feat(images): add thumbnail gallery with select/exclude workflow

backend/app/admin_ui.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import json
 from pathlib import Path
+import re
 from urllib.parse import urlencode
 
 from fastapi import APIRouter, Form, Request
@@ -24,6 +25,7 @@ from .repositories import (
     list_feeds,
     list_runs,
     list_sources,
+    set_article_image_decision,
     set_article_legal_review,
     update_article_status,
 )
@@ -83,6 +85,63 @@ def _parse_meta_json(raw: str | None) -> dict:
         return {}
 
 
+def _read_article_images(article: dict, extraction: dict) -> list[str]:
+    images: list[str] = []
+    if article.get("image_urls_json"):
+        try:
+            parsed_images = json.loads(article["image_urls_json"])
+            if isinstance(parsed_images, list):
+                images = [str(item) for item in parsed_images if item]
+        except Exception:
+            images = []
+    if not images and isinstance(extraction.get("images"), list):
+        images = [str(item) for item in extraction.get("images") if item]
+    # deduplicate preserving order
+    seen: set[str] = set()
+    deduped: list[str] = []
+    for image in images:
+        if image not in seen:
+            seen.add(image)
+            deduped.append(image)
+    return deduped
+
+
+def _is_probably_irrelevant_image(url: str) -> bool:
+    lowered = url.lower()
+    patterns = (
+        r"logo",
+        r"icon",
+        r"sprite",
+        r"avatar",
+        r"favicon",
+        r"/ads/",
+        r"tracking",
+        r"pixel",
+        r"banner",
+    )
+    return any(re.search(pattern, lowered) for pattern in patterns)
+
+
+def _build_image_entries(article: dict, extraction: dict, meta: dict) -> list[dict[str, object]]:
+    all_images = _read_article_images(article, extraction)
+    image_review = meta.get("image_review") if isinstance(meta.get("image_review"), dict) else {}
+    selected_url = image_review.get("selected_url") if isinstance(image_review.get("selected_url"), str) else None
+    excluded_urls = image_review.get("excluded_urls") if isinstance(image_review.get("excluded_urls"), list) else []
+    excluded_set = {str(item) for item in excluded_urls if item}
+
+    entries: list[dict[str, object]] = []
+    for url in all_images:
+        entries.append(
+            {
+                "url": url,
+                "is_selected": selected_url == url,
+                "is_excluded": url in excluded_set,
+                "is_irrelevant_hint": _is_probably_irrelevant_image(url),
+            }
+        )
+    return entries
+
+
 def _legal_checklist(article: dict, feed: dict | None) -> list[dict[str, str]]:
     meta = article.get("meta", {})
     extraction = meta.get("extraction") if isinstance(meta.get("extraction"), dict) else {}
@@ -138,6 +197,15 @@ def _legal_checklist(article: dict, feed: dict | None) -> list[dict[str, str]]:
             "value": article.get("legal_checked_at") or "-",
         }
     )
+    image_review = meta.get("image_review") if isinstance(meta.get("image_review"), dict) else {}
+    selected_image = image_review.get("selected_url") if isinstance(image_review.get("selected_url"), str) else None
+    checks.append(
+        {
+            "label": "Hauptbild ausgewählt",
+            "status": "ok" if selected_image else "missing",
+            "value": selected_image or "-",
+        }
+    )
     return checks
 
