modify scripts

scrapy_proj/scrapy_proj/extensions/stats_extension.py

@@ -76,6 +76,14 @@ class StatsExtension:
 
         # 获取当前统计信息
         stats = self.stats.get_stats()
+        # 获取spider自定义的信息
+        spider_stat = {'sp': '-------'}
+        prefix = f"{self.spider_name}/"
+        for key, value in stats.items():
+            if key.startswith(prefix):
+                short_key = key.replace(prefix, "", 1)
+                spider_stat[short_key] = value
+
         # 构建统计摘要
         stats_summary = {
             'spider': self.spider_name,
@@ -87,6 +95,8 @@ class StatsExtension:
             '404_cnt': stats.get('downloader/response_status_count/404', 0),
             'log_err_cnt': stats.get('log_count/ERROR', 0),
             'status': self.current_status,
+            **spider_stat,
+            'db': '-------',
             **db_stat
         }
         

scrapy_proj/scrapy_proj/spiders/clm_spider.py

@@ -99,6 +99,10 @@ class ClmSpider(BaseSpider):
                 callback=self.handle_redirect
             )
 
+        # 添加统计项
+        self.crawler.stats.set_value(f"{self.name}/req_words_all", len(keywords))
+        self.crawler.stats.set_value(f"{self.name}/req_words_done", 0)
+
     # 处理POST过来的302请求
     def handle_redirect(self, response):
         """处理302重定向，获取location并访问结果页面"""
@@ -242,6 +246,7 @@ class ClmSpider(BaseSpider):
             self.logger.info(f'debug模式下停止翻页. {total_text}. url: {response.url}')  
             return
         elif not need_next or not next_page_url: 
+            self.crawler.stats.inc_value(f"{self.name}/req_words_done")
             total_rows = db_clm.get_count_by_keywords_id(response.meta.get('words_id', 0))
             curr_words = response.meta.get('words', '')
             self.logger.info(f'停止翻页. 更新模式: {self.update_mod}. {total_text}, 共 {total_rows} 条记录。 key words: ({curr_words}), url: {response.url}')  

scrapy_proj/scrapy_proj/spiders/pornbox_spider.py

@@ -70,6 +70,8 @@ class PornboxSpider(BaseSpider):
         if self.cmd_studio in self.cmd_list:
             url = self._build_studio_list_url()
             yield scrapy.Request(url, callback=self.parse_studios_list)
+            self.crawler.stats.set_value(f"{self.name}/req_list_all", 0)
+            self.crawler.stats.set_value(f"{self.name}/req_list_done", 0)
 
         # 获取每个stutio, 获取详情
         if self.cmd_movie in self.cmd_list:
@@ -80,7 +82,10 @@ class PornboxSpider(BaseSpider):
             for stu in stu_list:
                 url = self._build_studio_url(stu['label_id'])
                 yield scrapy.Request(url, callback=self.parse_studio, meta={'stu_id':stu['label_id'], 'name': stu['name'], 'scene_count': stu['scene_count']})
-
+            
+            # 添加统计项
+            self.crawler.stats.set_value(f"{self.name}/req_mov_all", len(stu_list))
+            self.crawler.stats.set_value(f"{self.name}/req_mov_done", 0)
 
     def parse_studios_list(self, response):
         # 尝试解析 JSON 响应
@@ -100,6 +105,8 @@ class PornboxSpider(BaseSpider):
         current_page = data.get('current_page', 1)
         total_pages = data.get('total_pages', 1)
         
+        self.crawler.stats.inc_value(f"{self.name}/req_list_done")
+        self.crawler.stats.set_value(f"{self.name}/req_list_all", total_pages)
         self.logger.info(f"url: {response.url}, total: {total_pages}, items: {len(data.get('items', []))}")
 
         # 处理每个工作室项目
@@ -214,6 +221,7 @@ class PornboxSpider(BaseSpider):
         stu_name = response.meta['name']
         scene_count = response.meta['scene_count']
         if not need_next or current_page >= total_pages or (self.debug and current_page >= 50000): 
+            self.crawler.stats.inc_value(f"{self.name}/req_mov_done")
             total_rows = db_tools.get_stu_mov_count(stu_id)
             self.logger.info(f'停止翻页. 更新模式: {self.update_mod}. studio: ({stu_name}), total movies: {total_rows}, scene_count: {scene_count}, url: {response.url}')  
             return