modify scripts

aabook/src/fetch.py

@@ -18,6 +18,7 @@ force = False
 # 获取列表
 def fetch_book_list():
     url = scraper.list_url_update
+    updated_books = 0
     while True:
         logging.info(f'fetching book list. url: {url}')
         soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="list_main", attr_type="class"))
@@ -25,14 +26,14 @@ def fetch_book_list():
             # 获取书籍列表
             list_data, next_url = scraper.parse_book_list(soup, url=url)
             for item in list_data:
-                #row_id = db_tools.insert_or_update_common(item, db_tools.tbl_name_books)
-                row_id = db_tools.insert_books_index(item)
+                row_id, affected_rows = db_tools.insert_books_index(item)
                 if row_id:
                     logging.debug(f"insert one book. row_id: {row_id}, name: {item['name']}")
                 else:
                     logging.warning(f"insert book error. name: {item['name']}, href: {item['href']}")
+                updated_books = updated_books + (affected_rows if affected_rows else 0)
             if next_url is None:
-                logging.info(f'get all pages.')
+                logging.info(f"get all pages. updated books: {updated_books}")
                 return True
             else:
                 url = next_url

aabook/src/sqlite_utils.py

@@ -134,14 +134,14 @@ def insert_books_index(data):
 
         if existing_book:  # **如果演员已存在**
             logging.debug(f"book {data['href']} already exist. id: {existing_book[0]}")
-            return existing_book[0]
+            return existing_book[0], 0
         
         # 不存在，或者需要更新
         data['is_latest'] = 0
-        return insert_or_update_common(data, tbl_name_books)
+        return insert_or_update_common(data, tbl_name_books), 1
     except sqlite3.Error as e:
         logging.error(f"Error inserting or updating data: {e}")
-        return None
+        return None, 0
     
 # 更新详细信息
 def update_book_detail(data):
@@ -302,6 +302,7 @@ def get_statics():
 
     all_chapters = 0
     all_chapters_has_contents = 0
+    finished_books = 0
 
     # 循环遍历 0 到 100 的数字
     for i in range(100):
@@ -313,11 +314,25 @@ def get_statics():
             cursor.execute(f"SELECT COUNT(*) FROM {table_name} where has_content=1")
             all_chapters_has_contents += cursor.fetchone()[0]
 
+            # 统计已经下载完的书籍总数
+            sql = f"""
+                SELECT COUNT(*)
+                FROM (
+                    SELECT book_id
+                    FROM {table_name}
+                    GROUP BY book_id
+                    HAVING SUM(CASE WHEN has_content = 1 THEN 1 ELSE 0 END) = COUNT(*)
+                )
+            """
+            cursor.execute(sql)
+            finished_books += cursor.fetchone()[0]
+
         except sqlite3.Error as e:
             logging.debug(f"Error querying table {table_name}: {e}")
     
     result['all_chapters'] = all_chapters
     result['all_chapters_has_contents'] = all_chapters_has_contents
+    result['finished_books'] = finished_books
 
     return result