Tweepy syntax and Twitter streaming api - python

So far I have the following code that works and inserts the tweets into my mongodb but I had a few questions.
class CustomStreamListener(tweepy.StreamListener):
def __init__(self, api):
self.api = api
super(tweepy.StreamListener, self).__init__()
self.db = pymongo.MongoClient().test
def on_data(self, tweet):
self.db.tweets.insert(json.loads(tweet))
def on_error(self, status_code):
return True # Don't kill the stream
def on_timeout(self):
return True # Don't kill the stream
sapi = tweepy.streaming.Stream(auth, CustomStreamListener(api))
sapi.filter(track=['arsenal'] , languages = ['en'])
Could someone explain how I can get only certain parts of the tweet inserted into the database ie. just the tweet text and location.
Does the twitter streaming api allow displaying just tweets no # reply tweets?

json.loads(tweet) is just a dictionary, you can freely choose what parts of its key-values you process.
You can filter tweets by conditioning them either way you like:
tweet_obj = json.loads(tweet)
if not tweet_obj['in_reply_to_user_id']: # replies has `None` in this field
pass # add some processing here

Related

How to automatically generate partition keys for messages (Kafka + Python)?

I'm trying to generate keys for every message in Kafka, for that purpose I want to create a key generator that joins the topic first two characters and the tweet id.
Here is an example of the messages that get sent in kafka:
{"data":{"created_at":"2022-03-18T09:51:12.000Z","id":"1504757303811231755","text":"#Danielog111 #POTUS #NATO #UNPeacekeeping #UN Yes! Not to minimize Ukraine at all, but to bring attention to a horrific crisis and Tigrayan genocide that targets 7M people, longer time frame, and is largely unacknowledged by western news agencies. And people are being eaten-literally! #maddow #JoyAnnReid help Ethiopians!"},"matching_rules":[{"id":"1502932028618072070","tag":"NATO"},{"id":"1502932021731115013","tag":"Biden"}]}'
And here is my code modified to try generating partition keys (I'm using PyKafka):
from dotenv import load_dotenv
import os
import json
import tweepy
from pykafka import KafkaClient
# Getting credentials:
BEARER_TOKEN=os.getenv("BEARER_TOKEN")
# Setting up pykafka:
def get_kafka_client():
return KafkaClient(hosts='localhost:9092,localhost:9093,localhost:9094')
def send_message(data, name_topic, id):
client = get_kafka_client()
topic = client.topics[name_topic]
producer = topic.get_sync_producer()
producer.produce(data, partition_key=f"{name_topic[:2]}{id}")
# Creating a Twitter stream listener:
class Listener(tweepy.StreamingClient):
def on_data(self, data):
print(data)
message = json.loads(data)
for rule in message['matching_rules']:
send_message(data, rule['tag'], message['data']['id'].encode())
return True
def on_error(self, status):
print(status)
# Start streaming:
Listener(BEARER_TOKEN).filter(tweet_fields=['created_at'])
And this is the error I'm getting:
File "/Users/mac/.local/share/virtualenvs/tweepy_step-Ck3DvAWI/lib/python3.9/site-packages/pykafka/producer.py", line 372, in produce
raise TypeError("Producer.produce accepts a bytes object as partition_key, "
TypeError: ("Producer.produce accepts a bytes object as partition_key, but it got '%s'", <class 'str'>)
I've also tried not encoding it and trying to fetch the id just using the data (that comes in bytes) but none of these options work.
I found the error, I should've been encoding the partition key and not the json id:
def send_message(data, name_topic, id):
client = get_kafka_client()
topic = client.topics[name_topic]
producer = topic.get_sync_producer()
producer.produce(data, partition_key=f"{name_topic[:2]}{id}".encode())
# Creating a Twitter stream listener:
class Listener(tweepy.StreamingClient):
def on_data(self, data):
print(data)
message = json.loads(data)
for rule in message['matching_rules']:
send_message(data, rule['tag'], message['data']['id'])
return True
def on_error(self, status):
print(status)

