File size: 2,984 Bytes
5295f9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec915c6
5295f9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
240985f
5295f9d
 
 
3d20156
5295f9d
 
 
 
 
 
 
 
06ef4fc
cb98948
5295f9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec915c6
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
import streamlit as st
from sumy.parsers.plaintext import PlaintextParser
from sumy.parsers.html import HtmlParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words

import nltk
nltk.download('punkt')

def summarize(method, language, sentence_count, input_type, input_):
    if method== 'LSA':
        from sumy.summarizers.lsa import LsaSummarizer as Summarizer
    if method=='text-rank':
        from sumy.summarizers.text_rank import TextRankSummarizer as Summarizer
    if method=='lex-rank':
        from sumy.summarizers.lex_rank import LexRankSummarizer as Summarizer
    if method=='edmundson':
        from sumy.summarizers.edmundson import EdmundsonSummarizer as Summarizer
    if method=='luhn':
        from sumy.summarizers.luhn import LuhnSummarizer as Summarizer
    if method=='kl-sum':
        from sumy.summarizers.kl import KLSummarizer as Summarizer
    if method=='random':
        from sumy.summarizers.random import RandomSummarizer as Summarizer
    if method=='reduction':
        from sumy.summarizers.reduction import ReductionSummarizer as Summarizer

    if input_type=="URL":
        parser = HtmlParser.from_url(input_, Tokenizer(language))
    else:
        parser = PlaintextParser.from_string(input_, Tokenizer(language))

    stemmer = Stemmer(language)
    summarizer = Summarizer(stemmer)
    stop_words = get_stop_words(language)

    if method=='edmundson':
        summarizer.null_words = stop_words
        summarizer.bonus_words = parser.significant_words
        summarizer.stigma_words = parser.stigma_words
    else:
        summarizer.stop_words = stop_words

    summary_sentences = summarizer(parser.document, sentence_count)
    summary = ' '.join([str(sentence) for sentence in summary_sentences])

    return summary

title = "AIconvert AI text summarization"

description = """

The summary can be extracted either from url link or plain text. .
"""

methods = ["LSA", "luhn", "edmundson", "text-rank", "lex-rank", "random", "reduction", "kl-sum"]

supported_languages = ["english", "french", "arabic", "chinese", "czech", "german", "italian", "hebrew", 
                        "japanese", "portuguese", "slovak", "spanish", "ukrainian", "greek"]

# Streamlit UI
st.title("AIconvert AI text summarization")
st.markdown('<style>h1{color: Crimson; text-align: center;}</style>', unsafe_allow_html=True)
st.markdown(description)

method = st.selectbox("Select Summarization Method", methods)
language = st.selectbox("Select Language", supported_languages)
sentence_count = st.number_input("Number of Sentences", min_value=1, value=7)
input_type = st.radio("Input Type", ["URL", "Text"])

if input_type == "URL":
    input_ = st.text_input("Enter URL")
else:
    input_ = st.text_area("Enter Text", height=200)

if st.button("Summarize"):
    summary = summarize(method, language, sentence_count, input_type, input_)
    st.subheader("Summary")
    st.write(summary)