Update app.py
Browse files
app.py
CHANGED
@@ -3,7 +3,8 @@ import json
|
|
3 |
import requests
|
4 |
import time
|
5 |
from newspaper import Article
|
6 |
-
|
|
|
7 |
|
8 |
# Page title layout
|
9 |
c1, c2 = st.columns([0.32, 2])
|
@@ -13,13 +14,13 @@ with c1:
|
|
13 |
|
14 |
with c2:
|
15 |
st.title("Website Article Summarize")
|
16 |
-
st.markdown("**Generate summaries of articles from websites using abstractive summarization with
|
17 |
st.caption("Created by Bayhaqy.")
|
18 |
|
19 |
# Sidebar content
|
20 |
st.sidebar.subheader("About the app")
|
21 |
st.sidebar.info("This app uses optional 🤗HuggingFace's Model [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) \
|
22 |
-
or [pegasus_indonesian_base-finetune](https://huggingface.co/pegasus_indonesian_base-finetune) model.")
|
23 |
st.sidebar.write("\n\n")
|
24 |
st.sidebar.markdown("**Get a free API key from HuggingFace:**")
|
25 |
st.sidebar.markdown("* Create a [free account](https://huggingface.co/join) or [login](https://huggingface.co/login)")
|
@@ -27,7 +28,7 @@ st.sidebar.markdown("* Go to **Settings** and then **Access Tokens**")
|
|
27 |
st.sidebar.markdown("* Create a new Token (select 'read' role)")
|
28 |
st.sidebar.markdown("* Paste your API key in the text box")
|
29 |
st.sidebar.divider()
|
30 |
-
st.sidebar.write("Please make sure
|
31 |
st.sidebar.write("\n\n")
|
32 |
st.sidebar.divider()
|
33 |
|
@@ -55,28 +56,18 @@ if fetch_button:
|
|
55 |
time.sleep(3)
|
56 |
st.success('Your article is ready for summarization!')
|
57 |
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
title = article.title
|
66 |
-
text = article.text
|
67 |
-
html = article.html
|
68 |
-
|
69 |
-
st.divider()
|
70 |
-
st.subheader("Real Article")
|
71 |
-
st.markdown(f"Your article: **{title}**")
|
72 |
-
st.markdown(f"**{text}**")
|
73 |
-
st.divider()
|
74 |
-
|
75 |
-
st.divider()
|
76 |
-
st.subheader("Real Article (HTML)")
|
77 |
-
st.code(f"Your article: **{title}**",language='html')
|
78 |
-
st.code(f"**{html}**",language='html')
|
79 |
-
st.divider()
|
80 |
|
81 |
else:
|
82 |
st.write("Error occurred while fetching article.")
|
@@ -99,9 +90,6 @@ if selected_api_url == "bart-large-cnn":
|
|
99 |
else:
|
100 |
API_URL = "https://api-inference.huggingface.co/models/thonyyy/pegasus_indonesian_base-finetune"
|
101 |
|
102 |
-
|
103 |
-
API_URL_TL = "https://api-inference.huggingface.co/models/facebook/mbart-large-50-many-to-many-mmt"
|
104 |
-
|
105 |
submit_button = st.button("Submit to Summarize")
|
106 |
|
107 |
# Download and parse the article
|
@@ -109,10 +97,12 @@ if submit_button:
|
|
109 |
article = Article(url)
|
110 |
article.download()
|
111 |
article.parse()
|
|
|
112 |
|
113 |
title = article.title
|
114 |
text = article.text
|
115 |
html = article.html
|
|
|
116 |
|
117 |
# HuggingFace API request function summary
|
118 |
def query_sum(payload):
|
@@ -134,19 +124,11 @@ if submit_button:
|
|
134 |
st.markdown(f"**{summary}**")
|
135 |
|
136 |
st.divider()
|
137 |
-
st.subheader("
|
138 |
st.markdown(f"Your article: **{title}**")
|
139 |
-
st.markdown(f"**{
|
140 |
-
st.divider()
|
141 |
|
142 |
st.divider()
|
143 |
st.subheader("Real Article")
|
144 |
st.markdown(f"Your article: **{title}**")
|
145 |
st.markdown(f"**{text}**")
|
146 |
-
st.divider()
|
147 |
-
|
148 |
-
st.divider()
|
149 |
-
st.subheader("Real Article (HTML)")
|
150 |
-
st.code(f"Your article: **{title}**",language='html')
|
151 |
-
st.code(f"**{html}**",language='html')
|
152 |
-
st.divider()
|
|
|
3 |
import requests
|
4 |
import time
|
5 |
from newspaper import Article
|
6 |
+
import nltk
|
7 |
+
nltk.download('punkt')
|
8 |
|
9 |
# Page title layout
|
10 |
c1, c2 = st.columns([0.32, 2])
|
|
|
14 |
|
15 |
with c2:
|
16 |
st.title("Website Article Summarize")
|
17 |
+
st.markdown("**Generate summaries of articles from websites using abstractive summarization with Language Model and Library NewsPaper.**")
|
18 |
st.caption("Created by Bayhaqy.")
