Update app.py

app.py

@@ -25,13 +25,13 @@ Summary:
 """)
 summary_chain = LLMChain(llm=llm, prompt=summary_prompt)
 
-# Extract main article content
+# Extract main article content (first 20 meaningful paragraphs)
 def extract_main_content(url):
     resp = requests.get(url, timeout=10)
     soup = BeautifulSoup(resp.content, "html.parser")
     for tag in soup(["nav","header","footer","aside","script","style","noscript"]): tag.decompose()
-    paras = soup.find_all("p")
-    content = "\n".join(p.get_text() for p in paras if len(p.get_text())>60)
+    paras = [p.get_text() for p in soup.find_all("p") if len(p.get_text()) > 60]
+    content = "\n".join(paras[:20])  # limit to top 20 paragraphs
     return content or None
 
 # Create gradient background image
@@ -39,28 +39,26 @@ def create_background(image_path, size=(1280,720)):
     img = Image.new("RGB", size)
     draw = ImageDraw.Draw(img)
     for i in range(size[1]):
-        # gradient from dark blue to black
         r = int(10 + (i/size[1])*20)
         g = int(20 + (i/size[1])*30)
         b = int(50 + (i/size[1])*50)
         draw.line([(0, i), (size[0], i)], fill=(r, g, b))
     img.save(image_path)
 
-# Generate AV summary
+# Generate 5s AV summary
 def url_to_av_summary(url):
     text = extract_main_content(url)
     if not text:
         return "Failed to extract article content.", None
-    text = text[:3000]
-    summary = summary_chain.run(text=text)
-    summary = summary.replace('"','')
-    # TTS
+    text = text[:2000]  # truncate
+    summary = summary_chain.run(text=text).replace('"','')[:250]  # short summary
+
     audio_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3").name
     gTTS(text=summary).save(audio_path)
-    # Background image
+
     bg_path = tempfile.NamedTemporaryFile(delete=False, suffix=".png").name
     create_background(bg_path)
-    # Video with animated text
+
     video_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4").name
     cmd = [
         'ffmpeg', '-y',
@@ -69,16 +67,16 @@ def url_to_av_summary(url):
         '-vf', (
             "drawtext=fontfile=/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf:text='" + summary +
             "':fontcolor=white:fontsize=48:box=1:[email protected]:boxborderw=5:"
-            "x=(w-text_w)/2:y=h-(t*(h+text_h)/300)"
+            "x=(w-text_w)/2:y=h-(t*(h+text_h)/5)"
         ),
-        '-t', '300',  # 5 minutes max
+        '-t', '5',
         '-c:v', 'libx264', '-c:a', 'aac', '-pix_fmt', 'yuv420p', '-shortest', video_path
     ]
     subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
     return summary, video_path
 
-# Timeout wrapper
-def safe_summary(url, timeout_secs=300):
+# Timeout wrapper: 60s max
+def safe_summary(url, timeout_secs=60):
     with concurrent.futures.ThreadPoolExecutor() as executor:
         future = executor.submit(url_to_av_summary, url)
         try:
@@ -90,9 +88,9 @@ iface = gr.Interface(
     fn=safe_summary,
     inputs=gr.Textbox(label="Article URL"),
     outputs=[gr.Textbox(label="Summary"), gr.Video(label="Video Preview")],
-    title="🎥 Promo-Style AV Summary with Gradient Background",
-    description="Generates a video (max 5 min) with animated text over a gradient background. CPU-only, Hugging Face Spaces-ready."
+    title="🎥 5-Second AV Summary (CPU-only)",
+    description="Fast, CPU-only AV summary of a URL. Video capped at 5 seconds to prevent timeouts."
 )
 
 if __name__ == '__main__':
-    iface.launch()
+    iface.launch()