更新YutianTopSpider爬虫以处理公司和职位信息的保存逻辑，增加错误处理和公司ID回写功能

TS_resume_spider/pipelines.py

@@ -120,6 +120,24 @@ class YTSavePipeline:
 
 class CompanySavePipeline:
     def process_item(self, item, spider):
+        if spider.name == 'yutian_top_compary':
+            company = item.get("company")
+            if not company:
+                return item
+            if 'website' in company:
+                company['website_id'] = company.pop('website')
+            company_name = company.get("name")
+            website_id = company.get("website_id")
+            if not company_name or not website_id:
+                return item
+            try:
+                DB.insert_company(company)
+                # 设置 company_id 回写
+                item["position"]["company_id"] = DB.get_company_id(company_name)
+            except Exception as e:
+                spider.logger.warning(f"❌ 写入失败：company_name={company_name}, 错误={e}")
+            return item
+
         if spider.name not in ['zhrczp_com_compary']:
             return item
 
@@ -138,6 +156,19 @@ class CompanySavePipeline:
 
 class PositionSavePipeline:
     def process_item(self, item, spider):
+        if spider.name == 'yutian_top_compary':
+            position = item.get("position")
+            if not position:
+                return item
+            title = position.get("title")
+            if not title:
+                return item
+            try:
+                DB.insert_position(position)
+            except Exception as e:
+                spider.logger.warning(f"❌ 写入失败：title={title}, company_id={position.get('company_id')}, 错误={e}")
+            return item
+
         if spider.name not in ['zhrczp_com_position']:
             return item