herztard commited on
Commit
1e5a29f
·
1 Parent(s): 1915d98

parse data from link and button

Browse files
Files changed (1) hide show
  1. app.py +22 -0
app.py CHANGED
@@ -1,14 +1,36 @@
 
1
  import streamlit as st
 
2
  from transformers import pipeline
 
 
3
  @st.cache_resource
4
  def load_model():
5
  return pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
6
 
7
  model = load_model()
8
 
 
 
 
 
 
 
 
 
 
 
 
 
9
 
10
  st.title("Tag Detection from CNN News articles")
11
  st.write("Enter a CNN News article URL.")
12
 
13
  news_url = st.text_input("CNN Article URL:", placeholder="Example: https://edition.cnn.com/2024/12/19/science/stonehenge-monument-early-farmers/index.html")
14
  categories = ["Politics", "Sports", "Weather", "Culture", "Crime"]
 
 
 
 
 
 
 
1
+ import requests
2
  import streamlit as st
3
+ from bs4 import BeautifulSoup
4
  from transformers import pipeline
5
+
6
+
7
  @st.cache_resource
8
  def load_model():
9
  return pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
10
 
11
  model = load_model()
12
 
13
+ def extract_article_text(url):
14
+ try:
15
+ response = requests.get(url)
16
+ response.raise_for_status()
17
+ soup = BeautifulSoup(response.text, 'html.parser')
18
+ article = soup.find('div', class_='article__content')
19
+ if article:
20
+ return article.get_text(strip=True)
21
+ else:
22
+ return "Article not found."
23
+ except Exception as e:
24
+ return f"Error: {e}"
25
 
26
  st.title("Tag Detection from CNN News articles")
27
  st.write("Enter a CNN News article URL.")
28
 
29
  news_url = st.text_input("CNN Article URL:", placeholder="Example: https://edition.cnn.com/2024/12/19/science/stonehenge-monument-early-farmers/index.html")
30
  categories = ["Politics", "Sports", "Weather", "Culture", "Crime"]
31
+
32
+ if st.button("Get tags"):
33
+ if news_url.strip():
34
+ pass
35
+ else:
36
+ st.write("Please enter a valid news URL.")