filter by keywords OR accounts

collectTweets.py

@@ -101,8 +101,11 @@ if __name__ == '__main__':
 
     # Get twitter ID of account
     accounttofollowed = pd.read_csv("params/accountsFollowed.csv")
-    accounttofollowedlist = accounttofollowed['twitterID'].tolist()
-    accounttofollowedlist = list(map(str, accounttofollowedlist))
+    accounttofollowedlist = list(map(str,accounttofollowed['twitterID'].tolist()))
+
+    # Get hashtag to track
+    hashtagtracked = pd.read_csv("params/keywordsFilter.csv")
+    hashtagtrackedList = list(map(str, hashtagtracked['hashtags'].tolist()))
 
     # Start a Twitter stream
     timestr = time.strftime("%Y%m%d-%H%M%S")
@@ -112,7 +115,7 @@ if __name__ == '__main__':
     stream = tweepy.Stream(auth=api.auth, listener=myStreamListener)
     try:
         logger.info("Start streaming")
-        stream.filter(follow=accounttofollowedlist)
+        stream.filter(follow=accounttofollowedlist, track=hashtagtrackedList)
     except KeyboardInterrupt as e:
         logger.info("Stream Keyboard Interrupt")
     finally:

params/keywordsFilter.csv

+hashtags,disease,add_date
+coronavirus,covid19,2020-06-11
+covid-19,covid19,2020-06-11
+covid19,covid19,2020-06-11
+ncov,covid19,2020-06-11
+2019-ncov,covid19,2020-06-11
+n-cov2019,covid19,2020-06-11
+ncov2019,covid19,2020-06-11