v1.1.0: 真实网页采集(可读正文全文入库) + 大模型接口多预置一键切换(SiliconFlow默认) + 数据源可编辑

- 新增 crawler.py: requests+bs4 readability风格清洗, 提取候选链接按文章相似度排序, 前5条抓全文存 articles.full_text, 详情页展示; example.com占位源走模拟, 真实源失败标记error不造假
- 大模型: 新增 llm_providers 表(预置 SiliconFlow/DeepSeek官方/Autodl/Local Qwen), 设置页增删改/测试/一键切换, 激活接口失败自动切换备用
- 数据源: 前端补编辑按钮+弹窗(后端 update 已支持), 列表显示URL与采集状态
- 数据库迁移: articles.full_text 列 + llm_providers 表

db.py

@@ -83,6 +83,17 @@ CREATE TABLE IF NOT EXISTS settings (
     value TEXT DEFAULT ''
 );
 
+CREATE TABLE IF NOT EXISTS llm_providers (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    name TEXT NOT NULL,
+    base_url TEXT DEFAULT '',
+    api_key TEXT DEFAULT '',
+    model TEXT DEFAULT '',
+    active INTEGER DEFAULT 0,        -- 1=当前激活（网页一键切换）
+    enabled INTEGER DEFAULT 1,
+    created_at TEXT DEFAULT ''
+);
+
 CREATE INDEX IF NOT EXISTS idx_articles_collected ON articles(collected_at);
 CREATE INDEX IF NOT EXISTS idx_articles_score ON articles(total_score);
 CREATE INDEX IF NOT EXISTS idx_articles_status ON articles(llm_status);
@@ -100,7 +111,11 @@ def init_db():
     os.makedirs(config.DATA_DIR, exist_ok=True)
     conn = get_conn()
     conn.executescript(_SCHEMA)
-    conn.commit()
+    # 迁移：旧库补充 full_text 列（存页面可读正文）
+    cols = [r["name"] for r in conn.execute("PRAGMA table_info(articles)").fetchall()]
+    if "full_text" not in cols:
+        conn.execute("ALTER TABLE articles ADD COLUMN full_text TEXT DEFAULT ''")
+        conn.commit()
     conn.close()
 
 
@@ -221,14 +236,15 @@ def add_article(a):
     cur = conn.execute(
         """INSERT INTO articles(source_id,title,url,author,content,summary,domain,entities,
            importance,relevance,total_score,is_important,analysis,llm_status,status,
-           published_at,collected_at)
-           VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)""",
+           published_at,collected_at,full_text)
+           VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?) """,
         (a.get("source_id", 0), a["title"], a.get("url", ""), a.get("author", ""),
          a.get("content", ""), a.get("summary", ""), a.get("domain", ""),
          json.dumps(a.get("entities", []), ensure_ascii=False),
          a.get("importance", 0), a.get("relevance", 0), a.get("total_score", 0),
          a.get("is_important", 0), a.get("analysis", ""), a.get("llm_status", "pending"),
-         a.get("status", "new"), a.get("published_at", ""), now_str()),
+         a.get("status", "new"), a.get("published_at", ""), now_str(),
+         a.get("full_text", "")),
     )
     conn.commit()
     conn.close()
@@ -237,7 +253,8 @@ def add_article(a):
 
 def update_article(aid, **fields):
     allowed = {"summary", "domain", "entities", "importance", "relevance",
-               "total_score", "is_important", "analysis", "llm_status", "notified", "status"}
+               "total_score", "is_important", "analysis", "llm_status", "notified", "status",
+               "full_text", "content", "title", "url"}
     sets, vals = [], []
     for k, v in fields.items():
         if k in allowed:
@@ -447,6 +464,79 @@ def delete_company(cid):
     conn.close()
 
 
+# ---------------- 大模型接口（llm_providers） ----------------
+def list_providers():
+    conn = get_conn()
+    rows = conn.execute("SELECT * FROM llm_providers ORDER BY active DESC, id").fetchall()
+    conn.close()
+    return [dict(r) for r in rows]
+
+
+def get_provider(pid):
+    conn = get_conn()
+    row = conn.execute("SELECT * FROM llm_providers WHERE id=?", (pid,)).fetchone()
+    conn.close()
+    return dict(row) if row else None
+
+
+def add_provider(name, base_url, api_key, model, active=0, enabled=1):
+    conn = get_conn()
+    cur = conn.execute(
+        "INSERT INTO llm_providers(name,base_url,api_key,model,active,enabled,created_at) "
+        "VALUES(?,?,?,?,?,?,?)",
+        (name, base_url, api_key, model, active, enabled, now_str()),
+    )
+    conn.commit()
+    conn.close()
+    return cur.lastrowid
+
+
+def update_provider(pid, **fields):
+    allowed = {"name", "base_url", "api_key", "model", "active", "enabled"}
+    sets, vals = [], []
+    for k, v in fields.items():
+        if k in allowed:
+            sets.append(f"{k}=?")
+            vals.append(v)
+    if not sets:
+        return
+    vals.append(pid)
+    conn = get_conn()
+    conn.execute(f"UPDATE llm_providers SET {','.join(sets)} WHERE id=?", vals)
+    conn.commit()
+    conn.close()
+
+
+def delete_provider(pid):
+    conn = get_conn()
+    conn.execute("DELETE FROM llm_providers WHERE id=?", (pid,))
+    conn.commit()
+    conn.close()
+
+
+def get_active_provider():
+    conn = get_conn()
+    row = conn.execute("SELECT * FROM llm_providers WHERE active=1 AND enabled=1 LIMIT 1").fetchone()
+    conn.close()
+    return dict(row) if row else None
+
+
+def set_active_provider(pid):
+    conn = get_conn()
+    conn.execute("UPDATE llm_providers SET active=0")
+    conn.execute("UPDATE llm_providers SET active=1, enabled=1 WHERE id=?", (pid,))
+    conn.commit()
+    conn.close()
+
+
+def enabled_providers_except(pid):
+    conn = get_conn()
+    rows = conn.execute(
+        "SELECT * FROM llm_providers WHERE enabled=1 AND id!=? ORDER BY id", (pid,)).fetchall()
+    conn.close()
+    return [dict(r) for r in rows]
+
+
 # ---------------- 通知日志 ----------------
 def add_log(type_, subject, count, article_ids, status="ok", detail=""):
     conn = get_conn()