 
@@ -202,18 +270,12 @@ def admin_dashboard(request: Request):
     for article in articles:
         meta = _parse_meta_json(article.get("meta_json"))
         extraction = meta.get("extraction") if isinstance(meta.get("extraction"), dict) else {}
-        images = []
+        images = _read_article_images(article, extraction)
-        if article.get("image_urls_json"):
-            try:
-                parsed_images = json.loads(article["image_urls_json"])
-                if isinstance(parsed_images, list):
-                    images = [str(item) for item in parsed_images if item]
-            except Exception:
-                images = []
-        if not images and isinstance(extraction.get("images"), list):
-            images = extraction.get("images")
         article["meta"] = meta
         article["extracted_images"] = images
+        article["image_entries"] = _build_image_entries(article, extraction, meta)
+        image_review = meta.get("image_review") if isinstance(meta.get("image_review"), dict) else {}
+        article["selected_image_url"] = image_review.get("selected_url") if isinstance(image_review.get("selected_url"), str) else None
         if not article.get("press_contact") and isinstance(extraction.get("press_contact"), str):
             article["press_contact"] = extraction.get("press_contact")
         article["extraction_error"] = extraction.get("extraction_error") if isinstance(extraction.get("extraction_error"), str) else None
@@ -254,16 +316,13 @@ def admin_article_detail(request: Request, article_id: int):
     meta = _parse_meta_json(article.get("meta_json"))
     article["meta"] = meta
     extraction = meta.get("extraction") if isinstance(meta.get("extraction"), dict) else {}
-    if article.get("image_urls_json"):
+    extraction["images"] = _read_article_images(article, extraction)
-        try:
-            parsed_images = json.loads(article["image_urls_json"])
-            if isinstance(parsed_images, list):
-                extraction["images"] = [str(item) for item in parsed_images if item]
-        except Exception:
-            pass
     if not article.get("press_contact") and isinstance(extraction.get("press_contact"), str):
         article["press_contact"] = extraction.get("press_contact")
     article["extraction"] = extraction
+    article["image_entries"] = _build_image_entries(article, extraction, meta)
+    image_review = meta.get("image_review") if isinstance(meta.get("image_review"), dict) else {}
+    article["selected_image_url"] = image_review.get("selected_url") if isinstance(image_review.get("selected_url"), str) else None
     article["days_old"] = article_age_days(article.get("published_at"))
     article["relevance"] = article_relevance(article.get("published_at"))
     feed = get_feed_by_id(int(article["feed_id"])) if article.get("feed_id") else None
@@ -284,6 +343,23 @@ def admin_article_detail(request: Request, article_id: int):
     )
 
 
+@router.post("/admin/articles/{article_id}/images/decision")
+def admin_article_image_decision(
+    request: Request,
+    article_id: int,
+    image_url: str = Form(...),
+    action: str = Form(...),
+):
+    user = _admin_user(request)
+    if not user:
+        return RedirectResponse(url="/admin/login", status_code=303)
+
+    ok = set_article_image_decision(article_id=article_id, image_url=image_url, action=action, actor=user)
+    if not ok:
+        return _dashboard_redirect(msg=f"Bildaktion fehlgeschlagen fuer Artikel #{article_id}", msg_type="error")
+    return RedirectResponse(url=f"/admin/articles/{article_id}", status_code=303)
+
+
 @router.post("/admin/articles/{article_id}/legal-review")
 def admin_article_legal_review(request: Request, article_id: int, approved: str = Form("0"), note: str = Form("")):
     user = _admin_user(request)

backend/app/main.py

@@ -336,6 +336,17 @@ def api_export_articles(
     articles = repo_list_articles(limit=500, status_filter=status_filter)
     rows = []
     for article in articles:
+        meta: dict = {}
+        if article.get("meta_json"):
+            try:
+                parsed = json.loads(article["meta_json"])
+                if isinstance(parsed, dict):
+                    meta = parsed
+            except Exception:
+                meta = {}
+        image_review = meta.get("image_review") if isinstance(meta.get("image_review"), dict) else {}
+        selected_image_url = image_review.get("selected_url") if isinstance(image_review.get("selected_url"), str) else None
+
         days_old = article_age_days(article.get("published_at"))
         rows.append(
             {
@@ -353,6 +364,7 @@ def api_export_articles(
                 "source_terms_url_snapshot": article.get("source_terms_url_snapshot"),
                 "press_contact": article.get("press_contact"),
                 "image_urls_json": article.get("image_urls_json"),
+                "selected_image_url": selected_image_url,
                 "legal_checked": bool(int(article.get("legal_checked", 0))),
                 "legal_checked_at": article.get("legal_checked_at"),
                 "legal_note": article.get("legal_note"),
@@ -377,6 +389,7 @@ def api_export_articles(
             "source_terms_url_snapshot",
             "press_contact",
             "image_urls_json",
+            "selected_image_url",
             "legal_checked",
             "legal_checked_at",
             "legal_note",

backend/app/repositories.py

@@ -262,6 +262,16 @@ def _merge_review_event(meta_json: str | None, event: dict[str, Any]) -> str:
     return json.dumps(meta, ensure_ascii=False)
 
