wordcloud_pyrogram.py

# by @arthurwayne, I guess...

from datetime import datetime, date
import time
import os

import nltk

from nltk.corpus import stopwords
nltk.download("stopwords")

from PIL import Image
import numpy as np
from scipy.ndimage import gaussian_gradient_magnitude

from wordcloud import WordCloud, ImageColorGenerator, STOPWORDS

d = "."
f = "."

channel = "pyrogramlounge"

today_date = datetime.now().date()
today = datetime.now().strftime("%H_%M_%S-%Y-%m-%d")
# today_unixtime = int(time.mktime(today_date.timetuple()))

messages = await client.get_history(
    channel, limit=100, reverse=False
) # offset_date=int(today_unixtime)

msges = ""
for message in messages:
 if message.text:
  msg = str(message.text) + "\n"
  msges = msges + msg
  with open("messages-today-pyrogramlounge.text", "w") as file:
   file.write(msges)

text = open(
    os.path.join(d, "messages-today-pyrogramlounge.text"), encoding="UTF-8"
).read()
stop_words = stopwords.words("english")

new_stopwords = ["'"]
stop_words.extend(new_stopwords)

stop_words = set(stop_words)
clean_text = [word for word in text.split() if word not in stop_words]

cloud_image = np.array(Image.open(os.path.join(d, "/tmp/tmp_cloud.png")))

cloud_image = cloud_image[::3, ::3]

cloud_mask = cloud_image.copy()
cloud_mask[cloud_mask.sum(axis=2) == 0] = 255

image_edges = np.mean(
    [gaussian_gradient_magnitude(cloud_image[:, :, i] / 255.0, 2) for i in range(3)],
    axis=0,
)
cloud_mask[image_edges > 0.08] = 255

wc = WordCloud(
    max_words=2000,
    scale=3,
    mask=cloud_mask,
    relative_scaling=1,
    repeat=False,
    colormap="Pastel1",
    stopwords=str(clean_text),
)

wc.generate(str(clean_text))

wc.to_file("blue_cloud_pastel-pyrogramlounge.png")

image_colors = ImageColorGenerator(cloud_image)
wc.recolor(color_func=image_colors)
wc.to_file("cloud.png")

await client.send_photo(message.chat.id, "cloud.png")
await client.send_photo(message.chat.id, "blue_cloud_pastel-pyrogramlounge.png")