fix: enrich HSE profile parsing with publications and theses

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"