fix: pipeline content tracking + topic article preview

db_helper.py: save_article now calculates and persists word_count
generator.py: run_creator_blocking sets word_count for HTML-imported articles
writer.py: fix title regex stripping content-leading numbers (35岁后→岁后)
trends.py: fix Baidu hot_score str/int type comparison crash
database.py: add missing content_tasks.org_id ALTER TABLE migration
schemas.py + topics.py: topic list API returns article_count + articles[] previews
topics.html: table view and card view show article badges with word counts, clickable to open preview

Ultraworked with Sisyphus

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

scripts/db_helper.py

@@ -246,12 +246,14 @@ def save_article(topic_id: str, platform: str, html_content: str, *, title: str
         from app.models import Article
         article_id = f"{platform}_{topic_id}"
         existing = db.query(Article).filter(Article.id == article_id).first()
+        word_count = len(content) if content else (len(html_content) if html_content else 0)
         if existing:
             existing.html_content = html_content
             if title:
                 existing.title = title
             if content:
                 existing.content = content
+            existing.word_count = word_count
         else:
             article = Article(
                 id=article_id,
@@ -261,6 +263,7 @@ def save_article(topic_id: str, platform: str, html_content: str, *, title: str
                 title=title,
                 content=content,
                 html_content=html_content,
+                word_count=word_count,
                 status="draft",
                 compliance_score=None
             )

scripts/trends.py

@@ -193,7 +193,8 @@ def fetch_baidu_hot() -> List[Dict]:
                     word = item.get("query", "").strip() or item.get("word", "").strip()
                     if not word:
                         continue
-                    hot_score = item.get("hotScore", 0) or item.get("heat", 0)
+                    hot_score_raw = item.get("hotScore", 0) or item.get("heat", 0)
+                    hot_score = int(hot_score_raw) if hot_score_raw else 0
                     desc = item.get("desc", "")
                     results.append({
                         "domain": _guess_domain(word, desc),

scripts/writer.py

@@ -557,7 +557,7 @@ class Writer:
                 line = line.strip()
                 if not line:
                     continue
-                line = re.sub(r'^\d+[.、)\s]+', '', line)
+                line = re.sub(r'^\d+[.、)）]\s*', '', line)
                 line = line.strip('*#- \t"\'"''"')
                 # 跳过思考/建议类输出（如"不如："、"或者："、"建议方案"等）
                 if re.match(r'^(不如|或者|建议|推荐|参考|方案[一二三]|第[一二三]种|以[下是]|标题[一二三]|选项)', line):