Create app.py

app.py

@@ -0,0 +1,64 @@
+
+@author: prathap
+"""
+from transformers import pipeline
+from bs4 import BeautifulSoup
+import torch
+import requests
+import pandas as pd
+import streamlit as st
+import warnings
+warnings.filterwarnings("ignore")
+st.title("Automatic summarization")
+
+@st.cache(allow_output_mutation=True)
+def pipen():
+    summarizer = pipeline("summarization")
+    return summarizer
+
+
+
+
+
+url = st.text_input('The URL link')
+
+if st.button("Submit"):
+    r = requests.get(url)
+    soup = BeautifulSoup(r.text, 'html.parser')
+    results = soup.find_all(['h1', 'p'])
+    text = [result.text for result in results]
+    ARTICLE = ' '.join(text)
+    max_chunk = 400
+    ARTICLE = ARTICLE.replace('.', '.<eos>')
+    ARTICLE = ARTICLE.replace('?', '?<eos>')
+    ARTICLE = ARTICLE.replace('!', '!<eos>')
+    
+    
+    
+    sentences = ARTICLE.split('<eos>')
+    current_chunk = 0 
+    chunks = []
+    for sentence in sentences:
+        if len(chunks) == current_chunk + 1: 
+            if len(chunks[current_chunk]) + len(sentence.split(' '))<= max_chunk:
+                chunks[current_chunk].extend(sentence.split(' '))
+            else:
+                    current_chunk += 1
+                    chunks.append(sentence.split(' '))
+        else:
+            print(current_chunk)
+            chunks.append(sentence.split(' '))
+
+    for chunk_id in range(len(chunks)):
+        chunks[chunk_id] = ' '.join(chunks[chunk_id])
+        
+    with st.spinner("Loading the Model into the memory...."):
+        model=pipen()
+        res = model(chunks, max_length=120, min_length=30, do_sample=False)
+        text = ' '.join([summ['summary_text'] for summ in res])
+        print(len(text))
+        
+        st.write("Success")
+        st.write(text)
+        with open('stsummary.txt', 'w') as f:
+             f.write(text)