|
19 |
|
20 |
# Sidebar content
|
21 |
st.sidebar.subheader("About the app")
|
22 |
st.sidebar.info("This app uses optional 🤗HuggingFace's Model [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) \
|
23 |
+
or [pegasus_indonesian_base-finetune](https://huggingface.co/pegasus_indonesian_base-finetune) model and Library NewsPaper.")
|
24 |
st.sidebar.write("\n\n")
|
25 |
st.sidebar.markdown("**Get a free API key from HuggingFace:**")
|
26 |
st.sidebar.markdown("* Create a [free account](https://huggingface.co/join) or [login](https://huggingface.co/login)")
|
|
|
28 |
st.sidebar.markdown("* Create a new Token (select 'read' role)")
|
29 |
st.sidebar.markdown("* Paste your API key in the text box")
|
30 |
st.sidebar.divider()
|
31 |
+
st.sidebar.write("Please make sure you choose the correct model and is not behind a paywall.")
|
32 |
st.sidebar.write("\n\n")
|
33 |
st.sidebar.divider()
|
34 |
|
|
|
56 |
time.sleep(3)
|
57 |
st.success('Your article is ready for summarization!')
|
58 |
|
59 |
+
article = Article(url)
|
60 |
+
article.download()
|
61 |
+
article.parse()
|
62 |
+
|
63 |
+
title = article.title
|
64 |
+
text = article.text
|
65 |
|
66 |
+
st.divider()
|
67 |
+
st.subheader("Real Article")
|
68 |
+
st.markdown(f"Your article: **{title}**")
|
69 |
+
st.markdown(f"**{text}**")
|
70 |
+
st.divider()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
else:
|
73 |
st.write("Error occurred while fetching article.")
|
|
|
90 |
else:
|
91 |
API_URL = "https://api-inference.huggingface.co/models/thonyyy/pegasus_indonesian_base-finetune"
|
92 |
|
|
|
|
|
|
|
93 |
submit_button = st.button("Submit to Summarize")
|
94 |
|
95 |
# Download and parse the article
|
|
|
97 |
article = Article(url)
|
98 |
article.download()
|
99 |
article.parse()
|
100 |
+
article.nlp()
|
101 |
|
102 |
title = article.title
|
103 |
text = article.text
|
104 |
html = article.html
|
105 |
+
summ = article.summary
|
106 |
|
107 |
# HuggingFace API request function summary
|
108 |
def query_sum(payload):
|
|
|
124 |
st.markdown(f"**{summary}**")
|
125 |
|
126 |
st.divider()
|
127 |
+
st.subheader("Summary Library NewsPaper")
|
128 |
st.markdown(f"Your article: **{title}**")
|
129 |
+
st.markdown(f"**{summ}**")
|
|
|
130 |
|
131 |
st.divider()
|
132 |
st.subheader("Real Article")
|
133 |
st.markdown(f"Your article: **{title}**")
|
134 |
st.markdown(f"**{text}**")
|
|
|
|
|
|
|
|
|
|
|
|
|
|