Add enhanced PDF parsing with Student fields and folder organization

pdf_renamer.py

@@ -52,10 +52,21 @@ def extract_names_from_pdf(pdf_path):
     try:
         reader = PdfReader(pdf_path)
         fields = reader.get_fields()
-        last_name = fields.get('Last Name', {}).get('/V', '')
-        first_name = fields.get('First Name', {}).get('/V', '')
-        if last_name and first_name:
-            return f"{last_name}_{first_name}.pdf"
+        
+        # Extract all required fields
+        last_name = fields.get('Last Name', {}).get('/V', '').strip()
+        first_name = fields.get('First Name', {}).get('/V', '').strip()
+        grade = fields.get('Student Grade', {}).get('/V', '').strip()
+        school = fields.get('Student School', {}).get('/V', '').strip()
+        
+        if last_name and first_name and grade and school:
+            return {
+                'filename': f"{last_name}_{first_name}.pdf",
+                'last_name': last_name,
+                'first_name': first_name,
+                'grade': grade,
+                'school': school
+            }
         else:
             return None
     except Exception as e:
@@ -66,6 +77,10 @@ def process_job(job_id, files):
     processed_files = []
     temp_extract_dirs = []
     
+    # Create base Episode directory for this job
+    episode_dir = os.path.join(app.config['UPLOAD_FOLDER'], f'Episode_{job_id}')
+    os.makedirs(episode_dir, exist_ok=True)
+    
     for file_info in files:
         filepath = file_info['path']
         filename = file_info['name']
@@ -82,40 +97,55 @@ def process_job(job_id, files):
                 for f in files_in_zip:
                     if f.lower().endswith('.pdf'):
                         pdf_path = os.path.join(root, f)
-                        new_name = extract_names_from_pdf(pdf_path)
-                        if new_name:
-                            new_path = os.path.join(root, new_name)
+                        pdf_info = extract_names_from_pdf(pdf_path)
+                        if pdf_info:
+                            # Create folder structure: Episode/School/Grade/
+                            school_dir = os.path.join(episode_dir, pdf_info['school'])
+                            grade_dir = os.path.join(school_dir, pdf_info['grade'])
+                            os.makedirs(grade_dir, exist_ok=True)
+                            
+                            # Move file to appropriate folder with new name
+                            new_path = os.path.join(grade_dir, pdf_info['filename'])
                             counter = 1
                             while os.path.exists(new_path):
-                                base, ext = os.path.splitext(new_name)
-                                new_path = os.path.join(root, f"{base}_{counter}{ext}")
+                                base, ext = os.path.splitext(pdf_info['filename'])
+                                new_path = os.path.join(grade_dir, f"{base}_{counter}{ext}")
                                 counter += 1
                             os.rename(pdf_path, new_path)
-                            processed_files.append(('success', os.path.relpath(new_path, extract_dir), new_path))
+                            processed_files.append(('success', os.path.relpath(new_path, episode_dir), new_path))
                         else:
                             processed_files.append(('skipped', f, None))
         else:
             # Single PDF
-            new_name = extract_names_from_pdf(filepath)
-            if new_name:
-                new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{new_name}")
+            pdf_info = extract_names_from_pdf(filepath)
+            if pdf_info:
+                # Create folder structure: Episode/School/Grade/
+                school_dir = os.path.join(episode_dir, pdf_info['school'])
+                grade_dir = os.path.join(school_dir, pdf_info['grade'])
+                os.makedirs(grade_dir, exist_ok=True)
+                
+                # Move file to appropriate folder with new name
+                new_filepath = os.path.join(grade_dir, pdf_info['filename'])
                 counter = 1
                 while os.path.exists(new_filepath):
-                    base, ext = os.path.splitext(new_name)
-                    new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{base}_{counter}{ext}")
+                    base, ext = os.path.splitext(pdf_info['filename'])
+                    new_filepath = os.path.join(grade_dir, f"{base}_{counter}{ext}")
                     counter += 1
                 os.rename(filepath, new_filepath)
-                processed_files.append(('success', os.path.basename(new_filepath), new_filepath))
+                processed_files.append(('success', os.path.relpath(new_filepath, episode_dir), new_filepath))
             else:
                 processed_files.append(('skipped', filename, None))
     
-    # Create ZIP of all successful renames
+    # Create ZIP of the entire Episode directory structure
     successful_files = [p for p in processed_files if p[0] == 'success']
     if successful_files:
         zip_output = os.path.join(app.config['UPLOAD_FOLDER'], f'renamed_{job_id}.zip')
         with zipfile.ZipFile(zip_output, 'w') as zip_out:
-            for _, rel_name, full_path in successful_files:
-                zip_out.write(full_path, rel_name)
+            for root, dirs, files_in_dir in os.walk(episode_dir):
+                for file in files_in_dir:
+                    file_path = os.path.join(root, file)
+                    arcname = os.path.relpath(file_path, episode_dir)
+                    zip_out.write(file_path, arcname)
         job_queue[job_id]['zip_path'] = zip_output
         job_queue[job_id]['zip_name'] = f'renamed_{job_id}.zip'