🔍 Code Extractor

A SharePoint REST API client that provides app-only authentication and methods for retrieving and downloading documents from SharePoint sites.

Purpose

This class implements a SharePoint client using direct REST API calls with OAuth 2.0 client credentials flow for app-only authentication. It provides functionality to connect to SharePoint sites, retrieve document listings recursively from folders, download file content, and get detailed file information. The client bypasses potential issues with the office365 library by using direct HTTP requests to SharePoint REST endpoints.

Source Code

class SharePointRestClient:
    """
    SharePoint client using direct REST API calls with app-only authentication.
    This bypasses potential issues with the office365 library.
    """
    
    def __init__(self, site_url: str, client_id: str, client_secret: str):
        """
        Initialize SharePoint REST client.
        
        Args:
            site_url: SharePoint site URL
            client_id: Azure AD app client ID
            client_secret: Azure AD app client secret
        """
        self.site_url = site_url.rstrip('/')
        self.client_id = client_id
        self.client_secret = client_secret
        
        # Extract tenant information
        if '.sharepoint.com' in site_url:
            self.tenant = site_url.split('.sharepoint.com')[0].split('https://')[-1]
            self.sharepoint_resource = f"https://{self.tenant}.sharepoint.com"
        else:
            raise ValueError("Invalid SharePoint URL format")
        
        # Setup logging
        self.logger = logging.getLogger(__name__)
        
        # Get access token
        self.access_token = self._get_access_token()
        if self.access_token:
            self.logger.info("Successfully authenticated with SharePoint")
            self._test_connection()
        else:
            raise ConnectionError("Failed to authenticate with SharePoint")
    
    def _get_access_token(self) -> Optional[str]:
        """Get access token for SharePoint."""
        token_url = f"https://login.microsoftonline.com/{self.tenant}.onmicrosoft.com/oauth2/v2.0/token"
        
        data = {
            'client_id': self.client_id,
            'client_secret': self.client_secret,
            'scope': f'{self.sharepoint_resource}/.default',
            'grant_type': 'client_credentials'
        }
        
        try:
            response = requests.post(token_url, data=data)
            if response.status_code == 200:
                token_data = response.json()
                return token_data.get('access_token')
            else:
                error_data = response.json() if response.content else {}
                self.logger.error(f"Token request failed: {error_data}")
                return None
        except Exception as e:
            self.logger.error(f"Exception getting token: {e}")
            return None
    
    def _test_connection(self) -> bool:
        """Test the SharePoint connection."""
        try:
            headers = {
                'Authorization': f'Bearer {self.access_token}',
                'Accept': 'application/json',
                'Content-Type': 'application/json'
            }
            
            response = requests.get(f"{self.site_url}/_api/web", headers=headers)
            if response.status_code == 200:
                data = response.json()
                site_title = data.get('Title', 'Unknown')
                self.logger.info(f"Successfully connected to SharePoint site: {site_title}")
                return True
            else:
                self.logger.error(f"Connection test failed: {response.status_code} - {response.text}")
                return False
        except Exception as e:
            self.logger.error(f"Connection test exception: {e}")
            return False
    
    def get_all_documents(self, folder_path: str = "/Shared Documents") -> List[Dict]:
        """
        Get all documents from SharePoint recursively using REST API.
        
        Args:
            folder_path: Server relative path to folder
            
        Returns:
            List of document information dictionaries
        """
        documents = []
        try:
            self._get_documents_recursive(folder_path, documents)
            self.logger.info(f"Retrieved {len(documents)} documents from SharePoint")
            return documents
        except Exception as e:
            self.logger.error(f"Error getting documents from {folder_path}: {e}")
            raise
    
    def _get_documents_recursive(self, folder_path: str, documents: List[Dict]):
        """
        Recursively get all documents from a folder using REST API.
        
