app.py

import gradio as gr
import wikipedia
import numpy as np
import pandas as pd
from os import path
from PIL import Image
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
import matplotlib.pyplot as plt

def wikipediaScrap(article_name, wikipedia_language = "en"):
  if wikipedia_language:
    wikipedia.set_lang(wikipedia_language)

  et_page = wikipedia.page(article_name)
  title = et_page.title
  content = et_page.content
  page_url = et_page.url
  linked_pages = et_page.links
  
  text = content

  # Create and generate a word cloud image:
  wordcloud = WordCloud(font_path="HelveticaWorld-Regular.ttf").generate(text)

  # Display the generated image:
  plt.imshow(wordcloud, interpolation='bilinear')
  plt.axis("off")
  
  return title, content, page_url, "\n". join(linked_pages), plt



with gr.Blocks( css = "footer {visibility: hidden} #dsd_button {background: purple, color: white} {background: blue, color: white}" ) as demo:
    with gr.Row():
      inp = gr.Textbox(placeholder="Enter the name of wikipedia article")
      lan = gr.Textbox(placeholder="Enter the language code")
    btn = gr.Button("Start Scraping", elem_id="dsd_button")
    gr.Markdown("""### Wordcloud""")
    with gr.Row():
      with gr.Column():
        title = gr.Textbox()
        url = gr.Textbox()
      with gr.Column():
        wordcloud = gr.Plot()
    gr.Markdown("""### Content""")
    with gr.Row():
      content = gr.Textbox()
    gr.Markdown("""### Linked Articles""")
    with gr.Row():
      linked = gr.Textbox()
    with gr.Row():
      gr.Examples(
                examples = [["Eiffel Tower", "en"], ["Eiffel tower", 'ur']], fn=wikipediaScrap, inputs=[inp, lan], outputs=[title, content, url, linked, wordcloud], cache_examples=True)
    btn.click(fn=wikipediaScrap, inputs=[inp, lan], outputs=[title, content, url, linked, wordcloud])

demo.launch()