Created
March 5, 2020 02:35
-
-
Save jamespaultg/ec6cd358eaabb55d5e44855abafe35a9 to your computer and use it in GitHub Desktop.
Get tweets from twitter using the tweepy api
This file contains hidden or 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
| # Thanks to Kaggle user yassinehamdaoui1 | |
| # https://www.kaggle.com/c/nlp-getting-started/discussion/132762 | |
| import pandas as pd | |
| import tweepy as tw | |
| consumer_key = "put here you consumer_key" | |
| consumer_secret ="put here your consumer_secret" | |
| access_token = "your access" | |
| access_token_secret ="your access token" | |
| auth = tw.OAuthHandler(consumer_key, consumer_secret) | |
| auth.set_access_token(access_token, access_token_secret) | |
| api = tw.API(auth) | |
| search_words ="earthquake+disaster" # you gonna search by hashtags , the "+" stands for concatenating keywords | |
| date = "2020-01-01" # choose any date with the format "yyyy-mm-dd" | |
| number_posts = 100 # choose the number of posts available in that day | |
| posts =[] | |
| tweets = tw.Cursor(api.search,q=search_words,lang="en",since=date).items(number_posts) | |
| for tweet in tweets: | |
| posts.append([tweet.user.screen_name,tweet.user.location,tweet.text]) | |
| df = pd.DataFrame(posts) | |
| df.to_csv('data.csv',index=False,header=["username","location","text"]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment