Update app.py

app.py

@@ -1,3 +1,4 @@
+from gensim.parsing.preprocessing import STOPWORDS
 import wikipedia
 import gradio as gr
 from gradio.mix import Parallel
@@ -7,27 +8,38 @@ from nltk.tokenize import word_tokenize
 from nltk.tokenize import sent_tokenize
 import re
 nltk.download('punkt')
+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 opendomain(text):
-  question_words = ["what", "why", "when", "where","name", "is", "how", "do", "does",
-                    "which", "are", "could", "would","should", "has", "have", "whom",
-                    "whose", "don't", "a", "an","?",".","the","i","you","he","she","it",
-                    "that","this",",","am",","]
+def opendomain(text,wikipedia_language="en"):
+  question_words = STOPWORDS.union(set(['likes','play','.',',','like',"don't",'?','use','choose','important','better','?']))
   lower_text = text.lower()
   lower_text = word_tokenize(lower_text)
   new_text = [i for i in lower_text if i not in question_words]
   new_txt = "".join(new_text)
+  if wikipedia_language:
+    wikipedia.set_lang(wikipedia_language)
 
-  r = requests.post(
-      url="https://jaimin-new-content.hf.space/run/predict",
-      json={"data": [new_txt, "en"]},
-    )
-  response = r.json()
-  text1 = response["data"]
-  final_out = text1[0]
-  final_out=re.sub(r'\=.+\=', '', final_out)
+  et_page = wikipedia.page(new_txt.replace(" ", ""))
+  title = et_page.title
+  content = et_page.content
+  page_url = et_page.url
+  linked_pages = et_page.links
 
+  text = content
+  print(type(text))
+  wordcloud = WordCloud(font_path="HelveticaWorld-Regular.ttf").generate(text)
+
+  plt.imshow(wordcloud, interpolation='bilinear')
+  plt.axis("off")
+
+
+  final_out = re.sub(r'\=.+\=', '', text)
   result = list(filter(lambda x: x != '', final_out.split('\n\n')))
 
   answer = []
@@ -49,3 +61,8 @@ def opendomain(text):
 iface = gr.Interface(fn=opendomain, inputs=[gr.inputs.Textbox(lines=5)], outputs="text")
 iface.launch()
 
+
+
+
+
+