no_links = re.sub(r'\S+.com', '', no_links)
return no_links
def create_words(clean_string):
words = clean_string.split(" ")
words = [w for w in words if len(w) > 3] # ignore a, to, at...
return words
#Collect the data from the user timeline
with open("tweets_username.json", "r") as read_file:
user_timeline = json.load(read_file)
raw_tweets = []
for tweets in user_timeline:
raw_tweets.append(tweets['text'])
#Generate the cloud
clean_text = clean_tweets(raw_tweets)
words = create_words(clean_text)
clean_string = ','.join(words)
mask = np.array(Image.open('twitter-logo.jpg'))
wc = PersianWordCloud(background_color="white", max_words=2000, mask=mask)
wc.generate(clean_string)
plt.imshow(wc, interpolation='bilinear')
plt.axis("off")
plt.show(block=True)
#text = ' '.join(all_words)
print("finished")
# loading the mask
twitter_mask = np.array(Image.open(path.join(d, "twitter_mask.png")))
# generating wordcloud
wc = PersianWordCloud(only_persian=True,
regexp=r".*\w+.*",
font_step=3,
font_path=path.join(d, "IRANSans.ttf"),
background_color="white",
max_words=800,
mask=twitter_mask,
stopwords=stopwords)
wc.generate(text)
currTime = datetime.datetime.utcnow()
output_name = currTime.strftime("%d-%m-%Y_%H_%M.png")
#output_name = "test.png"
# store to file
wc.to_file(path.join(d, output_name))
import tweepy
import telegram
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)
telegram_bot = telegram.Bot(token=telegram_bot_token)