        Args:
            folder_path: Server relative path to folder
            documents: List to append document information to
        """
        headers = {
            'Authorization': f'Bearer {self.access_token}',
            'Accept': 'application/json',
            'Content-Type': 'application/json'
        }
        
        try:
            # Get files in current folder
            files_url = f"{self.site_url}/_api/web/GetFolderByServerRelativeUrl('{folder_path}')/Files"
            files_response = requests.get(files_url, headers=headers)
            
            if files_response.status_code == 200:
                files_data = files_response.json()
                for file_info in files_data.get('value', []):
                    # Skip system files and hidden files
                    if not file_info['Name'].startswith('.') and not file_info['Name'].startswith('~'):
                        # Calculate relative path
                        server_relative_url = file_info['ServerRelativeUrl']
                        if '/Shared Documents' in server_relative_url:
                            relative_path = server_relative_url.split('/Shared Documents/')[-1]
                        else:
                            relative_path = file_info['Name']
                        
                        doc_info = {
                            'name': file_info['Name'],
                            'server_relative_url': file_info['ServerRelativeUrl'],
                            'size': file_info['Length'],
                            'modified': file_info['TimeLastModified'],
                            'created': file_info['TimeCreated'],
                            'author': file_info.get('Author', {}).get('Title', 'Unknown') if isinstance(file_info.get('Author'), dict) else 'Unknown',
                            'file_type': file_info['Name'].split('.')[-1] if '.' in file_info['Name'] else '',
                            'relative_path': relative_path
                        }
                        documents.append(doc_info)
            
            # Get subfolders
            folders_url = f"{self.site_url}/_api/web/GetFolderByServerRelativeUrl('{folder_path}')/Folders"
            folders_response = requests.get(folders_url, headers=headers)
            
            if folders_response.status_code == 200:
                folders_data = folders_response.json()
                for folder_info in folders_data.get('value', []):
                    # Skip system folders
                    if not folder_info['Name'].startswith('.') and \
                       folder_info['Name'] not in ['Forms', 'Item']:
                        subfolder_path = folder_info['ServerRelativeUrl']
                        self._get_documents_recursive(subfolder_path, documents)
                        
        except Exception as e:
            self.logger.error(f"Error processing folder {folder_path}: {e}")
            # Continue processing other folders even if one fails
    
    def download_file_content(self, server_relative_url: str) -> Optional[bytes]:
        """
        Download file content from SharePoint using REST API.
        
        Args:
            server_relative_url: SharePoint server relative URL of file
            
        Returns:
            File content as bytes, or None if failed
        """
        try:
            headers = {
                'Authorization': f'Bearer {self.access_token}',
            }
            
            # Get file content using REST API
            content_url = f"{self.site_url}/_api/web/GetFileByServerRelativeUrl('{server_relative_url}')/$value"
            response = requests.get(content_url, headers=headers)
            
            if response.status_code == 200:
                return response.content
            else:
                self.logger.error(f"Failed to download file {server_relative_url}: {response.status_code}")
                return None
                
        except Exception as e:
            self.logger.error(f"Error downloading file content {server_relative_url}: {e}")
            return None
    
    def get_file_info(self, server_relative_url: str) -> Optional[Dict]:
        """
        Get detailed information about a file using REST API.
        
        Args:
            server_relative_url: SharePoint server relative URL of file
            
        Returns:
            File information dictionary if successful, None otherwise
        """
        try:
            headers = {
                'Authorization': f'Bearer {self.access_token}',
                'Accept': 'application/json',
                'Content-Type': 'application/json'
            }
            
            file_url = f"{self.site_url}/_api/web/GetFileByServerRelativeUrl('{server_relative_url}')"
            response = requests.get(file_url, headers=headers)
            
            if response.status_code == 200:
                file_data = response.json()
                return {
                    'name': file_data['Name'],
                    'server_relative_url': file_data['ServerRelativeUrl'],
                    'size': file_data['Length'],
                    'modified': file_data['TimeLastModified'],
                    'created': file_data['TimeCreated'],
                    'version': file_data.get('UIVersionLabel', '1.0'),
                    'author': 'Unknown',  # Would need additional API call
                    'file_type': file_data['Name'].split('.')[-1] if '.' in file_data['Name'] else ''
                }
            else:
                self.logger.error(f"Failed to get file info {server_relative_url}: {response.status_code}")
                return None
                
        except Exception as e:
            self.logger.error(f"Error getting file info for {server_relative_url}: {e}")
            return None

Parameters

Parameter Details

site_url: The full URL of the SharePoint site (e.g., 'https://tenant.sharepoint.com/sites/sitename'). Must contain '.sharepoint.com' in the URL. Trailing slashes are automatically removed.

client_id: Azure AD application (app registration) client ID used for authentication. This is the Application (client) ID from Azure AD app registration.

client_secret: Azure AD application client secret used for authentication. This is the secret value (not the secret ID) created in the app registration's Certificates & secrets section.

