Upload 3 files

app.py

@@ -0,0 +1,169 @@
+import gradio as gr
+from transformers import pipeline
+import feedparser
+from datetime import datetime, timedelta
+import pytz
+from bs4 import BeautifulSoup
+import hashlib
+import threading
+import pandas as pd
+
+# Global settings
+SUMMARIZER_MODELS = {
+    "Default (facebook/bart-large-cnn)": "facebook/bart-large-cnn",
+    "Free Model (distilbart-cnn-6-6)": "sshleifer/distilbart-cnn-6-6"
+}
+CACHE_SIZE = 500
+RSS_FETCH_INTERVAL = timedelta(hours=8)
+ARTICLE_LIMIT = 5
+
+NEWS_SOURCES = {
+    "Movilizaciones Sindicales": {
+      
+        "Pagina12": "https://www.pagina12.com.ar/rss/edicion-impresa",
+       
+    }
+}
+
+class NewsCache:
+    def __init__(self, size):
+        self.cache = {}
+        self.size = size
+        self.lock = threading.Lock()
+
+    def get(self, key):
+        with self.lock:
+            return self.cache.get(key)
+
+    def set(self, key, value):
+        with self.lock:
+            if len(self.cache) >= self.size:
+                oldest_key = next(iter(self.cache))
+                del self.cache[oldest_key]
+            self.cache[key] = value
+
+cache = NewsCache(CACHE_SIZE)
+
+def fetch_rss_news(categories):
+    articles = []
+    cutoff_time = datetime.now(pytz.UTC) - RSS_FETCH_INTERVAL
+    for category in categories:
+        for source, url in NEWS_SOURCES.get(category, {}).items():
+            try:
+                feed = feedparser.parse(url)
+                for entry in feed.entries:
+                    published = datetime(*entry.published_parsed[:6], tzinfo=pytz.UTC)
+                    if published > cutoff_time:
+                        articles.append({
+                            "title": entry.title,
+                            "description": BeautifulSoup(entry.description, "html.parser").get_text(),
+                            "link": entry.link,
+                            "category": category,
+                            "source": source,
+                            "published": published
+                        })
+            except Exception:
+                continue
+    articles = sorted(articles, key=lambda x: x["published"], reverse=True)[:ARTICLE_LIMIT]
+    return articles
+
+def summarize_text(text, model_name):
+    summarizer = pipeline("summarization", model=model_name, device=-1)
+    content_hash = hashlib.md5(text.encode()).hexdigest()
+    cached_summary = cache.get(content_hash)
+    if cached_summary:
+        return cached_summary
+    try:
+        result = summarizer(text, max_length=120, min_length=40, truncation=True)
+        summary = result[0]['summary_text']
+        cache.set(content_hash, summary)
+        return summary
+    except Exception:
+        return "Summary unavailable."
+
+def summarize_articles(articles, model_name):
+    summaries = []
+    for article in articles:
+        content = article["description"]
+        summary = summarize_text(content, model_name)
+        summaries.append(f"""
+        📰 {article['title']}
+        - 📁 Category: {article['category']}
+        - 💡 Source: {article['source']}
+        - 🔗 Read More: {article['link']}
+        📃 Summary: {summary}
+        """)
+    return "\n".join(summaries)
+
+def generate_summary(selected_categories, model_name):
+    if not selected_categories:
+        return "Please select at least one category."
+    articles = fetch_rss_news(selected_categories)
+    if not articles:
+        return "No recent news found in the selected categories."
+    return summarize_articles(articles, model_name)
+
+def fetch_union_mobilizations():
+    articles = []
+    cutoff_time = datetime.now(pytz.UTC) - timedelta(days=1)
+    for source, url in NEWS_SOURCES["Movilizaciones Sindicales"].items():
+        try:
+            feed = feedparser.parse(url)
+            for entry in feed.entries:
+                published = datetime(*entry.published_parsed[:6], tzinfo=pytz.UTC)
+                if published > cutoff_time:
+                    # Filtrar por movilizaciones sindicales
+                    if "movilización" in entry.title.lower() or "sindical" in entry.title.lower():
+                        articles.append({
+                            "title": entry.title,
+                            "description": BeautifulSoup(entry.description, "html.parser").get_text(),
+                            "link": entry.link,
+                            "source": source,
+                            "published": published
+                        })
+        except Exception:
+            continue
+    return articles
+
+def create_mobilization_table():
+    articles = fetch_union_mobilizations()
+    if not articles:
+        return "No se encontraron movilizaciones sindicales recientes."
+    
+    # Crear una tabla con pandas
+    df = pd.DataFrame(articles)
+    return df.to_string(index=False)
+
+# Gradio Interface
+demo = gr.Blocks()
+
+with demo:
+    gr.Markdown("# 📰 AI News Summarizer")
+    with gr.Row():
+        categories = gr.CheckboxGroup(
+            choices=list(NEWS_SOURCES.keys()),
+            label="Select News Categories"
+        )
+        model_selector = gr.Radio(
+            choices=list(SUMMARIZER_MODELS.keys()),
+            label="Choose Summarization Model",
+            value="Default (facebook/bart-large-cnn)"
+        )
+    summarize_button = gr.Button("Get News Summary")
+    summary_output = gr.Textbox(label="News Summary", lines=20)
+
+    def get_summary(selected_categories, selected_model):
+        model_name = SUMMARIZER_MODELS[selected_model]
+        return generate_summary(selected_categories, model_name)
+
+    summarize_button.click(get_summary, inputs=[categories, model_selector], outputs=summary_output)
+
+if __name__ == "__main__":
+    demo.launch()
+
+
+
+
+
+
+

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,7 @@
+transformers>=4.30.0
+gradio>=3.0.0
+feedparser>=6.0.0
+torch>=1.8.0
+beautifulsoup4>=4.9.0
+pytz>=2023.3
+requests>=2.31.0