How to store only the text of tweet using Tweepy

I'm watching this series https://www.youtube.com/watch?v=wlnx-7cm4Gg&list=PL5tcWHG-UPH2zBfOz40HSzcGUPAVOOnu1 which is about mining tweets with tweepy (python) and the guy stores the tweets with everything ( such as created_at, id, id_str, text) and then he uses Dataframes in pandas to store only the text. Is this way efficient ? How Can I only store the "text" in the Json file instead of all other details ?
The code:
ACCESS_TOKEN = "xxxxxxxxxxxxxxxxxxxxx"
ACCESS_TOKEN_SECRET = "xxxxxxxxxxxxxxxxxxxxxxxxx"
CONSUMER_KEY = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
CONSUMER_SECRET = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
import tweepy
import numpy as np
import pandas as pd
# import twitter_credentials
class TwitterAuthenticator():
def authenticate_twitter_app(self):
auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
return auth
class TwitterStreamer():
"""
Class for streaming and processing live tweets.
"""
def __init__(self):
self.twitter_authenticator = TwitterAuthenticator()
def stream_tweets(self, fetched_tweets_filename, hash_tag):
# This handles Twitter authetification and the connection to Twitter Streaming API
listener = TwitterListener(fetched_tweets_filename)
auth = self.twitter_authenticator.authenticate_twitter_app()
# api = tweepy.API(auth)
stream = tweepy.Stream(auth,listener)
stream.filter(track = hash_tag)
class TwitterListener(tweepy.StreamListener):
"""
This is a basic listener class that just prints received tweets to stdout.
"""
def __init__(self, fetched_tweets_filename):
self.fetched_tweets_filename = fetched_tweets_filename
def on_data(self, data):
try:
print(data)
with open(self.fetched_tweets_filename, 'a') as tf:
tf.write(data)
return True
except BaseException as e:
print("Error on_data %s" % str(e))
return True
def on_status(self, status):
print(status)
def on_error(self, status):
if status == 420:
# Returning False on_data method in case rate limit occurs.
return False
print(status)
# public_tweets = api.home_timeline()
# for tweet in public_tweets:
# print tweet.text
if __name__ == '__main__':
hash_tag = ["python"]
fetched_tweets_filename = "tweets.json"
twitter_streamer = TwitterStreamer()
twitter_streamer.stream_tweets(fetched_tweets_filename,hash_tag)
# print stream.text
The tweet stored in the json file:
{"created_at":"Sun Nov 04 18:43:59 +0000 2018","id":1059154305498972160,"id_str":"1059154305498972160","text":"RT #hmason: When you want to use a new algorithm that you don't deeply understand, the best approach is to implement it yourself to learn h\u2026","source":"\u003ca href=\"http:\/\/twitter.com\/download\/android\" rel=\"nofollow\"\u003eTwitter for Android\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":14858491,"id_str":"14858491","name":"Alexandra Lemus","screen_name":"nankyoku","location":"M\u00e9xico","url":null,"description":"Transitioning into the Permanent Beta state...","translator_type":"none","protected":false,"verified":false,"followers_count":173,"friends_count":585,"listed_count":18,"favourites_count":658,"statuses_count":572,"created_at":"Wed May 21 16:35:49 +0000 2008","utc_offset":null,"time_zone":null,"geo_enabled":true,"lang":"es","contributors_enabled":false,"is_translator":false,"profile_background_color":"EDECE9","profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme3\/bg.gif","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme3\/bg.gif","profile_background_tile":false,"profile_link_color":"088253","profile_sidebar_border_color":"D3D2CF","profile_sidebar_fill_color":"E3E2DE","profile_text_color":"634047","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/378800000575875952\/f00390453684dd243d7ca95c69a05f74_normal.jpeg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/378800000575875952\/f00390453684dd243d7ca95c69a05f74_normal.jpeg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/14858491\/1381524599","default_profile":false,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"retweeted_status":{"created_at":"Sat Nov 03 17:36:24 +0000 2018","id":1058774912201035776,"id_str":"1058774912201035776","text":"When you want to use a new algorithm that you don't deeply understand, the best approach is to implement it yoursel\u2026 https:\/\/t.co\/9F7SmlGfyf","source":"\u003ca href=\"http:\/\/twitter.com\" rel=\"nofollow\"\u003eTwitter Web Client\u003c\/a\u003e","truncated":true,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":765548,"id_str":"765548","name":"Hilary Mason","screen_name":"hmason","location":"NYC","url":"http:\/\/www.hilarymason.com","description":"GM for Machine Learning at #Cloudera. Founder at #FastForwardLabs. Data Scientist in Residence at #accel. I \u2665 data and cheeseburgers.","translator_type":"none","protected":false,"verified":true,"followers_count":111311,"friends_count":1539,"listed_count":5276,"favourites_count":12049,"statuses_count":17602,"created_at":"Sun Feb 11 21:22:24 +0000 2007","utc_offset":null,"time_zone":null,"geo_enabled":false,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"000000","profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_tile":false,"profile_link_color":"282F8A","profile_sidebar_border_color":"87BC44","profile_sidebar_fill_color":"AB892B","profile_text_color":"000000","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/948689418709323777\/sTBM3vG0_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/948689418709323777\/sTBM3vG0_normal.jpg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/765548\/1353033581","default_profile":false,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"is_quote_status":false,"extended_tweet":{"full_text":"When you want to use a new algorithm that you don't deeply understand, the best approach is to implement it yourself to learn how it works, and then use a library to benefit from robust code.\n\nHere's one article showing this with neural networks in Python: https:\/\/t.co\/3ehO86NFKI","display_text_range":[0,280],"entities":{"hashtags":[],"urls":[{"url":"https:\/\/t.co\/3ehO86NFKI","expanded_url":"https:\/\/towardsdatascience.com\/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6","display_url":"towardsdatascience.com\/how-to-build-y\u2026","indices":[257,280]}],"user_mentions":[],"symbols":[]}},"quote_count":14,"reply_count":8,"retweet_count":290,"favorite_count":1019,"entities":{"hashtags":[],"urls":[{"url":"https:\/\/t.co\/9F7SmlGfyf","expanded_url":"https:\/\/twitter.com\/i\/web\/status\/1058774912201035776","display_url":"twitter.com\/i\/web\/status\/1\u2026","indices":[117,140]}],"user_mentions":[],"symbols":[]},"favorited":false,"retweeted":false,"possibly_sensitive":false,"filter_level":"low","lang":"en"},"is_quote_status":false,"quote_count":0,"reply_count":0,"retweet_count":0,"favorite_count":0,"entities":{"hashtags":[],"urls":[],"user_mentions":[{"screen_name":"hmason","name":"Hilary Mason","id":765548,"id_str":"765548","indices":[3,10]}],"symbols":[]},"favorited":false,"retweeted":false,"filter_level":"low","lang":"en","timestamp_ms":"1541357039223"}
If the question is not clear then please comment it out and I will try to edit the question.
If you want only the "text" field to be saved in the json file, you can tweak the definition of the TwitterListener.on_data method:
import json
def on_data(self, data):
try:
print(data)
with open(self.fetched_tweets_filename, 'a') as tf:
json_load = json.loads(data)
text = {'text': json_load['text']}
tf.write(json.dumps(text))
return True
except BaseException as e:
print("Error on_data %s" % str(e))
return True
Fair warning, I don't have tweepy installed/set up, so I was only able to test a version of the above code using the json file you posted above. Let me know if you run into any bugs and I'll see what I can do.
It looks like what you're getting from the API and storing in your variable "data" is unicode text in a json format. You are just writing that text directly to a file. Using the API call you do, you're always going to get all of the data so it isn't that inefficient. If you just wanted to get/write the text of the tweet, try using a json load and then processing from there.

