removed twint get just use fh.search_time_range

modules/FirehoseJob.py

@@ -717,10 +717,11 @@ def search_time_range(self,
             logger.debug('hits %s to %s: %s', t0, t1, len(df))
             if self.save_to_neo:
                 logger.debug('writing to neo4j')
-                df2 = Neo4jDataAccess(self.neo4j_creds).save_twintdf_to_neo(df, job_name, job_id)
+                df = tp.check_hydrate(df)
+                res = Neo4jDataAccess(self.neo4j_creds).save_twintdf_to_neo(df, job_name, job_id)
                 # df3 = Neo4jDataAccess(self.debug, self.neo4j_creds).save_df_to_graph(df2, job_name)
                 logger.debug('wrote to neo4j, # ', len(df2))
-                yield df2
+                yield res
             else:
                 yield df
         logger.debug('done')

modules/TwintPool.py

@@ -68,22 +68,7 @@ def _get_timeline(self, username, limit):
         tweets_df = twint.storage.panda.Tweets_df
         return tweets_df
 
-    def twint_get(self, Search, Since, Until, job_name, Limit, **kwargs):
-        from .FirehoseJob import FirehoseJob
-        neo4j_creds = None
-        with open('../neo4jcreds.json') as json_file:
-            neo4j_creds = json.load(json_file)
-        fh = FirehoseJob(neo4j_creds=neo4j_creds, PARQUET_SAMPLE_RATE_TIME_S=30, save_to_neo=False, writers={})
-        dfs = []
-        for df in fh.search_time_range(
-                Search=Search,
-                Since=Since,
-                Until=Until,
-                job_name=job_name,
-                Limit=Limit):
-            dfs.append(df)
-        df = pd.concat(dfs)
-        return df
+
 
     def _get_user_info(self, username):
         self.config.User_full = True