Spaces:
Sleeping
Sleeping
EmreYY20
commited on
Commit
·
03ddbfd
1
Parent(s):
5ea550e
update
Browse files- app.py +12 -14
- extractive_model.py +0 -1
app.py
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
import streamlit as st
|
|
|
|
| 2 |
from extractive_model import summarize_pdf_with_textrank
|
| 3 |
|
| 4 |
# Set page to wide mode
|
|
@@ -9,42 +10,39 @@ def load_pdf(file):
|
|
| 9 |
pdf_reader = PyPDF2.PdfReader(file)
|
| 10 |
pdf_text = ""
|
| 11 |
for page_num in range(len(pdf_reader.pages)):
|
| 12 |
-
pdf_text += pdf_reader.pages[page_num].extract_text()
|
| 13 |
return pdf_text
|
| 14 |
|
| 15 |
# Main app
|
| 16 |
def main():
|
| 17 |
-
|
| 18 |
st.title("Terms of Service Summarizer")
|
| 19 |
|
| 20 |
# Layout: 3 columns
|
| 21 |
col1, col2, col3 = st.columns([1, 3, 2], gap="large")
|
| 22 |
|
| 23 |
-
# Left column:
|
| 24 |
with col1:
|
| 25 |
-
# Options for the radio buttons
|
| 26 |
radio_options = ['Abstractive', 'Extractive']
|
| 27 |
-
|
| 28 |
-
# Create radio buttons and get the selected option
|
| 29 |
radio_selection = st.radio("Choose type of summarizer:", radio_options)
|
| 30 |
|
| 31 |
-
|
| 32 |
# Middle column: Text input and File uploader
|
| 33 |
with col2:
|
| 34 |
user_input = st.text_input("Enter your text here:")
|
| 35 |
uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
|
| 36 |
if st.button("Summarize"):
|
| 37 |
-
|
| 38 |
if uploaded_file is not None:
|
|
|
|
| 39 |
file_content = load_pdf(uploaded_file)
|
| 40 |
st.write("PDF uploaded successfully.")
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
else:
|
| 47 |
-
st.
|
|
|
|
| 48 |
st.session_state.summary = summary
|
| 49 |
|
| 50 |
# Right column: Displaying text after pressing 'Summarize'
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
+
import PyPDF2
|
| 3 |
from extractive_model import summarize_pdf_with_textrank
|
| 4 |
|
| 5 |
# Set page to wide mode
|
|
|
|
| 10 |
pdf_reader = PyPDF2.PdfReader(file)
|
| 11 |
pdf_text = ""
|
| 12 |
for page_num in range(len(pdf_reader.pages)):
|
| 13 |
+
pdf_text += pdf_reader.pages[page_num].extract_text() or ""
|
| 14 |
return pdf_text
|
| 15 |
|
| 16 |
# Main app
|
| 17 |
def main():
|
|
|
|
| 18 |
st.title("Terms of Service Summarizer")
|
| 19 |
|
| 20 |
# Layout: 3 columns
|
| 21 |
col1, col2, col3 = st.columns([1, 3, 2], gap="large")
|
| 22 |
|
| 23 |
+
# Left column: Radio buttons for summarizer choice
|
| 24 |
with col1:
|
|
|
|
| 25 |
radio_options = ['Abstractive', 'Extractive']
|
|
|
|
|
|
|
| 26 |
radio_selection = st.radio("Choose type of summarizer:", radio_options)
|
| 27 |
|
|
|
|
| 28 |
# Middle column: Text input and File uploader
|
| 29 |
with col2:
|
| 30 |
user_input = st.text_input("Enter your text here:")
|
| 31 |
uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
|
| 32 |
if st.button("Summarize"):
|
| 33 |
+
summary = ""
|
| 34 |
if uploaded_file is not None:
|
| 35 |
+
# Extract text from PDF
|
| 36 |
file_content = load_pdf(uploaded_file)
|
| 37 |
st.write("PDF uploaded successfully.")
|
| 38 |
+
if radio_selection == "Extractive":
|
| 39 |
+
# Perform extractive summarization
|
| 40 |
+
summary = summarize_pdf_with_textrank(file_content)
|
| 41 |
+
else:
|
| 42 |
+
None
|
| 43 |
else:
|
| 44 |
+
st.write("Please upload a PDF or enter some text to summarize.")
|
| 45 |
+
|
| 46 |
st.session_state.summary = summary
|
| 47 |
|
| 48 |
# Right column: Displaying text after pressing 'Summarize'
|
extractive_model.py
CHANGED
|
@@ -9,7 +9,6 @@ from pysummarization.abstractabledoc.top_n_rank_abstractor import TopNRankAbstra
|
|
| 9 |
from sumy.nlp.stemmers import Stemmer
|
| 10 |
from sumy.utils import get_stop_words"""
|
| 11 |
|
| 12 |
-
import PyPDF2
|
| 13 |
from sumy.parsers.plaintext import PlaintextParser
|
| 14 |
from sumy.nlp.tokenizers import Tokenizer
|
| 15 |
from sumy.summarizers.text_rank import TextRankSummarizer
|
|
|
|
| 9 |
from sumy.nlp.stemmers import Stemmer
|
| 10 |
from sumy.utils import get_stop_words"""
|
| 11 |
|
|
|
|
| 12 |
from sumy.parsers.plaintext import PlaintextParser
|
| 13 |
from sumy.nlp.tokenizers import Tokenizer
|
| 14 |
from sumy.summarizers.text_rank import TextRankSummarizer
|