Twitter Streaming - Find Top 10 trending topics | PySpark

Am doing a project to find top 10 trending topics or hashtags on Twitter. Am creating a class with the code below:
class TweetsListener(StreamListener):
def __init__(self, csocket):
self.client_socket = csocket
def on_data(self, data):
try:
msg = json.loads( data )
print(msg['user']['screen_name'].encode('utf-8'))
return True
except BaseException as e:
print("Error on_data: %s" % str(e))
return True
def on_error(self, status):
print(status)
return True
Below is the code for sending data:
def sendData(c_socket):
auth = OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_secret)
twitter_stream = Stream(auth, TweetsListener(c_socket))
twitter_stream.filter(track=['india']
Here twitter_stream.filter is filtering messages with tag India. I want to get all the messages from Twitter. In short, I do not want a filter to be applied. Is there a way to do the same?
Any help appreciated.
- P.S : Novice in Spark streaming and PySpark
Twitter now offers a sample stream: https://developer.twitter.com/en/docs/tweets/sample-realtime/overview/GET_statuse_sample.html
It's fairly new so I'm not sure if the wrappers (looks like you're using Tweepy) have implemented it yet, but it shouldn't be hard to interface with.

Avoid error 420s with streaming API tweepy

I made a python script which uses tweepy streaming module to stream mentions to a twitter account and carry some functions based on the status text.
I wanted it to stream until a mention is made, next stop streaming, carry some functions based on the status text and again start streaming.
This is my code:
class StdOutListener(tweepy.StreamListener):
def on_data(self, data):
tweet = json.loads(data.strip())
global d
d=tweet
return False #stops streaming after a tweet is fed to it
def on_error(self, status_code):
print(status_code)
time.sleep(120)
return F # To continue listening
def on_timeout(self)
time.sleep(120)
return True # To continue listening
while True:
d={}
listener = StdOutListener()
stream = tweepy.Stream(twitter_auth(tokens), listener)
stream.filter(track=['#xxx'])
stream.disconnect()
doSomething(d)
But it only works for one loop and later shows 420(Exceeding Rate Limit) errors,even though I just take in a single tweet (per stream, if I'm not wrong).
Can anyone please explain where I'm doing it wrong? And also when should we use async mode in tweepy stream listener?

Can not connect to Twitter using Tweepy Streaming

Trying to check whether connection established or not, but nothing happened
I used on_connect to understand but got nothing:
import tweepy
import time
class InOutStreamListener(tweepy.StreamListener):
def on_connect(self):
print 'Connected'
def disconnect(self):
if self.running is False:
return
self.running = False
def on_friends(self, friends):
print friends[0]
auth = tweepy.OAuthHandler('code', 'code')
auth.set_access_token('code', 'code')
l = InOutStreamListener()
streamer = tweepy.Stream(auth, l)
time.sleep(15)
streamer.disconnect()
You only created a Stream, you didn't start it, see the docs.
In this example we will use filter to stream all tweets containing the
word python. The track parameter is an array of search terms to
stream.
myStream.filter(track=['python'])

Categories

Resources