(#29)

* Separate `get_article` function to `get_article_by_id` and `get_article_by_url` * Fix `get_many` function in `mongodb_driver`
all-news-project · Jun 8, 2023 · 15b2c3a · 15b2c3a
1 parent 2611046
commit 15b2c3a
Show file tree

Hide file tree

Showing 4 changed files with 17 additions and 4 deletions.
diff --git a/api/server_api/api_logic.py b/api/server_api/api_logic.py
@@ -25,7 +25,7 @@ def get_similar_articles_data(self, article_url: str) -> List[ArticleApiData]:
         """
         self.server_logger.debug(f"Checking similar articles to article -> `{article_url}`")
         similar_articles: List[ArticleApiData] = list()
-        article_object: Article = self._article_utils.get_article(article_url=article_url)
+        article_object: Article = self._article_utils.get_article_by_url(article_url=article_url)
 
         if not article_object:
             desc = f"Didn't find article in db with article url: `{article_url}`"

diff --git a/db_driver/mongodb_driver.py b/db_driver/mongodb_driver.py
@@ -194,7 +194,7 @@ def get_many(self, table_name: str, data_filter: dict) -> List[dict]:
             if res:
                 object_id = res.cursor_id
                 self.logger.info(f"Got data from db: '{self.DB_NAME}', table_name: '{table_name}', id: '{object_id}'")
-                return list(dict(res))
+                return list(res)
             else:
                 desc = f"Error find data with filter: {data_filter}, table: '{table_name}', db: '{self.DB_NAME}'"
                 self.logger.warning(desc)

diff --git a/server_utils/db_utils/article_utils.py b/server_utils/db_utils/article_utils.py
@@ -57,7 +57,19 @@ def get_unclassified_article(self, required_filter_data: dict = None, get_random
 
         return Article(**article)
 
-    def get_article(self, article_url: str) -> Union[Article, None]:
+    def get_article_by_id(self, article_id: str) -> Union[Article, None]:
+        article = None
+        data_filter = {"article_id": article_id}
+        try:
+            article_data = self._db.get_one(table_name=DBConsts.ARTICLE_TABLE_NAME, data_filter=data_filter)
+            article_object: Article = get_db_object_from_dict(object_dict=article_data, class_instance=Article)
+            article = article_object
+        except DataNotFoundDBException as e:
+            self.logger.warning(f"Error get article by article id: `{article_id}` - {str(e)}")
+        self.logger.info(f"Got article from db, article_id: `{article.article_id}`, url: `{article.url}`")
+        return article
+
+    def get_article_by_url(self, article_url: str) -> Union[Article, None]:
         article = None
         data_filter = {"url": article_url}
         try:
@@ -70,6 +82,7 @@ def get_article(self, article_url: str) -> Union[Article, None]:
         return article
 
     def get_articles(self, articles_id: List[str]) -> List[Article]:
+        # todo: separate this function to: get_articles_by_ids and get_articles_by_urls
         articles: List[Article] = []
         data_filter = {"article_id": {"$in": articles_id}}
         articles_data = self._db.get_many(table_name=DBConsts.ARTICLE_TABLE_NAME, data_filter=data_filter)

diff --git a/server_utils/db_utils/cluster_utils.py b/server_utils/db_utils/cluster_utils.py
@@ -48,6 +48,6 @@ def get_cluster(self, cluster_id: str) -> Cluster:
 # For debug
 if __name__ == '__main__':
     article_utils = ArticleUtils()
-    new_article: Article = article_utils.get_article(article_url="https://www.bbc.com/news/world-europe-65471904")
+    new_article: Article = article_utils.get_article_by_url(article_url="https://www.bbc.com/news/world-europe-65471904")
     cluster_utils = ClusterUtils()
     cluster_utils.create_new_cluster(article=new_article, classified_categories=["finance", "bitcoin"])