Last active
June 26, 2020 20:45
-
-
Save aditideokar93/ee3c4050821170a590d8ef9c6c8328a5 to your computer and use it in GitHub Desktop.
Fetch older tweets using GetOldTweets3 package
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
__author__ = "Aditi Deokar" | |
""" | |
The Python code below makes use of GetOldTweets3 Package to collect older tweets | |
""" | |
import time | |
import pandas as pd | |
import GetOldTweets3 as got | |
#list of column names | |
COLS = ['id', 'created_at','original_text', 'screen_name', 'author_id', | |
'replies', 'retweet_count', 'to','hashtags', | |
'user_mentions', 'urls'] | |
path=r"D:\Older_tweets_data" | |
politicians=['SenatorMenendez','SenStabenow','SenatorTester','SenWhitehouse','SenatorDurbin'] | |
#Function to fetch the tweet object, grab the information and write into a .csv file | |
for screenname in politicians: | |
entry = [] | |
tweetCriteria = got.manager.TweetCriteria().setUsername(screenname)\ | |
.setSince("2019-12-18")\ | |
.setUntil("2020-01-01")\ | |
.setMaxTweets(1000)\ | |
.setEmoji("unicode") | |
tweet = got.manager.TweetManager.getTweets(tweetCriteria) | |
for twt in tweet: | |
entry.append([twt.id,twt.formatted_date,twt.text,twt.username,twt.author_id,twt.replies,twt.retweets,twt.to,twt.hashtags,twt.mentions,twt.urls]) | |
print(len(entry),screenname) | |
df = pd.DataFrame(entry,columns=COLS) | |
# print(df.head()) | |
df.to_csv(path+'\\'+screenname+"_tweets.csv", mode='a+', columns=COLS, index=False, | |
encoding="utf-8") | |
time.sleep(3) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment