Update app.py

app.py

@@ -1,111 +1,115 @@
 import gradio as gr
-from playwright.sync_api import sync_playwright
-import time
-import json
-from download_browsers import download_playwright_browsers
+import pandas as pd
+import numpy as np
+from datetime import datetime
 
-# Download browsers on startup
-download_playwright_browsers()
-
-def scrape_website(url, wait_time=5):
-    """
-    Scrape a website using Playwright headless browser
-    Args:
-        url (str): The URL to scrape
-        wait_time (int): Time to wait for dynamic content to load
-    Returns:
-        dict: Dictionary containing scraped data
-    """
+def parse_wind(wind_str):
+    if pd.isna(wind_str):
+        return np.nan, np.nan
     try:
-        with sync_playwright() as p:
-            # Launch browser in headless mode
-            browser = p.chromium.launch(headless=True)
-            context = browser.new_context(
-                user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
-            )
-            page = context.new_page()
-            
-            # Go to URL and wait for network to be idle
-            page.goto(url, wait_until="networkidle")
-            time.sleep(wait_time)  # Additional wait for dynamic content
-            
-            # Get basic page information
-            title = page.title()
-            
-            # Extract all text content
-            text_content = page.text_content('body')
-            
-            # Extract all links
-            links = page.eval_on_selector_all('a[href]', 'elements => elements.map(el => el.href)')
-            
-            # Extract all images
-            images = page.eval_on_selector_all('img[src]', 'elements => elements.map(el => el.src)')
-            
-            # Get meta description
-            meta_description = page.eval_on_selector('meta[name="description"]', 
-                'element => element.content') if page.query_selector('meta[name="description"]') else ''
-            
-            # Close browser
-            browser.close()
-            
-            return {
-                "title": title,
-                "meta_description": meta_description,
-                "text_content": text_content[:1000] + "...",  # Truncate for display
-                "links": links[:10],  # Show first 10 links
-                "images": images[:5],  # Show first 5 images
-                "status": "Success"
-            }
-            
-    except Exception as e:
-        return {
-            "status": "Error",
-            "error_message": str(e)
-        }
+        if 'G' in str(wind_str):
+            speed, gust = str(wind_str).split('G')
+            return float(speed), float(gust)
+        return float(wind_str), np.nan
+    except:
+        return np.nan, np.nan
 
-def format_output(result):
-    """Format the output for better display in Gradio"""
-    if result["status"] == "Error":
-        return f"Error: {result['error_message']}"
+def process_weather_data(data_str):
+    # Split the data into lines and remove empty lines
+    lines = [line.strip() for line in data_str.split('\n') if line.strip()]
     
-    output = f"""
-### Page Title
-{result['title']}
-
-### Meta Description
-{result['meta_description']}
-
-### First 1000 characters of content
-{result['text_content']}
-
-### First 10 Links
-{json.dumps(result['links'], indent=2)}
-
-### First 5 Images
-{json.dumps(result['images'], indent=2)}
-    """
-    return output
+    # Find the start of actual data (after headers)
+    start_idx = 0
+    for i, line in enumerate(lines):
+        if 'Date/Time' in line:
+            start_idx = i + 1
+            break
+    
+    # Process the data lines
+    data = []
+    for line in lines[start_idx:]:
+        parts = line.split('\t')
+        if len(parts) >= 8:
+            try:
+                date_str = parts[0].strip()
+                temp = float(parts[1]) if parts[1].strip() else np.nan
+                dew_point = float(parts[2]) if parts[2].strip() else np.nan
+                humidity = float(parts[3]) if parts[3].strip() else np.nan
+                wind_chill = float(parts[4]) if parts[4].strip() else np.nan
+                wind_speed, wind_gust = parse_wind(parts[6])
+                snow_depth = float(parts[7]) if parts[7].strip() else np.nan
+                
+                data.append({
+                    'datetime': pd.to_datetime(date_str),
+                    'temperature': temp,
+                    'dew_point': dew_point,
+                    'humidity': humidity,
+                    'wind_chill': wind_chill,
+                    'wind_speed': wind_speed,
+                    'wind_gust': wind_gust,
+                    'snow_depth': snow_depth
+                })
+            except:
+                continue
+    
+    df = pd.DataFrame(data)
+    
+    # Calculate statistics
+    stats = {
+        'Temperature Range': f"{df['temperature'].min():.1f}°F to {df['temperature'].max():.1f}°F",
+        'Average Temperature': f"{df['temperature'].mean():.1f}°F",
+        'Max Wind Speed': f"{df['wind_speed'].max():.1f} mph",
+        'Max Wind Gust': f"{df['wind_gust'].max():.1f} mph",
+        'Average Humidity': f"{df['humidity'].mean():.1f}%",
+        'Max Snow Depth': f"{df['snow_depth'].max():.1f} inches"
+    }
+    
+    # Create plots
+    temp_fig = gr.Plot()
+    df.plot(x='datetime', y=['temperature', 'wind_chill'], 
+            title='Temperature and Wind Chill Over Time',
+            figsize=(12, 6))
+    temp_fig.pyplot()
+    
+    wind_fig = gr.Plot()
+    df.plot(x='datetime', y=['wind_speed', 'wind_gust'],
+            title='Wind Speed and Gusts Over Time',
+            figsize=(12, 6))
+    wind_fig.pyplot()
+    
+    stats_html = "<div style='font-size: 16px; line-height: 1.5;'>"
+    for key, value in stats.items():
+        stats_html += f"<p><strong>{key}:</strong> {value}</p>"
+    stats_html += "</div>"
+    
+    return stats_html, temp_fig, wind_fig
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=lambda url, wait_time: format_output(scrape_website(url, wait_time)),
-    inputs=[
-        gr.Textbox(label="URL to scrape", placeholder="https://example.com"),
-        gr.Slider(minimum=1, maximum=15, value=5, step=1, label="Wait time (seconds)")
-    ],
-    outputs=gr.Markdown(),
-    title="Web Scraper with Headless Browser",
-    description="""
-    Enter a URL to scrape its content using a headless browser.
-    The tool will extract the title, meta description, text content, links, and images.
-    Please use responsibly and respect websites' terms of service and robots.txt files.
-    """,
-    examples=[
-        ["https://example.com", 5],
-        ["https://news.ycombinator.com", 8]
-    ]
-)
+# Create the Gradio interface
+with gr.Blocks(title="Weather Data Analysis") as demo:
+    gr.Markdown("# Weather Data Analysis")
+    gr.Markdown("Paste weather data from weather.gov/wrh/timeseries in the format shown below:")
+    
+    with gr.Row():
+        input_text = gr.Textbox(
+            label="Weather Data",
+            placeholder="Paste weather data here...",
+            lines=10
+        )
+    
+    analyze_btn = gr.Button("Analyze Weather Data")
+    
+    with gr.Row():
+        stats_output = gr.HTML(label="Statistics")
+    
+    with gr.Row():
+        temp_plot = gr.Plot(label="Temperature Plot")
+        wind_plot = gr.Plot(label="Wind Plot")
+    
+    analyze_btn.click(
+        fn=process_weather_data,
+        inputs=[input_text],
+        outputs=[stats_output, temp_plot, wind_plot]
+    )
 
-# Launch the interface
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()