" action="/admin/runs"><button class="button" type="submit">Запустить парсинг</button></form>
   </div>
   {% set run = runs[0] if runs else none %}
   {% if run %}
@@ -12,9 +12,9 @@
   {% set percent = ((processed / run.found_count) * 100) | round(1) if run.found_count else 0 %}
   <div class="progress-panel" data-progress-panel>
     <div class="progress-panel__meta">
-      <span data-progress-status>{{ run.status }}</span>
-      <span><span data-progress-processed>{{ processed }}</span> / <span data-progress-found>{{ run.found_count }}</span> processed</span>
-      <span><span data-progress-errors>{{ run.error_count }}</span> errors</span>
+      <span data-progress-status>{{ run.status_display }}</span>
+      <span>обработано: <span data-progress-processed>{{ processed }}</span> / <span data-progress-found>{{ run.found_count }}</span></span>
+      <span>ошибок: <span data-progress-errors>{{ run.error_count }}</span></span>
     </div>
     <div class="progress-bar" aria-label="Parsing progress">
       <div class="progress-bar__fill" data-progress-fill style="width: {{ percent }}%"></div>
@@ -24,9 +24,9 @@
   {% else %}
   <div class="progress-panel" data-progress-panel>
     <div class="progress-panel__meta">
-      <span data-progress-status>idle</span>
-      <span><span data-progress-processed>0</span> / <span data-progress-found>0</span> processed</span>
-      <span><span data-progress-errors>0</span> errors</span>
+      <span data-progress-status>Ожидание</span>
+      <span>обработано: <span data-progress-processed>0</span> / <span data-progress-found>0</span></span>
+      <span>ошибок: <span data-progress-errors>0</span></span>
     </div>
     <div class="progress-bar" aria-label="Parsing progress">
       <div class="progress-bar__fill" data-progress-fill style="width: 0%"></div>
@@ -35,18 +35,18 @@
   </div>
   {% endif %}
   <table class="table">
-    <thead><tr><th class="table__head">ID</th><th class="table__head">Status</th><th class="table__head">Found</th><th class="table__head">Parsed</th><th class="table__head">New</th><th class="table__head">Errors</th><th class="table__head">Dismissed</th></tr></thead>
+    <thead><tr><th class="table__head">ID</th><th class="table__head">Статус</th><th class="table__head">Найдено</th><th class="table__head">Обработано</th><th class="table__head">Новые</th><th class="table__head">Ошибки</th><th class="table__head">Уволены</th><th class="table__head">Старт</th></tr></thead>
     <tbody>
       {% for run in runs %}
-      <tr><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status }}</td><td class="table__cell">{{ run.found_count }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.new_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.dismissed_count }}</td></tr>
+      <tr><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.found_count }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.new_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.dismissed_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
       {% endfor %}
     </tbody>
   </table>
 </section>
 <section class="panel">
-  <h2 class="panel__title">Recent errors</h2>
+  <h2 class="panel__title">Последние ошибки</h2>
   <table class="table">
-    <thead><tr><th class="table__head">Run</th><th class="table__head">Profile</th><th class="table__head">Error</th></tr></thead>
+    <thead><tr><th class="table__head">Запуск</th><th class="table__head">Профиль</th><th class="table__head">Ошибка</th></tr></thead>
     <tbody>
       {% for error in errors %}
       <tr><td class="table__cell">{{ error.crawl_run_id }}</td><td class="table__cell">{{ error.profile_url }}</td><td class="table__cell">{{ error.error_type }}: {{ error.message }}</td></tr>

app/version.py

@@ -1,3 +1,3 @@
-APP_VERSION = "0.2.1"
-FRONTEND_VERSION = "0.2.1"
-BACKEND_VERSION = "0.2.1"
+APP_VERSION = "0.2.8"
+FRONTEND_VERSION = "0.2.8"
+BACKEND_VERSION = "0.2.8"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "miem-workers"
-version = "0.1.0"
+version = "0.2.8"
 description = "MIEM employees parser, admin API, and MCP server"
 requires-python = ">=3.11"
 dependencies = [

