modify scripts

src/crawling/craw.py

@@ -178,6 +178,7 @@ class JavbusCrawler(GenericCrawler):
         """
         result = {
             'avatar': {},
+            'title' : {},
             'movies': []
         }
         
@@ -189,6 +190,9 @@ class JavbusCrawler(GenericCrawler):
             else:
                 logging.debug(f"avatar-box not found. href: {href}")
             
+            # 解析页面上的title，获取影片数量等信息
+            result['title'] = self.parse_title_info(soup, href)
+            
             # 解析影片列表
             movie_boxes = soup.find_all('a', class_='movie-box')
             if movie_boxes:
@@ -336,17 +340,9 @@ class JavbusCrawler(GenericCrawler):
             
         return movie_info
 
-
-    # 获取演员详情
-    def parse_studios_labels_series_detail(self, soup, href):
-        """
-        解析Javbus网页内容，提取演员信息和影片列表
-        """
-        result = {
-            'meta': {},
-            'movies': []
-        }
-        
+    # 获取页面头部的信息
+    def parse_title_info(self, soup, href):
+        title_info = {}
         try:           
             # 解析标题
             b_tag = soup.select_one('.alert.alert-success.alert-common p b')
@@ -367,8 +363,8 @@ class JavbusCrawler(GenericCrawler):
                     # 提取前两个元素作为工作室和角色
                     studio = parts[video_index - 2]
                     role = parts[video_index - 1]
-                    result['meta']['title'] = studio
-                    result['meta']['role'] = role
+                    title_info['title'] = studio
+                    title_info['role'] = role
                 else:
                     logging.debug(f"无法按规则解析: {' - '.join(parts)}")
                 
@@ -384,13 +380,31 @@ class JavbusCrawler(GenericCrawler):
                     if '全部影片' in text:
                         match = re.search(r'全部影片\s*(\d+)\s*', text)
                         if match:
-                            result['meta']['movies_cnt'] = int(match.group(1))
+                            title_info['movies_cnt'] = int(match.group(1))
                     
                     # 提取已有磁力数量
                     if '已有磁力' in text:
                         match = re.search(r'已有磁力\s*(\d+)\s*', text)
                         if match:
-                            result['meta']['magnet_cnt'] = int(match.group(1))
+                            title_info['magnet_cnt'] = int(match.group(1))
+        except Exception as e:
+            logging.warning(f"parse html error: {str(e)}, href: {href}", exc_info=True)
+
+        return title_info
+
+    # 获取演员详情
+    def parse_studios_labels_series_detail(self, soup, href):
+        """
+        解析Javbus网页内容，提取演员信息和影片列表
+        """
+        result = {
+            'meta': {},
+            'movies': []
+        }
+        
+        try:           
+            # 解析标题
+            result['meta'] = self.parse_title_info(soup, href)
 
             div_waterfall = soup.find('div', id='waterfall')
             if not div_waterfall: