modify scripts

javdb/src/sqlite_utils.py

@@ -64,7 +64,7 @@ def insert_actor_index(name, href, from_actor_list=None, from_movie_list=None):
         logging.error(f"未知错误: {e}")
         return None
 
-def insert_movie_index(title, href, from_actor_list=None, from_movie_makers=None, from_movie_series=None, maker_id=None, series_id=None, from_movie_publishers=None, pub_id=None):
+def insert_movie_index_old(title, href, from_actor_list=None, from_movie_makers=None, from_movie_series=None, maker_id=None, series_id=None, from_movie_publishers=None, pub_id=None):
     try:
         # **先检查数据库中是否已有该电影**
         cursor.execute("SELECT id, from_actor_list, from_movie_makers, from_movie_series, maker_id, series_id, from_movie_publishers, pub_id FROM javdb_movies WHERE href = ?", (href,))
@@ -114,6 +114,59 @@ def insert_movie_index(title, href, from_actor_list=None, from_movie_makers=None
         logging.error(f"Error inserting/updating movie: {e}")
         return None
 
+def insert_movie_index(title, href, **kwargs):
+    try:
+        # 先检查数据库中是否已有该电影
+        cursor.execute("SELECT * FROM javdb_movies WHERE href = ?", (href,))
+        existing_movie = cursor.fetchone()
+
+        # 获取列名
+        column_names = [description[0] for description in cursor.description]
+
+        fields = [
+            'from_actor_list', 'from_movie_makers', 'from_movie_series', 'from_movie_publishers',
+            'maker_id', 'series_id', 'pub_id', 'uncensored'
+        ]
+
+        if existing_movie:  # 如果电影已存在
+            existing_values = dict(zip(column_names, existing_movie))
+            movie_id = existing_values['id']
+            logging.debug(f"values in db: {existing_values}")
+
+            # 如果没有传入值，就用原来的值
+            for field in fields:
+                kwargs[field] = kwargs.get(field) if kwargs.get(field) is not None else existing_values[field]
+
+            set_clauses = ", ".join([f"{field} = ?" for field in fields])
+            sql = f"""
+                UPDATE javdb_movies 
+                SET title = ?, {set_clauses}, updated_at = datetime('now', 'localtime')
+                WHERE href = ?
+            """
+            values = [title] + [kwargs[field] for field in fields] + [href]
+            logging.debug(f"sql: {sql}, values: {values}")
+            cursor.execute(sql, values)
+        else:  # 如果电影不存在，插入
+            columns = ', '.join(['title', 'href'] + fields)
+            placeholders = ', '.join(['?'] * (len(fields) + 2))
+            sql = f"INSERT INTO javdb_movies ({columns}) VALUES ({placeholders})"
+            values = [title, href] + [kwargs.get(field, 0) for field in fields]
+            logging.debug(f"sql: {sql}, values: {values}")
+            cursor.execute(sql, values)
+
+        conn.commit()
+
+        movie_id = get_id_by_href('javdb_movies', href)
+        if movie_id:
+            logging.debug(f'Inserted/Updated movie index, id: {movie_id}, title: {title}, href: {href}')
+
+        return movie_id
+
+    except Exception as e:
+        conn.rollback()
+        logging.error(f"Error inserting/updating movie: {e}")
+        return None
+
 
 # 插入演员和电影的关联数据
 def insert_actor_movie(performer_id, movie_id, tags=''):
@@ -145,10 +198,11 @@ def insert_or_update_actor(actor):
             ON CONFLICT(href) DO UPDATE SET name=excluded.name, pic=excluded.pic, is_full_data=1, updated_at=datetime('now', 'localtime')
         ''', (actor['name'], actor['href'], actor['pic']))
         
-        cursor.execute('SELECT id FROM javdb_actors WHERE href = ?', (actor['href'],))
         conn.commit()
 
-        actor_id = get_id_by_href('javdb_actors', actor['href'])
+        # 查询刚插入的数据
+        cursor.execute('SELECT id, from_actor_list FROM javdb_actors WHERE href = ?', (actor['href'],))
+        actor_id, uncensored = cursor.fetchone()
         if actor_id is None:
             logging.warning(f'insert data error. name: {actor['name']}, href: {actor['href']}')
             return None
@@ -166,10 +220,10 @@ def insert_or_update_actor(actor):
 
         # 插入影片列表
         for movie in actor.get("credits") or []:
-            movie_id = get_id_by_href('javdb_movies', movie['href'])
-            # 影片不存在，先插入
-            if movie_id is None:
-                # TODO: from_actor_list 只标记无码女优的话，这里要修改，暂时不动
+            # from_actor_list = 1 表示无码影星的，其他不处理
+            if uncensored and uncensored > 0:
+                movie_id = insert_movie_index(movie['title'], movie['href'], from_actor_list=1, uncensored=uncensored)
+            else:
                 movie_id = insert_movie_index(movie['title'], movie['href'], from_actor_list=1)
             if movie_id:
                 tmp_id = insert_actor_movie(actor_id, movie_id)
@@ -227,47 +281,40 @@ def query_actors(**filters):
         sql = "SELECT href, name FROM javdb_actors WHERE 1=1"
         params = []
 
-        if "id" in filters:
-            sql += " AND id = ?"
-            params.append(filters["id"])
-        if "href" in filters:
-            sql += " AND href = ?"
-            params.append(filters["href"])
-        if "name" in filters:
-            sql += " AND name LIKE ?"
-            params.append(f"%{filters['name']}%")
-        if "is_full_data" in filters:
-            sql += " AND is_full_data = ?"
-            params.append(filters["is_full_data"])
-        if "from_actor_list" in filters:
-            sql += " AND from_actor_list = ?"
-            params.append(filters["from_actor_list"])
-        if "is_full_data_in" in filters:
-            values = filters["is_full_data_in"]
-            if values:
-                placeholders = ", ".join(["?"] * len(values))
-                sql += f" AND is_full_data IN ({placeholders})"
-                params.extend(values)
-        if "is_full_data_not_in" in filters:
-            values = filters["is_full_data_not_in"]
-            if values:
-                placeholders = ", ".join(["?"] * len(values))
-                sql += f" AND is_full_data NOT IN ({placeholders})"
-                params.extend(values)
-        if "before_updated_at" in filters:
-            sql += " AND updated_at <= ?"
-            params.append(filters["before_updated_at"])
-        if "after_updated_at" in filters:
-            sql += " AND updated_at >= ?"
-            params.append(filters["after_updated_at"])
-        if "start_id" in filters:
-            sql += " AND id > ?"
-            params.append(filters["start_id"])
+        conditions = {
+            "id": " AND id = ?",
+            "href": " AND href = ?",
+            "name": " AND name LIKE ?",
+            "is_full_data": " AND is_full_data = ?",
+            "from_actor_list": " AND from_actor_list = ?",
+            "before_updated_at": " AND updated_at <= ?",
+            "after_updated_at": " AND updated_at >= ?",
+            "start_id": " AND id > ?",
+        }
+
+        for key, condition in conditions.items():
+            if key in filters:
+                sql += condition
+                if key == "name":
+                    params.append(f"%{filters[key]}%")
+                else:
+                    params.append(filters[key])
+
+        for key in ["is_full_data_in", "is_full_data_not_in"]:
+            if key in filters:
+                values = filters[key]
+                if values:
+                    placeholders = ", ".join(["?"] * len(values))
+                    operator = "IN" if key == "is_full_data_in" else "NOT IN"
+                    sql += f" AND is_full_data {operator} ({placeholders})"
+                    params.extend(values)
+
         if "order_by" in filters:
-            sql += " order by ? asc"
-            params.append(filters["order_by"])
+            # 注意：这里 order by 后面直接跟字段名，不能用占位符，否则会被当作字符串处理
+            sql += f" ORDER BY {filters['order_by']} "
+
         if 'limit' in filters:
-            sql += " limit ?"
+            sql += " LIMIT ?"
             params.append(filters["limit"])
 
         cursor.execute(sql, params)
@@ -353,7 +400,7 @@ def query_maker(identifier):
 # 按条件查询 href 列表 
 def query_maker_hrefs(**filters):
     try:
-        sql = "SELECT href, id FROM javdb_makers WHERE 1=1"
+        sql = "SELECT href, id, from_list FROM javdb_makers WHERE 1=1"
         params = []
 