 
+def _load_meta(meta_json: str | None) -> dict[str, Any]:
+    if not meta_json:
+        return {}
+    try:
+        parsed = json.loads(meta_json)
+        return parsed if isinstance(parsed, dict) else {}
+    except Exception:
+        return {}
+
+
 def update_article_status(
     article_id: int,
     new_status: str,
@@ -317,6 +327,54 @@ def set_article_legal_review(article_id: int, approved: bool, note: str | None,
     return True
 
 
+def set_article_image_decision(article_id: int, image_url: str, action: str, actor: str | None = None) -> bool:
+    article = get_article_by_id(article_id)
+    if not article:
+        return False
+    url = (image_url or "").strip()
+    if not url:
+        return False
+    if action not in {"select", "exclude", "restore"}:
+        return False
+
+    meta = _load_meta(article.get("meta_json"))
+    image_review = meta.get("image_review")
+    if not isinstance(image_review, dict):
+        image_review = {}
+
+    excluded = image_review.get("excluded_urls")
+    if not isinstance(excluded, list):
+        excluded = []
+    excluded_set = {str(item) for item in excluded if item}
+
+    selected_url = image_review.get("selected_url")
+    if not isinstance(selected_url, str):
+        selected_url = None
+
+    if action == "select":
+        selected_url = url
+        excluded_set.discard(url)
+    elif action == "exclude":
+        excluded_set.add(url)
+        if selected_url == url:
+            selected_url = None
+    elif action == "restore":
+        excluded_set.discard(url)
+
+    image_review["selected_url"] = selected_url
+    image_review["excluded_urls"] = sorted(excluded_set)
+    image_review["updated_at"] = datetime.now(timezone.utc).isoformat()
+    image_review["updated_by"] = actor or "system"
+    meta["image_review"] = image_review
+
+    with get_conn() as conn:
+        conn.execute(
+            "UPDATE articles SET meta_json = ? WHERE id = ?",
+            (json.dumps(meta, ensure_ascii=False), article_id),
+        )
+    return True
+
+
 def _resolve_existing_article_id(payload: ArticleUpsert) -> int | None:
     with get_conn() as conn:
         # 1) strongest key: source_url

backend/static/admin.css

@@ -179,6 +179,60 @@ button.secondary {
   background: #f8fafc;
 }
 
+.thumb {
+  width: 72px;
+  height: 72px;
+  object-fit: cover;
+  border-radius: 8px;
+  border: 1px solid #cbd5e1;
+  margin-top: 6px;
+}
+
+.image-grid {
+  display: grid;
+  grid-template-columns: repeat(auto-fill, minmax(180px, 1fr));
+  gap: 10px;
+}
+
+.image-card {
+  border: 1px solid #e2e8f0;
+  border-radius: 8px;
+  padding: 8px;
+  background: #fff;
+}
+
+.image-card img {
+  width: 100%;
+  height: 120px;
+  object-fit: cover;
+  border-radius: 6px;
+  border: 1px solid #e2e8f0;
+  background: #f8fafc;
+}
+
+.image-meta {
+  margin-top: 6px;
+  display: flex;
+  gap: 6px;
+  flex-wrap: wrap;
+}
+
+.image-actions {
+  margin-top: 8px;
+  display: flex;
+  gap: 6px;
+  flex-wrap: wrap;
+}
+
+.image-selected {
+  border-color: #10b981;
+  box-shadow: 0 0 0 1px rgba(16, 185, 129, 0.25);
+}
+
+.image-excluded {
+  opacity: 0.65;
+}
+
 @media (max-width: 920px) {
   .stats {
     grid-template-columns: repeat(2, minmax(0, 1fr));

