Update app.py

app.py

@@ -4,7 +4,6 @@ import plotly.express as px
 import requests
 from io import BytesIO
 from PyPDF2 import PdfReader
-import time
 
 # Set Page Configurations
 st.set_page_config(page_title="GreenLens-AI", layout="wide")
@@ -36,56 +35,52 @@ st.markdown("<p>A Sustainable Tool for Calculating Carbon, Energy, and Ecologica
 DATASET_URL = "https://drive.google.com/uc?id=1QY9yv2mhz4n8bOTi4ahbjBpapltqXV6D"
 
 # Function to fetch dataset from Google Drive
-@st.cache_data
 def fetch_pdf_from_drive(url):
     """Fetch the dataset (PDF) from Google Drive."""
-    progress_text = "Downloading dataset from Google Drive..."
-    progress_bar = st.progress(0)
-
-    try:
-        response = requests.get(url, stream=True)
+    st.info("Downloading dataset from Google Drive...")
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
         total_size = int(response.headers.get('content-length', 0))
         downloaded_size = 0
         chunks = []
 
-        for chunk in response.iter_content(chunk_size=8192):
-            downloaded_size += len(chunk)
-            progress_bar.progress(min(1.0, downloaded_size / total_size), text=progress_text)
-            chunks.append(chunk)
+        with st.spinner("Fetching dataset..."):
+            for chunk in response.iter_content(chunk_size=8192):
+                downloaded_size += len(chunk)
+                chunks.append(chunk)
 
         pdf_content = b"".join(chunks)
-        progress_bar.progress(1.0, text="Download Complete")
         st.success("Dataset downloaded successfully!")
         return PdfReader(BytesIO(pdf_content))
-
-    except Exception as e:
-        st.error(f"Error fetching dataset: {e}")
+    else:
+        st.error("Failed to fetch dataset. Please check the URL or your internet connection.")
         return None
 
-# Function to extract data from the PDF
-@st.cache_data
+# Function to extract relevant data from the PDF
 def process_pdf_data(pdf_reader):
-    """Extract relevant data from the PDF."""
+    """Process the PDF file and extract relevant data."""
+    st.info("Processing dataset...")
     extracted_data = {}
+
     for page in pdf_reader.pages:
         text = page.extract_text()
-        # Example: Extract fiber impact data or other metrics
+
+        # Example parsing rules (adjust based on the actual file format):
         if "Global average water footprint of cotton fabric" in text:
             extracted_data["Cotton"] = {"Water": 10000, "Energy": 60, "Carbon": 3.18}
         if "Water footprint by region: China" in text:
             extracted_data["China"] = {"Water": 6000}
+
+    st.success("Dataset processed successfully!")
     return extracted_data
 
-# Fetch and process the dataset
-st.info("Fetching dataset. Please wait...")
+# Step 1: Fetch dataset from Google Drive
 pdf_reader = fetch_pdf_from_drive(DATASET_URL)
 if pdf_reader:
     fiber_impact_data = process_pdf_data(pdf_reader)
-    if not fiber_impact_data:
-        st.error("Failed to extract data from the PDF. Please check the PDF structure.")
+    st.write(fiber_impact_data)  # Debugging: Display parsed data
 else:
-    st.error("Failed to fetch the dataset. Check your internet connection or the dataset link.")
-    fiber_impact_data = {}
+    st.stop()
 
 # Sidebar for User Inputs
 st.sidebar.header("Input Product Details")