How to filter tweets based on input location's boundary box (City, country, area) in tweepy API python – Twitter API

I am trying to filter the tweet stream based on both input keyword and location (variables).

If I want to filter tweets based on keyword and a certain location, locations parameters in line below

myStream.filter(track=keywords_to_track, locations=boundary_box)

should be a boundary box with four coordinates of the input location (maxlog, minlog, maxlat, minlag)

how to get boundary_box for a given location(variable)?
or
is there any other way to solve this issue?

I have also tried https://www.mapdevelopers.com/geocode_bounding_box.php, but it’s not working.

I am new to tweepy API.

# arguments
topic_name = 'kafkatwitter_1'

#input variables
keywords_to_track = ['modi']
location_filter = 'New Delhi'

# twitter authorization
auth = OAuthHandler(API_KEY, API_KEY_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_SECRET)

# init tweepy
api = tweepy.API(auth)
producer = KafkaProducer(bootstrap_servers=['localhost:9092'],
                         value_serializer=lambda x: dumps(x).encode('utf-8'),
                         api_version=(0, 10, 1))
class MyStreamListener(tweepy.Stream):
    def on_status(self, tweet):
        length = len(tweet.text.split(' '))
        if (tweet.lang != 'en') or (length <= 10):
            pass
            print("==filtered==")
        else:
            message = {
                "text": tweet.text,
                "created_at": process_time(tweet.created_at),}
        producer.send(topic_name, value=message)
# Step 2: Creating a Stream
myStreamListener = MyStreamListener()
myStream = tweepy.Stream(auth=api.auth, listener=myStreamListener)

# Step 3: Starting a Stream
myStream.filter(track=keywords_to_track, locations=boundary_box)