Я собираю твиты о COVID19, используя твипи. Я собираюсь sh собирать только те твиты, сделанные простыми людьми, а не новостные каналы. Какой самый простой способ отфильтровать их?
def search_for_hashtags(consumer_key, consumer_secret, access_token, access_token_secret, hashtag_phrase):
#create authentication for accessing Twitter
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
#initialize Tweepy API
api = tweepy.API(auth)
#get the name of the spreadsheet we will write to
fname = '_'.join(re.findall(r"(\w+)", hashtag_phrase))
#open the spreadsheet we will write to
with open('%s.csv' % (fname), 'w', encoding="utf-8") as file:
w = csv.writer(file)
#write header row to spreadsheet
w.writerow(['timestamp', 'tweet_text', 'username', 'all_hashtags', 'followers_count'])
#for each tweet matching our hashtags, write relevant info to the spreadsheet
for tweet in tweepy.Cursor(api.search, q=hashtag_phrase+' -filter:retweets', \
lang="en", tweet_mode='extended').items(100):
w.writerow([tweet.created_at, tweet.full_text.replace('\n',' ').encode('utf-8'), tweet.user.screen_name.encode('utf-8'), [e['text'] for e in tweet._json['entities']['hashtags']], tweet.user.followers_count])