tests/test_admin_data.py

@@ -1,7 +1,22 @@
 from datetime import datetime, timezone
 
 from app.models import CrawlRun, Employee
-from app.services.admin_data import employee_display_payload, list_employees_page, run_payload, stats_payload
+from app.services.admin_data import (
+    employee_detail_payload,
+    employee_display_payload,
+    format_admin_datetime,
+    list_employees_page,
+    run_payload,
+    stats_payload,
+)
+
+
+def test_format_admin_datetime_handles_datetime_string_and_none():
+    value = datetime(2026, 4, 28, 17, 13, 34, tzinfo=timezone.utc)
+
+    assert format_admin_datetime(value) == "28.04.2026 20:13"
+    assert format_admin_datetime("2026-04-28T17:13:34.448605+00:00") == "28.04.2026 20:13"
+    assert format_admin_datetime(None) == "Не указано"
 
 
 def test_employee_display_payload_extracts_common_fields(db_session):
@@ -26,9 +41,103 @@ def test_employee_display_payload_extracts_common_fields(db_session):
     payload = employee_display_payload(employee)
 
     assert payload["positions_text"] == "Professor"
+    assert payload["status_display"] == "Работает"
     assert payload["email_text"] == "person@hse.ru"
     assert payload["publications_count"] == 1
     assert payload["courses_count"] == 1
+    assert payload["first_seen_display"] != "Не указано"
+
+
+def test_employee_detail_payload_normalizes_human_readable_sections(db_session):
+    employee = Employee(
+        profile_key="staff:person",
+        profile_type="staff",
+        profile_id="person",
+        canonical_url="https://www.hse.ru/staff/person",
+        full_name="Person Name",
+        status="active",
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+        current_data={
+            "positions": ["Professor"],
+            "hse_start_year": 2024,
+            "contacts": {
+                "emails": ["person@hse.ru"],
+                "phones": ["+79990000000"],
+                "address": "Moscow",
+                "items": [{"raw": "consultation hours"}],
+            },
+            "external_ids": [{"system": "ORCID", "value": "0000", "url": "https://orcid.org/0000"}],
+            "sections": [
+                {
+                    "title": "Education",
+                    "type": "year_blocks",
+                    "year_entries": [{"year": 2020, "text": "Master degree"}],
+                },
+                {
+                    "title": "Publications",
+                    "type": "publications",
+                    "publications": [{"title": "Paper", "text": "Paper details", "url": "https://example.test/paper"}],
+                },
+                {
+                    "title": "Courses",
+                    "type": "courses_by_year",
+                    "academic_year": "2025/2026",
+                    "courses": [{"title": "Course", "url": "https://example.test/course"}],
+                },
+                {
+                    "title": "ВКР",
+                    "type": "graduation_theses",
+                    "theses_count": 1,
+                    "theses": [
+                        {
+                            "student": "Student Name",
+                            "title": "Thesis title",
+                            "defense_year": 2025,
+                            "project_url": "https://www.hse.ru/edu/vkr/1",
+                        }
+                    ],
+                },
+                {
+                    "title": "Fallback",
+                    "type": "generic",
+                    "raw_text": "Fallback text",
+                },
+            ],
+        },
+    )
+
+    payload = employee_detail_payload(employee)
+
+    assert payload["contacts"]["emails"] == ["person@hse.ru"]
+    assert payload["contacts"]["contact_items"] == ["consultation hours"]
+    assert payload["external_ids"][0]["system"] == "ORCID"
+    assert payload["sections"][0]["year_entries"][0]["text"] == "Master degree"
+    assert payload["sections"][1]["publications"][0]["title"] == "Paper"
+    assert payload["sections"][2]["courses"][0]["title"] == "Course"
+    assert payload["sections"][3]["theses"][0]["student"] == "Student Name"
+    assert payload["sections"][4]["paragraphs"] == ["Fallback text"]
+
+
+def test_employee_payloads_tolerate_malformed_current_data(db_session):
+    employee = Employee(
+        profile_key="staff:broken",
+        canonical_url="https://www.hse.ru/staff/broken",
+        full_name="Broken Data",
+        status="active",
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+        current_data="not-a-dict",
+    )
+
+    display = employee_display_payload(employee)
+    detail = employee_detail_payload(employee)
+
+    assert display["positions"] == []
+    assert display["email_text"] == ""
+    assert detail["contacts"]["emails"] == []
+    assert detail["contacts"]["contact_items"] == []
+    assert detail["sections"] == []
 
 
 def test_list_employees_page_filters_sorts_and_paginates(db_session):
@@ -59,7 +168,8 @@ def test_list_employees_page_filters_sorts_and_paginates(db_session):
     page = list_employees_page(db_session, status="active", sort="full_name", direction="asc", limit=10)
 
     assert page["total"] == 1
-    assert page["items"][0]["full_name"] == "Alpha"
+    assert page["employees"][0]["full_name"] == "Alpha"
+    assert page["limit"] == 50
 
 
 def test_stats_payload_uses_latest_run_new_count(db_session):
@@ -96,3 +206,4 @@ def test_run_payload_calculates_progress():
 
     assert payload["processed_count"] == 5
     assert payload["progress_percent"] == 50.0
+    assert payload["status_display"] == "Выполняется"

tests/test_admin_templates.py

@@ -0,0 +1,34 @@
+from pathlib import Path
+
+
+def test_base_navigation_is_russian_and_has_no_legacy_employees_link():
+    template = Path("app/templates/base.html").read_text(encoding="utf-8")
+
+    assert "Обзор" in template
+    assert "Сотрудники" in template
+    assert "Запуски" in template
+    assert "Выйти" in template
+    assert ">Employees<" not in template
+    assert "/admin/employees" not in template
+
+
+def test_directory_template_is_russian_and_uses_display_dates():
+    template = Path("app/templates/directory.html").read_text(encoding="utf-8")
+
+    assert "Сотрудники" in template
+    assert "Колонки" in template
+    assert "Применить" in template
+    assert "На странице: {{ value }}" in template
+    assert "{% for value in [25, 50, 100] %}" in template
+    assert "Найдено:" in template
+    assert "employee.first_seen_display" in template
+    assert "employee.last_seen_display" in template
+    assert "employee.dismissed_display" in template
+    assert "Directory" not in template
+    assert "employees found" not in template
+
+
+def test_admin_employees_route_redirects_to_directory():
+    source = Path("app/admin.py").read_text(encoding="utf-8")
+
+    assert 'RedirectResponse("/admin/directory", status_code=303)' in source

tests/test_api_mcp.py

@@ -18,7 +18,7 @@ def test_health_returns_versions():
     response = client.get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "0.2.1"
+    assert response.json()["backend_version"] == "0.2.8"
 
 
 def test_mcp_requires_token_and_lists_tools():

tests/test_config.py

@@ -0,0 +1,13 @@
+from app.config import Settings
+
+
+def test_empty_crawl_limit_is_treated_as_none():
+    settings = Settings(crawl_limit="")
+
+    assert settings.crawl_limit is None
+
+
+def test_numeric_crawl_limit_is_parsed():
+    settings = Settings(crawl_limit="25")
+
+    assert settings.crawl_limit == 25

tests/test_employee_detail_template.py

@@ -0,0 +1,30 @@
+from pathlib import Path
+
+
+def test_employee_detail_template_is_human_readable():
+    template = Path("app/templates/employee_detail.html").read_text(encoding="utf-8")
+
+    assert "Current data" not in template
+    assert "<pre class=\"code\"" not in template
+    assert ">Tabs<" not in template
+    assert "contacts.items" not in template
+    assert "contacts.contact_items" in template
+    assert "section.items" not in template
+    assert "section.list_items" in template
+    assert "Основная информация" in template
+    assert "Контакты" in template
+    assert "Разделы профиля" in template
+    assert "graduation_theses" in template
+    assert "Год защиты" in template
+    assert "Parser version" not in template
+    assert "First seen" not in template
+    assert "Last seen" not in template
+    assert "Dismissed at" not in template
+    assert "Profile type" not in template
+    assert "Profile ID" not in template
+    assert "Впервые найден" in template
+    assert "Последний раз найден" in template
+    assert "Дата увольнения" in template
+    assert "Тип профиля" in template
+    assert "ID профиля" in template
+    assert "Снапшоты" in template

tests/test_parser.py

@@ -1,9 +1,69 @@
 from bs4 import BeautifulSoup
 
-from app.parser.profile import extract_person_tabs
+from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs
 from app.parser.profile_url import normalize_profile_url, parse_profile_identity
 
