习近平讲话数据库

习近平讲话/1.py

-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
@@ -61,11 +61,11 @@ def newsdata(art_content_dict,art_type_dict,dic_lables):
             del post_dict['tags']
             del post_dict['title_pd']
             # 发送kafka
-            # producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], max_request_size=1024 * 1024 * 20)
-            # kafka_result = producer.send("research_center_fourth",
-            #                              json.dumps(post_dict, ensure_ascii=False).encode('utf8'))
-            #
-            # print(kafka_result.get(timeout=10))
+            producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], max_request_size=1024 * 1024 * 20)
+            kafka_result = producer.send("research_center_fourth",
+                                         json.dumps(post_dict, ensure_ascii=False).encode('utf8'))
+
+            print(kafka_result.get(timeout=10))
 
             dic_result = {
                 'success': 'ture',
@@ -127,9 +127,9 @@ def get_content():
         for data_dict in data_list[:1]:
             article_id = data_dict['article_id']
             print(type(article_id))
-            # is_article_id = db_storage.find_one({'id': f"1534423014825668610{article_id}"})
-            # if is_article_id:
-            #     continue
+            is_article_id = db_storage.find_one({'id': f"1534423014825668610{article_id}"})
+            if is_article_id:
+                continue
             title = data_dict['title'] # 采集到的标题
             pub_time = data_dict['input_date']
             current_date = datetime.now()