         if "id" in filters:
@@ -368,10 +415,13 @@ def query_maker_hrefs(**filters):
         if "name" in filters:
             sql += " AND name LIKE ?"
             params.append(f"%{filters['name']}%")
+        if 'limit' in filters:
+            sql += " limit ?"
+            params.append(filters["limit"])
 
         cursor.execute(sql, params)
         #return [row[0] for row in cursor.fetchall()]  # 链接使用小写
-        return [{'href': row[0], 'id': row[1]} for row in cursor.fetchall()]
+        return [{'href': row[0], 'id': row[1], 'from_list':row[2]} for row in cursor.fetchall()]
 
     except sqlite3.Error as e:
         logging.error(f"查询 href 失败: {e}")
@@ -451,7 +501,7 @@ def query_series(identifier):
 # 按条件查询 href 列表 
 def query_series_hrefs(**filters):
     try:
-        sql = "SELECT href, id FROM javdb_series WHERE 1=1"
+        sql = "SELECT href, id, from_list FROM javdb_series WHERE 1=1"
         params = []
 
         if "id" in filters:
@@ -466,10 +516,14 @@ def query_series_hrefs(**filters):
         if "name" in filters:
             sql += " AND name LIKE ?"
             params.append(f"%{filters['name']}%")
+        if 'limit' in filters:
+            sql += " limit ?"
+            params.append(filters["limit"])
 
         cursor.execute(sql, params)
         #return [row[0] for row in cursor.fetchall()]    # 链接使用小写
-        return [{'href': row[0], 'id': row[1]} for row in cursor.fetchall()]
+        #return [{'href': row[0], 'id': row[1]} for row in cursor.fetchall()]
+        return [{'href': row[0], 'id': row[1], 'from_list':row[2]} for row in cursor.fetchall()]
 
     except sqlite3.Error as e:
         logging.error(f"查询 href 失败: {e}")
@@ -795,7 +849,7 @@ def query_movies(identifier):
         return None
 
 # 按条件查询 href 列表 
-def query_movie_hrefs(**filters):
+def query_movie_hrefs_old(**filters):
     try:
         sql = "SELECT href, title, id FROM javdb_movies WHERE 1=1"
         params = []
@@ -850,7 +904,58 @@ def query_movie_hrefs(**filters):
     except sqlite3.Error as e:
         logging.error(f"查询 href 失败: {e}")
         return []
-    
+ 
+# 查询
+def query_movie_hrefs(**filters):
+    try:
+        sql = "SELECT href, name FROM javdb_movies WHERE 1=1"
+        params = []
+
+        conditions = {
+            "id": " AND id = ?",
+            "href": " AND href = ?",
+            "title": " AND title LIKE ?",
+            "is_full_data": " AND is_full_data = ?",
+            "uncensored": " AND uncensored = ?",
+            "from_actor_list": " AND from_actor_list = ?",
+            "before_updated_at": " AND updated_at <= ?",
+            "after_updated_at": " AND updated_at >= ?",
+            "start_id": " AND id > ?",
+        }
+
+        for key, condition in conditions.items():
+            if key in filters:
+                sql += condition
+                if key == "title":
+                    params.append(f"%{filters[key]}%")
+                else:
+                    params.append(filters[key])
+
+        for key in ["is_full_data_in", "is_full_data_not_in"]:
+            if key in filters:
+                values = filters[key]
+                if values:
+                    placeholders = ", ".join(["?"] * len(values))
+                    operator = "IN" if key == "is_full_data_in" else "NOT IN"
+                    sql += f" AND is_full_data {operator} ({placeholders})"
+                    params.extend(values)
+
+        if "order_by" in filters:
+            # 注意：这里 order by 后面直接跟字段名，不能用占位符，否则会被当作字符串处理
+            sql += f" ORDER BY {filters['order_by']} "
+
+        if 'limit' in filters:
+            sql += " LIMIT ?"
+            params.append(filters["limit"])
+
+        cursor.execute(sql, params)
+        #return [row[0].lower() for row in cursor.fetchall()]   # 返回小写
+        return [{'href': row[0], 'name': row[1]} for row in cursor.fetchall()]
+
+    except sqlite3.Error as e:
+        logging.error(f"查询 href 失败: {e}")
+        return None
+
 # 插入一条任务日志
 def insert_task_log():
     try: