Create app.py

app.py

@@ -0,0 +1,67 @@
+from summarizer import Summarizer
+#from goose3 import Goose
+from newsplease import NewsPlease
+import validators
+import streamlit as st
+import warnings
+warnings.filterwarnings("ignore")
+
+def article_text_extractor(url: str):
+  '''Extract text from url'''
+  article = NewsPlease.from_url(entry.link)
+  
+  return article.maintext
+  
+  
+@st.cache(allow_output_mutation=True)
+def model():    
+  model = Summarizer()
+  return model
+  
+#Streamlit App
+
+st.title("Article Extractive Summarizer")
+
+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.""")
+	    
+st.markdown("""Please do note that the model will take longer to generate summaries for documents that are too long.""")
+
+st.markdown(
+    "As input we only ingests the below formats :"
+)
+
+st.markdown(
+	    """- Raw text entered in text box. 
+	- URL of an article to be summarized."""
+	)
+
+st.markdown("---")
+	
+url_text = st.text_input("Please Enter a url here")
+
+st.markdown(
+	    "<h3 style='text-align: center; color: red;'>OR</h3>",
+	    unsafe_allow_html=True,
+	)
+
+plain_text = st.text_input("Please Paste/Enter plain text here")
+
+is_url = validators.url(url_text)
+
+if is_url:
+	    # complete text
+  clean_text = article_text_extractor(url=url_text)
+  
+summarize = st.button("Summarize")
+
+if summarize:
+  text_to_summarize = clean_text if is_url else plain_text
+  
+  with st.spinner(text="Loading Model and Extracting summary. This might take a few seconds depending on the length of your text..."):
+    model =  model()
+    summarized_text = text_to_summarize if len(text_to_summarize) > 60 else ''.join(model(body, min_length=60))
+   
+  st.subheader("Summarized text")
+    
+  st.write(summarized_text)