|
|
|
|
|
|
|
|
|
|
|
|
|
import validators, re |
|
from fake_useragent import UserAgent |
|
from bs4 import BeautifulSoup |
|
import streamlit as st |
|
from transformers import pipeline |
|
import time |
|
import base64 |
|
import requests |
|
import docx2txt |
|
from io import StringIO |
|
from PyPDF2 import PdfFileReader |
|
import warnings |
|
import nltk |
|
from nltk import sent_tokenize |
|
warnings.filterwarnings("ignore") |
|
|
|
|
|
|
|
|
|
time_str = time.strftime("%d%m%Y-%H%M%S") |
|
|
|
|
|
def article_text_extractor(url: str): |
|
|
|
'''Extract text from url and divide text into chunks if length of text is more than 500 words''' |
|
|
|
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>") |
|
|
|
current_chunk = 0 |
|
chunks = [] |
|
|
|
for sentence in sentences: |
|
if len(chunks) == current_chunk + 1: |
|
if len(chunks[current_chunk]) + len(sentence.split(" ")) <= 500: |
|
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]) |
|
|
|
return article_header, chunks |
|
|
|
def chunk_clean_text(text): |
|
|
|
sentences = sent_tokenize(text) |
|
current_chunk = 0 |
|
chunks = [] |
|
|
|
for sentence in sentences: |
|
if len(chunks) == current_chunk + 1: |
|
if len(chunks[current_chunk]) + len(sentence.split(" ")) <= 500: |
|
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]) |
|
|
|
return chunks |
|
|
|
def preprocess_plain_text(x): |
|
|
|
x = x.encode("ascii", "ignore").decode() |
|
x = re.sub(r"https*\S+", " ", x) |
|
x = re.sub(r"@\S+", " ", x) |
|
x = re.sub(r"#\S+", " ", x) |
|
x = re.sub(r"\s{2,}", " ", x) |
|
x = re.sub("[^.,!?A-Za-z0-9]+", " ", x) |
|
|
|
return x |
|
|
|
def extract_pdf(file): |
|
|
|
'''Extract text from PDF file''' |
|
|
|
pdfReader = PdfFileReader(file) |
|
count = pdfReader.numPages |
|
all_text = "" |
|
for i in range(count): |
|
page = pdfReader.getPage(i) |
|
all_text += page.extractText() |
|
|
|
|
|
return all_text |
|
|
|
|
|
def extract_text_from_file(file): |
|
|
|
'''Extract text from uploaded file''' |
|
|
|
|
|
if file.type == "text/plain": |
|
|
|
stringio = StringIO(file.getvalue().decode("utf-8")) |
|
|
|
|
|
file_text = stringio.read() |
|
|
|
|
|
elif file.type == "application/pdf": |
|
file_text = extract_pdf(file) |
|
|
|
|
|
elif ( |
|
file.type |
|
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document" |
|
): |
|
file_text = docx2txt.process(file) |
|
|
|
return file_text |
|
|
|
def summary_downloader(raw_text): |
|
|
|
b64 = base64.b64encode(raw_text.encode()).decode() |
|
new_filename = "new_text_file_{}_.txt".format(time_str) |
|
st.markdown("#### Download Summary as a File ###") |
|
href = f'<a href="data:file/txt;base64,{b64}" download="{new_filename}">Click to Download!!</a>' |
|
st.markdown(href,unsafe_allow_html=True) |
|
|
|
@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 schleifer_model(): |
|
|
|
summarizer = pipeline('summarization',model='sshleifer/distilbart-cnn-12-6') |
|
return summarizer |
|
|
|
|
|
|
|
st.title("Article Text and Link Extractive Summarizer π") |
|
|
|
model_type = st.sidebar.selectbox( |
|
"Model type", options=["Facebook-Bart", "Sshleifer-DistilBart"] |
|
) |
|
|
|
max_len= st.sidebar.slider("Maximum length of the summarized text",min_value=100,max_value=500) |
|
min_len= st.sidebar.slider("Minimum length of the summarized text",min_value=30) |
|
|
|
st.markdown( |
|
"Model Source: [Facebook-Bart-large-CNN](https://huggingface.co/facebook/bart-large-cnn) and [Sshleifer-distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6)" |
|
) |
|
|
|
st.markdown( |
|
"""The app supports extractive summarization which aims to identify the salient information that is then extracted and grouped together to form a concise summary. |
|
For documents or text that is more than 500 words long, the app will divide the text into chunks and summarize each chunk. Please note when using the sidebar slider, those values represent the min/max text length per chunk of text to be summarized. If your article to be summarized is 1000 words, it will be divided into two chunks of 500 words first then the default max length of 100 words is applied per chunk, resulting in a summarized text with 200 words maximum. |
|
There are two models available to choose from:""") |
|
|
|
st.markdown(""" |
|
- Facebook-Bart, trained on large [CNN and Daily Mail](https://huggingface.co/datasets/cnn_dailymail) news articles. |
|
- Sshleifer-Distilbart, which is a distilled (smaller) version of the large Bart model.""" |
|
) |
|
|
|
st.markdown("""Please do note that the model will take longer to generate summaries for documents that are too long.""") |
|
|
|
st.markdown( |
|
"The app only ingests the below formats for summarization task:" |
|
) |
|
st.markdown( |
|
"""- Raw text entered in text box. |
|
- URL of an article to be summarized. |
|
- Documents with .txt, .pdf or .docx file formats.""" |
|
) |
|
|
|
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") |
|
|
|
st.markdown( |
|
"<h3 style='text-align: center; color: red;'>OR</h3>", |
|
unsafe_allow_html=True, |
|
) |
|
|
|
upload_doc = st.file_uploader( |
|
"Upload a .txt, .pdf, .docx file for summarization" |
|
) |
|
|
|
is_url = validators.url(url_text) |
|
|
|
if is_url: |
|
|
|
article_title,chunks = article_text_extractor(url=url_text) |
|
|
|
elif upload_doc: |
|
|
|
clean_text = chunk_clean_text(preprocess_plain_text(extract_text_from_file(upload_doc))) |
|
|
|
else: |
|
|
|
clean_text = chunk_clean_text(preprocess_plain_text(plain_text)) |
|
|
|
summarize = st.button("Summarize") |
|
|
|
|
|
if summarize: |
|
if model_type == "Facebook-Bart": |
|
if is_url: |
|
text_to_summarize = chunks |
|
else: |
|
text_to_summarize = clean_text |
|
|
|
with st.spinner( |
|
text="Loading Facebook-Bart Model and Extracting summary. This might take a few seconds depending on the length of your text..." |
|
): |
|
summarizer_model = facebook_model() |
|
summarized_text = summarizer_model(text_to_summarize, max_length=max_len, min_length=min_len) |
|
summarized_text = ' '.join([summ['summary_text'] for summ in summarized_text]) |
|
|
|
elif model_type == "Sshleifer-DistilBart": |
|
if is_url: |
|
text_to_summarize = chunks |
|
else: |
|
text_to_summarize = clean_text |
|
|
|
with st.spinner( |
|
text="Loading Sshleifer-DistilBart Model and Extracting summary. This might take a few seconds depending on the length of your text..." |
|
): |
|
summarizer_model = schleifer_model() |
|
summarized_text = summarizer_model(text_to_summarize, max_length=max_len, min_length=min_len) |
|
summarized_text = ' '.join([summ['summary_text'] for summ in summarized_text]) |
|
|
|
|
|
st.subheader("Summarized text") |
|
|
|
if is_url: |
|
|
|
|
|
st.markdown(f"Article title: {article_title}") |
|
|
|
st.write(summarized_text) |
|
|
|
summary_downloader(summarized_text) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|