modify scripts

javdb/src/fetch.py

@@ -160,6 +160,8 @@ def fetch_performers_detail():
         if len(perfomers_list) < 1:
             logging.info(f'all performers fetched.')
             break
+
+        succ_rows = 0
         for performer in perfomers_list:
             url = performer['href']
             person = performer['name']
@@ -168,8 +170,9 @@ def fetch_performers_detail():
 
             next_url = url
             all_movies = []
+            need_insert = True
             while next_url:
-                logging.info(f"Fetching data for actor ({person}), url {next_url} ...")
+                logging.debug(f"Fetching data for actor ({person}), url {next_url} ...")
                 soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="span", identifier="actor-section-name", attr_type="class"))
                 if soup:
                     data, next_url = scraper.parse_actor_detail(soup, next_url)
@@ -179,10 +182,21 @@ def fetch_performers_detail():
                         all_movies.extend(data.get('movies', []))
 
                 elif status_code  and status_code == 404:
-                    logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}, Skiping...')
+                    actor_id = db_tools.insert_or_update_actor_404(name=person, href=url, is_full_data=2)
+                    logging.warning(f'404 page. id: {actor_id}, name: ({person}), url: {url}, Skiping...')
+                    need_insert = False
+                    break
+                elif status_code  and status_code == 401:
+                    actor_id = db_tools.insert_or_update_movie_404(name=person, href=url, is_full_data=3)
+                    logging.warning(f'401 page(need login). id: {actor_id}, name: ({person}), url: {url}, Skiping...')
+                    need_insert = False
                     break
                 else:
-                    logging.warning(f'fetch_page error. person: ({person}), url: {url}')
+                    logging.warning(f'fetch_page error. url: {url}')
+
+            # 如果出现了401或者404，已经处理，直接跳过
+            if not need_insert:
+                continue
                         
             # 获取完了个人的所有影片，开始插入数据
             performer_id = db_tools.insert_or_update_actor({
@@ -193,11 +207,14 @@ def fetch_performers_detail():
                 'credits':all_movies
             })
             if performer_id:
-                logging.info(f'insert one person, id: {performer_id}, person: ({person}), url: {url}')
+                logging.debug(f'insert one person, id: {performer_id}, person: ({person}), url: {url}')
                 last_perfomer_id = performer_id
+                succ_rows += 1
             else:
                 logging.warning(f'insert person: ({person}) {url} failed.')
             time.sleep(0.5)
+        
+        logging.info(f'total request: {len(perfomers_list)}, succ: {succ_rows}, last performer id: {last_perfomer_id}')
         # 调试break
         if debug:
             return True

javdb/src/sqlite_utils.py

@@ -172,6 +172,34 @@ def insert_or_update_actor(actor):
         logging.error(f"插入/更新演员 {actor['name']} 失败: {e}")
         conn.rollback()
 
+# """插入或更新电影数据(异常url的处理，比如404链接)"""
+def insert_or_update_actor_404(name, href, is_full_data=1):
+    try:
+        # 插入或更新电影信息
+        cursor.execute(
+            """
+            INSERT INTO javdb_actors (name, href, is_full_data, updated_at)
+            VALUES (?, ?, ?, datetime('now', 'localtime'))
+            ON CONFLICT(href) DO UPDATE SET 
+                name=excluded.name, is_full_data=excluded.is_full_data, updated_at = datetime('now', 'localtime')
+            """,
+            (name, href, is_full_data)
+        )
+        conn.commit()
+        
+        # 获取插入的 movie_id
+        actor_id = get_id_by_href('javdb_actors', href)
+        if actor_id is None:
+            return None
+                        
+        return actor_id
+        
+    except Exception as e:
+        conn.rollback()
+        logging.error("Error inserting movie: %s", e)
+        return None
+
+
 # 删除演员
 def delete_actor_by_href(href):
     try: