WordCloud

mkdir ~/mywordcloud; cd ~/mywordcloud

cat <<'EOF' > main.py
import fire
import matplotlib.pyplot as plt
import pandas as pd
import re
import requests
from bs4 import BeautifulSoup
from wordcloud import STOPWORDS, WordCloud


def gen_cloud_tag(url: str = "https://blog.stoege.net"):
    # add https
    if not url.startswith("https://"):
        url = "https://" + url

    # get Webpage
    response = requests.get(url, timeout=5, allow_redirects=True)
    soup = BeautifulSoup(response.text, "html.parser")
    words = soup.get_text()

    # split with multiple delimiters
    words = re.split(r"[\n\r]", words)

    # build Dataframe
    df = pd.DataFrame(words)

    # Stop Words
    comment_words = ""
    stopwords = set(STOPWORDS)

    # iterate
    for val in df.values:
        # typecaste each val to string
        val = str(val)

        # split the value
        tokens = val.split()

        # Converts each token into lowercase
        for i in range(len(tokens)):
            tokens[i] = tokens[i].lower()

        comment_words += " ".join(tokens) + " "

    # Build Wordcloud
    wordcloud = WordCloud(
        width=800,
        height=800,
        background_color="white",
        stopwords=stopwords,
        min_font_size=10,
    ).generate(comment_words)

    # Build Image
    plt.figure(figsize=(8, 8), facecolor=None)
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.tight_layout(pad=0)

    # show Image
    plt.show()


if __name__ == "__main__":
    fire.Fire(gen_cloud_tag)
EOF