 
+class FakeResponse:
+    def __init__(self, payload):
+        self.payload = payload
+
+    def raise_for_status(self):
+        return None
+
+    def json(self):
+        return self.payload
+
+
+class FakeSession:
+    def __init__(self):
+        self.posts = []
+        self.gets = []
+
+    def post(self, url, **kwargs):
+        self.posts.append((url, kwargs))
+        return FakeResponse(
+            {
+                "status": "ok",
+                "result": {
+                    "more": False,
+                    "total": 1,
+                    "items": [
+                        {
+                            "id": "888959076",
+                            "type": "ARTICLE",
+                            "title": "Дублирование пакетов",
+                            "year": 2023,
+                            "description": {"short": {"ru": "Информационные процессы. 2023."}},
+                        }
+                    ],
+                },
+            }
+        )
+
+    def get(self, url, **kwargs):
+        self.gets.append((url, kwargs))
+        return FakeResponse(
+            {
+                "lang": "ru",
+                "success": True,
+                "data": [
+                    {
+                        "id": 1045750164,
+                        "year": 2025,
+                        "level": "Бакалавриат",
+                        "title": "Аппаратно-программный комплекс защиты сети",
+                        "rating": 8,
+                        "student": "Лесняк Владислав Евгеньевич",
+                        "learnProgram": {"title": "Информатика и вычислительная техника", "url": "https://hse.ru/ba/isct/"},
+                        "orgUnit": {"title": "МИЭМ", "url": "https://www.hse.ru/org/url/59315150"},
+                        "supervisors": [{"url": "https://www.hse.ru/org/persons/803294906", "name": "Борисов Сергей Петрович"}],
+                    }
+                ],
+            }
+        )
+
+
 def test_normalize_profile_url_supports_staff_and_org_persons():
     assert normalize_profile_url("/staff/avsergeev#sci") == "https://www.hse.ru/staff/avsergeev"
     assert normalize_profile_url("https://www.hse.ru/org/persons/123/") == "https://www.hse.ru/org/persons/123"
@@ -26,3 +86,34 @@ def test_extract_person_tabs_prefers_person_menu_addition():
 
     assert [tab["title"] for tab in tabs] == ["Домашняя страница", "Публикации"]
     assert tabs[1]["href"] == "https://www.hse.ru/staff/avsergeev#sci"
+
+
+def test_enrich_sections_from_hse_widgets_loads_publications_and_vkr():
+    soup = BeautifulSoup(
+        """
+        <script src="/n/stat/publications/dist-w/publs.js" data-author="568398853" data-widget-name="AuthorSearch"></script>
+        <script src="/n/stat/vkr/app.js" data-api-url="/n/vkr/api/" data-person-id="803294906"></script>
+        """,
+        "html.parser",
+    )
+    session = FakeSession()
+
+    sections = enrich_sections_from_hse_widgets(
+        session,
+        soup,
+        "https://www.hse.ru/org/persons/803294906",
+        {"User-Agent": "test"},
+        10,
+        [],
+    )
+
+    publications = next(section for section in sections if section["type"] == "publications")
+    theses = next(section for section in sections if section["type"] == "graduation_theses")
+
+    assert publications["publications_count"] == 1
+    assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/888959076"
+    assert theses["theses_count"] == 1
+    assert theses["theses"][0]["student"] == "Лесняк Владислав Евгеньевич"
+    assert theses["theses"][0]["project_url"] == "https://www.hse.ru/edu/vkr/1045750164"
+    assert session.posts[0][0] == "https://publications.hse.ru/api/searchPubs"
+    assert session.gets[0][1]["params"] == {"supervisorId": "803294906"}