backend/templates/admin_article_detail.html

@@ -67,13 +67,46 @@
 
     <section class="card">
       <h2>Extrahierte Daten</h2>
-      <p><strong>Bilder:</strong> {{ article.extraction.images|length if article.extraction.images else 0 }}</p>
+      <p><strong>Bilder:</strong> {{ article.image_entries|length if article.image_entries else 0 }}</p>
-      {% if article.extraction.images %}
+      {% if article.selected_image_url %}
-      <ul>
+      <p><strong>Ausgewähltes Hauptbild:</strong> <a href="{{ article.selected_image_url }}" target="_blank" rel="noopener">{{ article.selected_image_url }}</a></p>
-        {% for img in article.extraction.images %}
+      {% endif %}
-        <li><a href="{{ img }}" target="_blank" rel="noopener">{{ img }}</a></li>
+      {% if article.image_entries %}
+      <div class="image-grid">
+        {% for image in article.image_entries %}
+        <article class="image-card {{ 'image-selected' if image.is_selected else '' }} {{ 'image-excluded' if image.is_excluded else '' }}">
+          <a href="{{ image.url }}" target="_blank" rel="noopener">
+            <img src="{{ image.url }}" alt="Artikelbild" loading="lazy" />
+          </a>
+          <div class="image-meta">
+            {% if image.is_selected %}<span class="badge ok">Ausgewählt</span>{% endif %}
+            {% if image.is_excluded %}<span class="badge bad">Ausgeblendet</span>{% endif %}
+            {% if image.is_irrelevant_hint %}<span class="badge">evtl. irrelevant</span>{% endif %}
+          </div>
+          <div class="image-actions">
+            <form method="post" action="/admin/articles/{{ article.id }}/images/decision">
+              <input type="hidden" name="image_url" value="{{ image.url }}" />
+              <input type="hidden" name="action" value="select" />
+              <button type="submit">Als Hauptbild</button>
+            </form>
+            {% if not image.is_excluded %}
+            <form method="post" action="/admin/articles/{{ article.id }}/images/decision">
+              <input type="hidden" name="image_url" value="{{ image.url }}" />
+              <input type="hidden" name="action" value="exclude" />
+              <button type="submit" class="secondary">Ausblenden</button>
+            </form>
+            {% else %}
+            <form method="post" action="/admin/articles/{{ article.id }}/images/decision">
+              <input type="hidden" name="image_url" value="{{ image.url }}" />
+              <input type="hidden" name="action" value="restore" />
+              <button type="submit" class="secondary">Einblenden</button>
+            </form>
+            {% endif %}
+          </div>
+          <div class="subtle"><a href="{{ image.url }}" target="_blank" rel="noopener">{{ image.url }}</a></div>
+        </article>
         {% endfor %}
-      </ul>
+      </div>
       {% endif %}
       {% if article.press_contact or article.extraction.press_contact %}
       <p><strong>Pressekontakt</strong></p>

backend/templates/admin_dashboard.html

@@ -155,6 +155,10 @@
             <td><span class="badge">{{ a.status }}</span></td>
             <td>
               <div class="subtle">Legal: {{ "OK" if a.legal_checked else "offen" }}</div>
+              {% if a.selected_image_url %}
+              <div class="subtle">Hauptbild gesetzt</div>
+              <a href="{{ a.selected_image_url }}" target="_blank" rel="noopener"><img src="{{ a.selected_image_url }}" alt="Hauptbild" class="thumb" loading="lazy" /></a>
+              {% endif %}
               {% if a.summary %}
               <div><strong>Summary:</strong> {{ a.summary }}</div>
               {% endif %}

backend/tests/test_admin_ui.py

@@ -8,7 +8,15 @@ from fastapi.testclient import TestClient
 from backend.app import config as config_module
 from backend.app.db import init_db
 from backend.app.main import app
-from backend.app.repositories import ArticleUpsert, FeedCreate, SourceCreate, create_feed, create_source, upsert_article
+from backend.app.repositories import (
+    ArticleUpsert,
+    FeedCreate,
+    SourceCreate,
+    create_feed,
+    create_source,
+    get_article_by_id,
+    upsert_article,
+)
 
 
 class TestAdminUi(unittest.TestCase):
@@ -119,6 +127,18 @@ class TestAdminUi(unittest.TestCase):
         self.assertIn("Artikel-Detail", res.text)
         self.assertIn("Rechts-Checkliste", res.text)
 
+        decision = self.client.post(
+            f"/admin/articles/{article_id}/images/decision",
+            data={"image_url": "https://example.org/img.jpg", "action": "select"},
+            follow_redirects=True,
+        )
+        self.assertEqual(decision.status_code, 200)
+        self.assertIn("Ausgewähltes Hauptbild", decision.text)
+
+        article = get_article_by_id(article_id)
+        self.assertIsNotNone(article)
+        self.assertIn("selected_url", article.get("meta_json", ""))
+
 
 if __name__ == "__main__":
     unittest.main()