Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from summarizer import Summarizer
|
2 |
+
#from goose3 import Goose
|
3 |
+
from newsplease import NewsPlease
|
4 |
+
import validators
|
5 |
+
import streamlit as st
|
6 |
+
import warnings
|
7 |
+
warnings.filterwarnings("ignore")
|
8 |
+
|
9 |
+
def article_text_extractor(url: str):
|
10 |
+
'''Extract text from url'''
|
11 |
+
article = NewsPlease.from_url(entry.link)
|
12 |
+
|
13 |
+
return article.maintext
|
14 |
+
|
15 |
+
|
16 |
+
@st.cache(allow_output_mutation=True)
|
17 |
+
def model():
|
18 |
+
model = Summarizer()
|
19 |
+
return model
|
20 |
+
|
21 |
+
#Streamlit App
|
22 |
+
|
23 |
+
st.title("Article Extractive Summarizer")
|
24 |
+
|
25 |
+
st.markdown(
|
26 |
+
"This application aims to make an extractive summary of newspaper articles from the text of the article or the url link of the article. The summary is based on a BERT model.""")
|
27 |
+
|
28 |
+
st.markdown("""Please do note that the model will take longer to generate summaries for documents that are too long.""")
|
29 |
+
|
30 |
+
st.markdown(
|
31 |
+
"As input we only ingests the below formats :"
|
32 |
+
)
|
33 |
+
|
34 |
+
st.markdown(
|
35 |
+
"""- Raw text entered in text box.
|
36 |
+
- URL of an article to be summarized."""
|
37 |
+
)
|
38 |
+
|
39 |
+
st.markdown("---")
|
40 |
+
|
41 |
+
url_text = st.text_input("Please Enter a url here")
|
42 |
+
|
43 |
+
st.markdown(
|
44 |
+
"<h3 style='text-align: center; color: red;'>OR</h3>",
|
45 |
+
unsafe_allow_html=True,
|
46 |
+
)
|
47 |
+
|
48 |
+
plain_text = st.text_input("Please Paste/Enter plain text here")
|
49 |
+
|
50 |
+
is_url = validators.url(url_text)
|
51 |
+
|
52 |
+
if is_url:
|
53 |
+
# complete text
|
54 |
+
clean_text = article_text_extractor(url=url_text)
|
55 |
+
|
56 |
+
summarize = st.button("Summarize")
|
57 |
+
|
58 |
+
if summarize:
|
59 |
+
text_to_summarize = clean_text if is_url else plain_text
|
60 |
+
|
61 |
+
with st.spinner(text="Loading Model and Extracting summary. This might take a few seconds depending on the length of your text..."):
|
62 |
+
model = model()
|
63 |
+
summarized_text = text_to_summarize if len(text_to_summarize) > 60 else ''.join(model(body, min_length=60))
|
64 |
+
|
65 |
+
st.subheader("Summarized text")
|
66 |
+
|
67 |
+
st.write(summarized_text)
|