Update app.py

app.py

@@ -83,8 +83,7 @@ def get_docparser_data(file, api_key, parser_id) -> Optional[dict]:
         import base64
         auth_string = base64.b64encode(f"{api_key}:".encode()).decode()
         headers = {
-            'Authorization': f'Basic {auth_string}',
-            'Content-Type': 'multipart/form-data'
+            'Authorization': f'Basic {auth_string}'
         }
         
         # Prepare the file for upload
@@ -95,55 +94,60 @@ def get_docparser_data(file, api_key, parser_id) -> Optional[dict]:
         # Upload document
         upload_response = requests.post(
             upload_url,
-            headers={'Authorization': f'Basic {auth_string}'},
+            headers=headers,
             files=files
         )
         upload_response.raise_for_status()
         
         # Get document ID from upload response
         upload_data = upload_response.json()
-        if not isinstance(upload_data, list) or len(upload_data) == 0:
-            st.error(f"Invalid response from Docparser upload: {upload_data}")
-            return None
-            
-        document_id = upload_data[0].get('id')
+        
+        # Extract document ID from the correct response format
+        document_id = upload_data.get('id')
         if not document_id:
             st.error("Failed to get document ID from upload response")
             return None
 
         # Wait a moment for processing
         import time
-        time.sleep(2)  # Give Docparser time to process the document
+        time.sleep(3)  # Increased wait time to ensure document is processed
 
         # Get parsed results
         results_url = f"https://api.docparser.com/v1/results/{parser_id}/{document_id}"
         results_response = requests.get(
             results_url,
-            headers={'Authorization': f'Basic {auth_string}'}
+            headers=headers
         )
         results_response.raise_for_status()
         
         # Handle results
         results_data = results_response.json()
         
-        # Debug information
-        st.write("Debug - API Response:", results_data)
-        
         if isinstance(results_data, list) and len(results_data) > 0:
-            # Extract the relevant fields based on your Docparser parser configuration
+            # Map the fields according to your Docparser parser configuration
+            result = results_data[0]  # Get the first result
             parsed_data = {
-                'name': results_data[0].get('full_name', 'Unknown'),
-                'email': results_data[0].get('email', 'Unknown'),
-                'phone': results_data[0].get('phone', 'Unknown'),
-                'skills': [skill.strip() for skill in results_data[0].get('skills', '').split(',') if skill.strip()],
-                'certifications': results_data[0].get('certifications', []),
-                'experience_years': float(results_data[0].get('experience_years', 0)),
-                'degree': results_data[0].get('degree', 'Not specified'),
-                'institution': results_data[0].get('institution', 'Not specified'),
-                'year': results_data[0].get('graduation_year', 'Not specified'),
-                'summary': results_data[0].get('summary', 'No summary available'),
-                'projects': results_data[0].get('projects', [])
+                'name': result.get('name', result.get('full_name', 'Unknown')),
+                'email': result.get('email', 'Unknown'),
+                'phone': result.get('phone', result.get('phone_number', 'Unknown')),
+                'skills': result.get('skills', []),
+                'certifications': result.get('certifications', []),
+                'experience_years': float(result.get('experience_years', 0)),
+                'degree': result.get('degree', result.get('education_degree', 'Not specified')),
+                'institution': result.get('institution', result.get('university', 'Not specified')),
+                'year': result.get('year', result.get('graduation_year', 'Not specified')),
+                'summary': result.get('summary', result.get('profile_summary', 'No summary available')),
+                'projects': result.get('projects', [])
             }
+            
+            # Convert skills from string to list if needed
+            if isinstance(parsed_data['skills'], str):
+                parsed_data['skills'] = [skill.strip() for skill in parsed_data['skills'].split(',')]
+            
+            # Convert certifications from string to list if needed
+            if isinstance(parsed_data['certifications'], str):
+                parsed_data['certifications'] = [cert.strip() for cert in parsed_data['certifications'].split(',')]
+            
             return parsed_data
         else:
             st.error(f"No parsed data received from Docparser: {results_data}")
@@ -158,6 +162,8 @@ def get_docparser_data(file, api_key, parser_id) -> Optional[dict]:
         st.error("Raw response content: " + str(upload_response.content if 'upload_response' in locals() else 'No response'))
     except Exception as e:
         st.error(f"Error fetching data from Docparser: {e}")
+        st.error(f"Upload data: {upload_data if 'upload_data' in locals() else 'No upload data'}")
+        st.error(f"Results data: {results_data if 'results_data' in locals() else 'No results data'}")
     return None
 
 def get_openai_data(file, openai_key: str) -> Optional[dict]: