Untitled

import tweepy
import configparser
import pandas as pd
from tqdm import tqdm


# read configs
config = configparser.ConfigParser()
config.read('config.ini')

api_key = config['twitter']['api_key']
api_key_secret = config['twitter']['api_key_secret']

access_token = config['twitter']['access_token']
access_token_secret = config['twitter']['access_token_secret']

# authentication
auth = tweepy.OAuthHandler(api_key, api_key_secret)
auth.set_access_token(access_token, access_token_secret)

api = tweepy.API(auth)


# search tweets
keywords = 'bitcoin'
limit=100

date_since ="2021-03-01"
date_until="2020-03-10"

tweets = tweepy.Cursor(api.search_tweets, q=keywords,lang="en",count=100, tweet_mode='extended').items(limit)

# tweets = api.user_timeline(screen_name=user, count=limit, tweet_mode='extended')

# create DataFrame

tweets_copy = []
for tweet in tqdm(tweets):
    tweets_copy.append(tweet)

print(f"New tweets retrieved: {len(tweets_copy)}")

tweets_df=[]

for tweet in tqdm(tweets_copy):
    #print(tweet)
    #print()
    hashtags = []
    try:
        for hashtag in tweet.entities["hashtags"]:
            hashtags.append(hashtag["text"])
    except:
        pass
    
    tweets_df.append(pd.DataFrame({'user_name': tweet.user.name, 
                                               'user_location': tweet.user.location,\
                                               'user_description': tweet.user.description,
                                               'user_created': tweet.user.created_at,
                                               'user_followers': tweet.user.followers_count,
                                               'user_friends': tweet.user.friends_count,
                                               'user_favourites': tweet.user.favourites_count,
                                               'user_verified': tweet.user.verified,
                                               'date': tweet.created_at,
                                               'text': tweet.full_text, 
                                               'hashtags': [hashtags if hashtags else None],
                                               'source': tweet.source,
                                               'is_retweet': tweet.retweeted}, index=[0]))


#tw_df = pd.DataFrame(tweets_df)
print(tweets_df)
tweets_df.to_csv('tweets_4.csv')