File size: 4,997 Bytes
a3962d0
 
 
 
 
 
 
 
 
 
 
06ae4c0
a3962d0
 
998932f
a3962d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
06ae4c0
a3962d0
 
06ae4c0
a3962d0
 
 
 
06ae4c0
 
 
 
 
 
 
a3962d0
 
998932f
a3962d0
06ae4c0
a3962d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
06ae4c0
a3962d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
06ae4c0
a3962d0
 
 
 
06ae4c0
a3962d0
06ae4c0
a3962d0
06ae4c0
a3962d0
06ae4c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3962d0
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
from transformers import pipeline
import streamlit as st
import requests
from bs4 import BeautifulSoup
import html
import time
from io import BytesIO
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.platypus import SimpleDocTemplate, Paragraph
from reportlab.lib.enums import TA_JUSTIFY
import pyttsx3

# Initialize the summarization pipeline
summarizer = pipeline("summarization", model="facebook/bart-small")   # facebook/bart-large-cnn

# Set page layout to wide
st.set_page_config(layout="wide")


# Function to create PDF with justified text
def create_pdf(text):
    pdf_buffer = BytesIO()
    doc = SimpleDocTemplate(pdf_buffer, pagesize=A4)
    styles = getSampleStyleSheet()
    justified_style = ParagraphStyle(
        name="JustifiedStyle",
        parent=styles["BodyText"],
        alignment=TA_JUSTIFY,
        fontSize=12,
        leading=15
    )
    paragraph = Paragraph(text, justified_style)
    doc.build([paragraph])
    pdf_buffer.seek(0)
    return pdf_buffer


# Function to read aloud the summary
def read_aloud(text):
    engine = pyttsx3.init()
    engine.say(text)
    engine.runAndWait()


# Main application
def main():
    st.title("Abstractive Article Summarizer")

    url = st.text_input("Enter the URL of an article:", key="url")
    max_chunk = 300

    if url:
        try:
            response = requests.get(url)
            response.encoding = 'utf-8'
            soup = BeautifulSoup(response.text, 'html.parser')
            results = soup.find_all(['h1', 'p'])
            text = [html.unescape(result.get_text()) for result in results]
            article = ' '.join(text)

            st.subheader("Extracted Article Content")
            st.text_area("Article", article, height=300)
            st.markdown(f"**Article Length:** {len(article)} characters")

            article = article.replace('.', '.<eos>').replace('?', '?<eos>').replace('!', '!<eos>')
            sentences = article.split('<eos>')
            current_chunk = 0
            chunks = [[]]

            for sentence in sentences:
                if len(chunks[current_chunk]) + len(sentence.split(' ')) <= max_chunk:
                    chunks[current_chunk].extend(sentence.split(' '))
                else:
                    current_chunk += 1
                    chunks.append(sentence.split(' '))

            for chunk_id in range(len(chunks)):
                chunks[chunk_id] = ' '.join(chunks[chunk_id])

            progress_bar = st.progress(0)
            status_text = st.empty()
            summaries = []
            start_time = time.time()

            for i, chunk in enumerate(chunks):
                summary = summarizer(chunk, max_length=120, min_length=30, do_sample=False)
                summaries.append(summary[0]['summary_text'])

                percent_complete = (i + 1) / len(chunks)
                elapsed_time = time.time() - start_time
                estimated_total_time = elapsed_time / percent_complete
                estimated_time_remaining = estimated_total_time - elapsed_time

                progress_bar.progress(percent_complete)
                status_text.markdown(f"**Progress:** {percent_complete * 100:.2f}% - "
                                     f"**Estimated time remaining:** {estimated_time_remaining:.2f} seconds")

            summary_text = ' '.join(summaries)

            st.subheader("Summarized Article Content")
            st.text_area("Summary", summary_text, height=300)
            st.markdown(f"**Summary Length:** {len(summary_text)} characters")

            pdf_buffer = create_pdf(summary_text)

            # Compression Ratio
            original_length = len(article.split())
            summary_length = len(summary_text.split())
            compression_ratio = (summary_length / original_length) * 100

            st.markdown(f"### Compression Ratio: {round(compression_ratio)}%")
            if compression_ratio < 20:
                st.success(f"Great Compression!\nThe summary is succinct and effectively highlights key points.")
            elif 20 <= compression_ratio <= 40:
                st.info(f"Well-balanced Summary.\nIt maintains essential details while being brief.")
            else:
                st.warning(f"Compression may be excessive.\nThe summary could be too brief and miss important details.")

            # Display buttons in columns
            col1, col2 = st.columns([1, 1])

            with col1:
                st.download_button(
                    label="Download Summary as PDF",
                    data=pdf_buffer,
                    file_name="summarized_article.pdf",
                    mime="application/pdf"
                )

            with col2:
                if st.button("Read Aloud Summary"):
                    read_aloud(summary_text)

        except Exception as e:
            st.warning(f"Error: {e}")


# Run the app
if __name__ == '__main__':
    main()