元博网 - 修复重复Object_id导致数据不保存问题

ybw/detail_spider.py

@@ -189,13 +189,11 @@ class DetailSpider:
         item["comeintime"] = int2long(int(time.time()))
         '''检查清洗之后的详情'''
         CheckText(item["detail"])
-        del item['count'], item['crawl']
-        if 'crawl_status' in item:
-            del item['crawl_status']
-        try:
-            self.save_tab.insert_one(item)
-        except DuplicateKeyError:
-            pass
+        insert = {}
+        for key, val in item.items():
+            if key not in ['crawl_status', 'crawl', 'count', '_id']:
+                insert[key] = val
+        self.save_tab.insert_one(insert)
         logger.info('[采集成功]{}-{}'.format(item['title'], item['publishtime']))
 
     def crawl_spider(self, sc: Scheduler):