Created
May 6, 2016 16:20
-
-
Save Assios/2275ce78e9c36655f5a84227a3bd0afd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tweepy | |
from keys import * | |
import json | |
import time | |
import sys | |
auth = tweepy.OAuthHandler(consumer_key, consumer_secret) | |
auth.set_access_token(access_token, access_token_secret) | |
api = tweepy.API(auth) | |
def download_tweets(_file, tweet_sentiment=True, topic=False, topic_sentiment=False): | |
""" | |
Takes file with one tweet per line, on the format: | |
105121481662541824 #dexter negative neutral | |
""" | |
with open(_file) as infile: | |
res = {} | |
for line in infile: | |
line = line.split() | |
_id = int(line.pop(0)) | |
try: | |
tweet_object = api.get_status(_id)._json | |
except: | |
print("Tweet not found.") | |
continue | |
if line[-1] == "topic": | |
line = line[:-2] | |
line.append("off-topic") | |
text_topic_sentiment = line.pop() | |
text_tweet_sentiment = line.pop() | |
text_topic = " ".join(line) | |
res["text"] = tweet_object.get("text") | |
res["tweet_sentiment"] = text_tweet_sentiment | |
if topic: | |
res["topic"] = text_topic | |
if topic_sentiment: | |
res["topci_sentiment"] = text_topic_sentiment | |
with open("out.json", "a") as f: | |
f.write(json.dumps(res) + "\n") | |
print json.dumps(res) | |
if __name__ == "__main__": | |
download_tweets("twitter-train-B-tweet-and-topics.txt") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment