Update app.py

app.py

@@ -1,129 +1,112 @@
 import gradio as gr
-from playwright.sync_api import sync_playwright
 import pandas as pd
-import time
-import json
+import numpy as np
 from datetime import datetime
-import subprocess
-import sys
-import os
+import re
 
-def install_playwright_browsers():
-    try:
-        if not os.path.exists('/home/user/.cache/ms-playwright'):
-            print("Installing Playwright browsers...")
-            subprocess.run(
-                [sys.executable, "-m", "playwright", "install", "chromium"],
-                check=True,
-                capture_output=True,
-                text=True
-            )
-            print("Playwright browsers installed successfully")
-    except Exception as e:
-        print(f"Error installing browsers: {e}")
-
-install_playwright_browsers()
-
-def scrape_weather_data(site_id="YCTIM", hours=720):
-    """Debug version that prints page content"""
-    url = f"https://www.weather.gov/wrh/timeseries?site={site_id}&hours={hours}&units=english&chart=on&headers=on&obs=tabular&hourly=false&pview=full&font=12&plot="
+def parse_weather_data(text):
+    """Parse the weather data text into a structured format"""
+    lines = [line.strip() for line in text.split('\n') if line.strip()]
+    data = []
     
-    try:
-        with sync_playwright() as p:
-            browser = p.chromium.launch(
-                headless=True,
-                args=['--no-sandbox', '--disable-dev-shm-usage']
-            )
-            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()
-            
-            print("\nNavigating to URL...")
-            response = page.goto(url)
-            print(f"Response status: {response.status}")
-            
-            # Wait a bit and get the content
-            time.sleep(5)
-            
-            # Print all HTML content
-            content = page.content()
-            print("\nPage Content:")
-            print("=" * 80)
-            print(content)
-            print("=" * 80)
-            
-            # Print all text content
-            text_content = page.evaluate('() => document.body.innerText')
-            print("\nText Content:")
-            print("=" * 80)
-            print(text_content)
-            print("=" * 80)
-            
-            # List all elements
-            elements = page.evaluate('''() => {
-                const all = document.getElementsByTagName('*');
-                return Array.from(all).map(el => ({
-                    tag: el.tagName,
-                    id: el.id,
-                    class: el.className
-                }));
-            }''')
-            print("\nPage Elements:")
-            print("=" * 80)
-            for el in elements:
-                print(f"Tag: {el['tag']}, ID: {el['id']}, Class: {el['class']}")
-            print("=" * 80)
+    for line in lines:
+        if not ('am' in line or 'pm' in line):
+            continue
             
-            # Save screenshot
-            page.screenshot(path="debug_screenshot.png")
-            print("\nSaved screenshot as debug_screenshot.png")
+        parts = line.split('\t')
+        if len(parts) < 8:
+            continue
             
-            browser.close()
+        try:
+            # Parse wind speed and gusts (format: "12G30")
+            wind_match = re.search(r'(\d+)G(\d+)', parts[6]) if len(parts) > 6 else None
+            wind_speed = int(wind_match.group(1)) if wind_match else np.nan
+            wind_gust = int(wind_match.group(2)) if wind_match else np.nan
             
-            return {
-                'status': 'Debug',
-                'message': 'Check console output for page content'
+            row = {
+                'datetime': parts[0].strip(),
+                'temperature': float(parts[1]),
+                'dew_point': float(parts[2]),
+                'humidity': float(parts[3]),
+                'wind_chill': float(parts[4]) if parts[4].strip() != '' else np.nan,
+                'wind_speed': wind_speed,
+                'wind_gust': wind_gust,
+                'snow_depth': float(parts[7]) if parts[7].strip() != '' else np.nan
             }
-            
-    except Exception as e:
-        return {
-            'status': 'Error',
-            'error_message': str(e)
-        }
+            data.append(row)
+        except:
+            continue
+    
+    return pd.DataFrame(data)
 
-def format_output(result):
-    """Simple output formatter for debug version"""
-    if result['status'] == 'Error':
-        return f"Error: {result['error_message']}", None, None
-    return result['message'], None, None
+def analyze_weather_data(data_str):
+    """Analyze weather data and create visualizations"""
+    try:
+        # Parse data
+        df = parse_weather_data(data_str)
+        if len(df) == 0:
+            return "Error: No valid data found in input."
+        
+        # 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 HTML output
+        html_output = "<div style='font-size: 16px; line-height: 1.5;'>"
+        for key, value in stats.items():
+            html_output += f"<p><strong>{key}:</strong> {value}</p>"
+        html_output += "</div>"
+        
+        # Create temperature plot
+        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()
+        
+        # Create wind plot
+        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()
+        
+        return html_output, temp_fig, wind_fig
+        
+    except Exception as e:
+        return f"Error analyzing data: {str(e)}", None, None
 
 # Create Gradio interface
-with gr.Blocks(title="Weather Data Scraper Debug") as demo:
-    gr.Markdown("# Weather Data Scraper (Debug Version)")
+with gr.Blocks(title="Weather Data Analyzer") as demo:
+    gr.Markdown("# Weather Data Analyzer")
+    gr.Markdown("Paste weather data from weather.gov/wrh/timeseries in the text box below.")
     
     with gr.Row():
-        site_id = gr.Textbox(
-            label="Weather Station ID",
-            value="YCTIM",
-            placeholder="Enter station ID (e.g., YCTIM)"
-        )
-        hours = gr.Number(
-            label="Hours of Data",
-            value=720,
-            minimum=1,
-            maximum=1440
+        input_text = gr.Textbox(
+            label="Weather Data",
+            placeholder="Paste weather data here...",
+            lines=10
         )
     
-    analyze_btn = gr.Button("Fetch and Print Page Content")
+    analyze_btn = gr.Button("Analyze Weather Data")
+    
+    with gr.Row():
+        stats_output = gr.HTML(label="Statistics")
     
     with gr.Row():
-        output = gr.HTML(label="Output")
+        temp_plot = gr.Plot(label="Temperature Plot")
+        wind_plot = gr.Plot(label="Wind Plot")
     
     analyze_btn.click(
-        fn=lambda sid, hrs: format_output(scrape_weather_data(sid, hrs)),
-        inputs=[site_id, hours],
-        outputs=[output]
+        fn=analyze_weather_data,
+        inputs=[input_text],
+        outputs=[stats_output, temp_plot, wind_plot]
     )
 
 if __name__ == "__main__":