Update verifier.py

verifier.py

@@ -59,6 +59,45 @@ def verifier_page():
                         # Update the session state with the selected file details
                         st.session_state.selected_file = row['filename']
                         st.session_state.selected_text = row['text']
+
+
+                        def extract_text_from_pdf(uploaded_file, start_page, end_page):
+                            if uploaded_file is None:
+                                return ""  # Return an empty string if no file is uploaded
+        
+                            reader = PyPDF2.PdfReader(uploaded_file)
+                            num_pages = len(reader.pages)
+    
+                            if start_page < 0 or start_page >= num_pages:
+                                start_page = 0
+                            if end_page < start_page or end_page >= num_pages:
+                                end_page = num_pages - 1
+    
+                            text = ''
+                            for page_num in range(start_page, end_page + 1):
+                                page = reader.pages[page_num]
+                                text += page.extract_text()
+    
+                            return text
+
+
+                        pdf_path = 'VCS-Standard.pdf'
+                        start_page = 0  # Start extracting from the first page (0-based index)
+                        end_page = 93    # Extract up to the third page (0-based index)
+                        vcs_text = extract_text_from_pdf(pdf_path, start_page, end_page)
+                        print(vcs_text)
+                        
+                        pdf_path = 'VCS-Methodology-Requirements.pdf'
+                        start_page = 0  # Start extracting from the first page (0-based index)
+                        end_page = 89    # Extract up to the third page (0-based index)
+                        methodology_text = extract_text_from_pdf(pdf_path, start_page, end_page)
+                        print(methodology_text)
+                        
+                        pdf_path = 'VCS-Project-Description-Template-v4.4-FINAL2.docx.pdf'
+                        start_page = 0  # Start extracting from the first page (0-based index)
+                        end_page = 34    # Extract up to the third page (0-based index)
+                        template_text = extract_text_from_pdf(pdf_path, start_page, end_page)
+                        print(template_text)
     
                         # Configure AI (this could be dynamic depending on how your setup works)
                         GOOGLE_API_KEY = "AIzaSyC7TpzrIH_3-dppWE8exqdZX3DAdE6cy8w"