Update app.py

app.py

@@ -19,36 +19,33 @@ def article_text_extractor(url: str):
   text = text if "REUTERS" not in first_sentence else "\n".join(list(filter(None, text.split("\n")))[1:])
   return text
   
-def article_text_extractor_(url: str):
-  '''Extract text from url'''
-  ua = UserAgent()
-  headers = {'User-Agent':str(ua.chrome)}
-  
-  r = requests.get(url,headers=headers)
-  
-  soup = BeautifulSoup(r.text, "html.parser")
-  title_text = soup.find_all(["h1"])
-  para_text = soup.find_all(["p"])
-  article_text = [result.text for result in para_text]
-  article_header = [result.text for result in title_text][0]
-  article = " ".join(article_text)
-  article = article.replace(".", ".<eos>")
-  article = article.replace("!", "!<eos>")
-  article = article.replace("?", "?<eos>")
-  sentences = article.split("<eos>")
-  
-  return ' '.join(sentences)
+
   
   
 @st.cache(allow_output_mutation=True)
-def model():    
+def extractive_model():    
   model = Summarizer()
   return model
   
+@st.cache(allow_output_mutation=True)
+def facebook_model():  
+  summarizer = pipeline('summarization',model='facebook/bart-large-cnn')
+  return summarizer
+
+@st.cache(allow_output_mutation=True)
+def model():
+  if summary_type == "Abstractive":
+    return facebook_model()
+  else:
+    return extractive_model()
+  
+  
 #Streamlit App
 
 st.title("Article Extractive Summarizer")
 
+summary_type = st.sidebar.selectbox("Summary type", options=["Abstractive", "Extractive"])
+
 st.markdown(
 	    "This application aims to make an extractive summary of newspaper articles from the text of the article or the url link of the article. The summary is based on  a BERT model.""")