Return Value

Instantiation returns a SharePointRestClient object with an active access token and verified connection to SharePoint. The constructor raises ConnectionError if authentication fails or ValueError if the site_url format is invalid. Methods return: get_all_documents() returns List[Dict] of document metadata; download_file_content() returns Optional[bytes] of file content; get_file_info() returns Optional[Dict] with file metadata.

Class Interface

Methods

Attributes

Dependencies

• requests
• json
• typing
• datetime
• logging

Required Imports

import requests
import json
from typing import List, Dict, Optional
from datetime import datetime
import logging

Usage Example

import logging
from typing import List, Dict, Optional
import requests

# Setup logging
logging.basicConfig(level=logging.INFO)

# Initialize the client
client = SharePointRestClient(
    site_url='https://contoso.sharepoint.com/sites/mysite',
    client_id='your-client-id-guid',
    client_secret='your-client-secret'
)

# Get all documents from default Shared Documents folder
documents = client.get_all_documents()
for doc in documents:
    print(f"File: {doc['name']}, Size: {doc['size']}, Modified: {doc['modified']}")

# Get documents from specific folder
folder_docs = client.get_all_documents('/Shared Documents/MyFolder')

# Download a specific file
file_content = client.download_file_content('/sites/mysite/Shared Documents/file.pdf')
if file_content:
    with open('downloaded_file.pdf', 'wb') as f:
        f.write(file_content)

# Get detailed file information
file_info = client.get_file_info('/sites/mysite/Shared Documents/file.pdf')
if file_info:
    print(f"Version: {file_info['version']}, Created: {file_info['created']}")

Best Practices

• Always handle ConnectionError during instantiation as authentication may fail
• The access token is obtained during initialization and stored for subsequent requests; consider token expiration for long-running applications
• Use try-except blocks when calling methods as they may raise exceptions for network or permission issues
• The client automatically tests the connection during initialization; check logs for connection status
• System files (starting with '.' or '~') and system folders ('Forms', 'Item') are automatically filtered out
• File paths should use server-relative URLs (e.g., '/sites/sitename/Shared Documents/file.pdf')
• The get_all_documents method recursively traverses all subfolders; be cautious with large document libraries
• Download operations return None on failure; always check for None before processing content
• The client continues processing other folders even if one folder fails during recursive traversal
• Ensure the Azure AD app has sufficient SharePoint permissions before instantiation

Tags

Similar Components

AI-powered semantic similarity - components with related functionality:

• class SharePointClient 79.8% similar

  A SharePoint client class that provides methods for connecting to SharePoint sites, retrieving documents recursively, downloading file content, and managing document metadata using app-only authentication.

  From: /tf/active/vicechatdev/SPFCsync/sharepoint_client.py

• function test_rest_client 75.4% similar

  A test function that validates the SharePoint REST API client by testing authentication, document listing, and file download capabilities.

  From: /tf/active/vicechatdev/SPFCsync/test_rest_client.py

• class SharePointGraphClient 70.3% similar

  SharePoint client using Microsoft Graph API. This bypasses SharePoint REST API app-only token issues.

  From: /tf/active/vicechatdev/SPFCsync/sharepoint_graph_client.py

• class NativeClient 67.7% similar

  A SharePoint OAuth client class that provides endpoints for native client authentication relative to the current request context.

  From: /tf/active/vicechatdev/SPFCsync/venv/lib64/python3.11/site-packages/office365/sharepoint/oauth/native_client.py

• function test_sharepoint_api_call 67.1% similar

  Tests SharePoint REST API connectivity by making an authenticated GET request to retrieve basic site information and validates the access token and permissions.

  From: /tf/active/vicechatdev/SPFCsync/diagnose_sharepoint.py