def collect_to_pandas_dataframe_user(user):
connexion = connect.twitter_setup()
tweets = collect_by_user(user)
data = pd.DataFrame(data=[tweet.text for tweet in tweets],
columns=['tweet_textual_content'])
data['len'] = np.array([len(tweet.text) for tweet in tweets])
data['ID'] = np.array([tweet.id for tweet in tweets])
data['Date'] = np.array([tweet.created_at for tweet in tweets])
data['Source'] = np.array([tweet.source for tweet in tweets])
data['Likes'] = np.array([tweet.favorite_count for tweet in tweets])
data['RTs'] = np.array([tweet.retweet_count for tweet in tweets])
return data
def collect_to_pandas_dataframe():
connexion = connect.twitter_setup()
tweets = connexion.search("@EmmanuelMacron", language="fr", rpp=100)
data = pd.DataFrame(data=[tweet.text for tweet in tweets],
columns=['tweet_textual_content'])
data['len'] = np.array([len(tweet.text) for tweet in tweets])
data['ID'] = np.array([tweet.id for tweet in tweets])
data['Date'] = np.array([tweet.created_at for tweet in tweets])
data['Source'] = np.array([tweet.source for tweet in tweets])
data['Likes'] = np.array([tweet.favorite_count for tweet in tweets])
data['RTs'] = np.array([tweet.retweet_count for tweet in tweets])
return data
def collect_by_user(user_id):
connexion = connect.twitter_setup()
statuses = connexion.user_timeline(id=user_id, count=10)
for status in statuses:
print(status.text)
return statuses
def collect():
connexion = connect.twitter_setup()
tweets = connexion.search("Emmanuel Macron", language="french", rpp=1)
for tweet in tweets:
print(tweet.text)
def collect_by_streaming():
connexion = connect.twitter_setup()
listener = StdOutListener()
stream=tweepy.Stream(auth = connexion.auth, listener=listener)
stream.filter(track=['Emmanuel Macron'])
def collect_by_user(user_id):
connexion = connect.twitter_setup()
statuses = connexion.user_timeline(id = user_id, count = 100)
return statuses