Last active
September 13, 2021 00:04
-
-
Save marcosan93/fb1424ce07c2c2bf52fc7e118c4fae87 to your computer and use it in GitHub Desktop.
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
| def getTweets(search_term, until, limit=20): | |
| """ | |
| Configures Twint and returns a dataframe of tweets for a specific day. | |
| """ | |
| # Configuring Twint for search | |
| c = twint.Config() | |
| # The limit of tweets to retrieve | |
| c.Limit = limit | |
| # Search term | |
| c.Search = search_term | |
| # Removing retweets | |
| c.Filter_retweets = True | |
| # Popular tweets | |
| c.Popular_tweets = True | |
| # Lowercasing tweets | |
| c.Lowercase = True | |
| # English only | |
| c.Lang = 'en' | |
| # Tweets until a specified date | |
| c.Until = until + " 00:00:00" | |
| # Making the results pandas friendly | |
| c.Pandas = True | |
| # Stopping print in terminal | |
| c.Hide_output = True | |
| # Searching | |
| twint.run.Search(c) | |
| # Assigning the DF | |
| df = twint.storage.panda.Tweets_df | |
| # Returning an empty DF if no tweets were found | |
| if len(df)<=0: | |
| return pd.DataFrame() | |
| # Formatting the date | |
| df['date'] = df['date'].apply(lambda x: x.split(" ")[0]) | |
| return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment