Spaces:
Runtime error
Runtime error
File size: 2,969 Bytes
2f1d1db 7d12a3b 562d978 dd69f73 4c40c59 9a04d19 eff9212 7d12a3b 2f1d1db 7d12a3b 2f1d1db 7d12a3b 2f1d1db 7d12a3b 2f1d1db 7d12a3b 2f1d1db | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | 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 - English"):
wikipedia_language = wikipedia_language.split(" - ")[0]
if wikipedia_language:
wikipedia.set_lang(wikipedia_language)
# rem_sp = article_name.replace(" ", "")
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
css = """
footer {display:none !important}
.output-markdown{display:none !important}
footer {visibility: hidden}
#component-12 img { max-height: 224px !important}
#component-14 textarea[data-testid="textbox"] { height: 178px !important}
#component-17 textarea[data-testid="textbox"] { height: 178px !important}
#component-20 tr:hover{
background-color: rgb(229,225,255) !important;
}
.max-h-[30rem] {max-height: 18rem !important;}
.hover\:bg-orange-50:hover {
--tw-bg-opacity: 1 !important;
background-color: rgb(229,225,255) !important;
}
"""
ini_dict = wikipedia.languages()
# split dictionary into keys and values
keys = []
values = []
language=[]
items = ini_dict.items()
for item in items:
keys.append(item[0]), values.append(item[1])
language.append(item[0]+" - "+item[1])
with gr.Blocks(title="Wikipedia Article Scrape | Data Science Dojo", css = css) as demo:
with gr.Row():
inp = gr.Textbox(placeholder="Enter the name of wikipedia article", label="Wikipedia article name")
lan = gr.Dropdown(label=" Select Language", choices=language, value=language[105], interactive=True)
btn = gr.Button("Start Scraping", elem_id="dsd_button")
with gr.Row():
with gr.Column():
# gr.Markdown("""## About""")
title = gr.Textbox(label="Article title")
url = gr.Textbox(label="Article URL")
with gr.Column():
# gr.Markdown("""## Wordcloud""")
wordcloud = gr.Plot()
# gr.Markdown("""### Content""")
with gr.Row():
content = gr.Textbox(label="Content")
# gr.Markdown("""### Linked Articles""")
with gr.Row():
linked = gr.Textbox(label="Linked Articles")
with gr.Row():
gr.Examples(
examples = [["Eiffel Tower", "en - English"], ["Eiffel tower", 'ur - اردو']], 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() |