news api integration

app.py

@@ -2,12 +2,16 @@ import gradio as gr
 import random
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
+import requests
+from bs4 import BeautifulSoup
 
 tokenizer = AutoTokenizer.from_pretrained("liamvbetts/bart-large-cnn-v4")
 model = AutoModelForSeq2SeqLM.from_pretrained("liamvbetts/bart-large-cnn-v4")
 
 dataset = load_dataset("cnn_dailymail", "3.0.0")
 
+NEWS_API_KEY = "da2cc601304341e7a39cb5604d0b076b"  
+
 def summarize(article):
     inputs = tokenizer(article, return_tensors="pt").input_ids
     outputs = model.generate(inputs, max_new_tokens=128, do_sample=False)
@@ -23,15 +27,61 @@ def get_random_article():
 def load_article():
     return get_random_article()
 
+def get_news_article():
+    url = 'https://newsapi.org/v2/top-headlines'
+    news_url = ''
+    params = {
+        'apiKey': NEWS_API_KEY,
+        'country': 'us',  # You can change this as needed
+        'pageSize': 100
+    }
+    response = requests.get(url, params=params)
+    articles = response.json().get('articles', [])
+    if articles:
+        random_article = random.choice(articles)
+        news_url = random_article.get('url')
+    else:
+        return None
+    
+    if news_url:
+        full_article, title = scrape_article(news_url)
+        return full_article, title
+    else:
+        return "No news article found.", ""
+
+def scrape_article(url):
+    try:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.content, 'html.parser')
+        
+        # Extracting the title - this is a general approach
+        title = soup.title.string if soup.title else "No Title Available"
+
+        article_content = soup.find_all('p')  # This is a simplification
+        
+        text = ' '.join([p.get_text() for p in article_content])
+        words = text.split()
+        truncated_text = ' '.join(words[:1024])  # Truncate to first 1024 words
+
+        return truncated_text, title
+    except Exception as e:
+        return "Error scraping article: " + str(e), ""
+
 # Using Gradio Blocks
 with gr.Blocks() as demo:
     gr.Markdown("## News Summary App")
-    gr.Markdown("Enter a news text and get its summary, or load a random article from the validation set.")
+    gr.Markdown("Enter a news text and get its summary, or load a random article.")
     with gr.Row():
+        article_title = gr.Label()  # Component to display the article title
         input_text = gr.Textbox(lines=10, label="Input Text")
         output_text = gr.Textbox(label="Summary")
-    load_article_button = gr.Button("Load Random Article")
-    load_article_button.click(fn=load_article, inputs=[], outputs=input_text)
+
+    load_dataset_article_button = gr.Button("Load Random Article from Dataset")
+    load_news_article_button = gr.Button("Load News Article")
+
+    load_dataset_article_button.click(fn=load_article, inputs=[], outputs=input_text)
+    load_news_article_button.click(fn=get_news_article, inputs=[], outputs=[input_text, article_title])
+
     summarize_button = gr.Button("Summarize")
     summarize_button.click(fn=summarize, inputs=input_text, outputs=output_text)
 

requirements.txt

@@ -4,3 +4,4 @@ datasets
 evaluate
 accelerate
 torch
+beautifulsoup4