Update app.py

app.py

@@ -2,11 +2,37 @@ from pdfminer.high_level import extract_text
 
 def extract_pdf_text(file_path):
     return extract_text(file_path)
-from google.colab import drive
-drive.mount('/content/drive')
+#from google.colab import drive
+
+import zipfile
+import os
+
+# Path to the uploaded zip file
+zip_file_path = './data.zip'
+extract_folder = './data'
+
+# Unzip the file if the directory does not already exist
+if not os.path.exists(extract_folder):
+    with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
+        zip_ref.extractall(extract_folder)
+
 import os
 
-pdf_folder = '/content/drive/MyDrive'
+pdf_folder = './data'
+
+# List all PDF files in the directory
+pdf_files = [f for f in os.listdir(pdf_folder) if f.endswith('.pdf')]
+
+# Process each PDF file
+for pdf_file in pdf_files:
+    pdf_path = os.path.join(pdf_folder, pdf_file)
+    # Your code to process PDF
+
+
+#drive.mount('/content/drive')
+#import os
+
+#pdf_folder = '/content/drive/MyDrive'
 pdf_texts = []
 
 for pdf_file in os.listdir(pdf_folder):