diff --git a/download_sharepoint.py b/download_sharepoint.py index cfc4e61..b8e7c2d 100644 --- a/download_sharepoint.py +++ b/download_sharepoint.py @@ -3,36 +3,40 @@ import csv import requests import time import re +import sys from datetime import datetime from msal import ConfidentialClientApplication from urllib.parse import urlparse, quote +# Global stats to track progress +stats = { + "total_checked": 0, + "downloaded": 0, + "skipped": 0, + "failed": 0 +} + +def print_progress(force=False): + """Prints a single-line progress update.""" + if force or stats["total_checked"] % 50 == 0: + sys.stdout.write(f"\rStatus: {stats['total_checked']} checked, {stats['downloaded']} downloaded, {stats['skipped']} skipped, {stats['failed']} failed... ") + sys.stdout.flush() + def sanitize_filename(name): """Removes invalid characters and handles Unicode whitespace for Windows.""" if not name: return "unnamed_item" - - # Handle Unicode non-breaking spaces (common in SharePoint names) name = name.replace('\u00A0', ' ').replace('\u200b', '') - - # Illegal characters: < > : " / \ | ? * invalid_chars = '<>:"/\\|?*' for char in invalid_chars: name = name.replace(char, '_') - - # Control characters (0-31) name = "".join(c for c in name if ord(c) >= 32) - - # Windows doesn't like trailing spaces or dots name = name.strip(' .') - - # Reserved names reserved_names = {"CON", "PRN", "AUX", "NUL", "COM1", "COM2", "COM3", "COM4", "COM5", "COM6", "COM7", "COM8", "COM9", "LPT1", "LPT2", "LPT3", "LPT4", "LPT5", "LPT6", "LPT7", "LPT8", "LPT9"} base_part = name.split('.')[0].upper() if base_part in reserved_names: name = "_" + name - return name if name else "unnamed_item" def get_long_path(path): @@ -95,7 +99,6 @@ def download_file(download_url, local_path, expected_size): try: long_local_path = get_long_path(local_path) - # Check if file exists and size matches if os.path.exists(long_local_path): if os.path.isdir(long_local_path): return False, f"Path exists as a directory: {local_path}" @@ -109,7 +112,6 @@ def download_file(download_url, local_path, expected_size): elif not os.path.isdir(target_dir): return False, f"Parent path exists but is not a directory: {target_dir}" - # Stream download with timeout and 1MB chunks response = requests.get(download_url, stream=True, timeout=60) response.raise_for_status() with open(long_local_path, 'wb') as f: @@ -147,21 +149,30 @@ def download_folder_recursive(app, drive_id, item_path, local_root_path, report) sub_item_path = f"{item_path}/{item_name}".strip('/') download_folder_recursive(app, drive_id, sub_item_path, local_path, report) elif 'file' in item: + stats["total_checked"] += 1 download_url = item.get('@microsoft.graph.downloadUrl') if not download_url: + stats["failed"] += 1 report.append({"Path": f"{item_path}/{item_name}", "Error": "No URL", "Timestamp": datetime.now().isoformat()}) continue success, status = download_file(download_url, local_path, item['size']) if success: - if status != "Skipped": - print(f"Downloaded: {item_path}/{item_name}") + if status == "Downloaded": + stats["downloaded"] += 1 + sys.stdout.write(f"\nDownloaded: {item_path}/{item_name}\n") + else: + stats["skipped"] += 1 else: - print(f"FAILED: {item_path}/{item_name} - {status}") + stats["failed"] += 1 + sys.stdout.write(f"\nFAILED: {item_path}/{item_name} - {status}\n") report.append({"Path": f"{item_path}/{item_name}", "Error": status, "Timestamp": datetime.now().isoformat()}) + + print_progress() + except Exception as e: err_msg = f"Folder error: {str(e)}" - print(f"FAILED FOLDER: {item_path} - {err_msg}") + sys.stdout.write(f"\nFAILED FOLDER: {item_path} - {err_msg}\n") report.append({"Path": item_path, "Error": err_msg, "Timestamp": datetime.now().isoformat()}) def main(): @@ -178,33 +189,42 @@ def main(): if not folders_to_download: folders_to_download = [""] - print(f"Connecting via Graph API...") - report = [] + print("Step 1: Authenticating with Microsoft Entra ID...") + app = create_msal_app(tenant_id, client_id, client_secret) try: - app = create_msal_app(tenant_id, client_id, client_secret) + print("Step 2: Connecting to SharePoint Site...") site_id = get_site_id(app, site_url) + print(f" - Site found (ID: {site_id[:10]}...)") + + print(f"Step 3: Accessing Document Library '{drive_name}'...") drive_id = get_drive_id(app, site_id, drive_name) + print(f" - Library found (ID: {drive_id[:10]}...)") for folder in folders_to_download: - # Clean folder paths from config folder_parts = [sanitize_filename(p) for p in folder.split('/') if p] local_folder_path = os.path.normpath(os.path.join(local_path_base, *folder_parts)) - print(f"\nProcessing: {folder if folder else 'Root'}") - download_folder_recursive(app, drive_id, folder, local_folder_path, report) + print(f"\nStep 4: Processing folder: {folder if folder else 'Root'}") + download_folder_recursive(app, drive_id, folder, local_folder_path, report := []) except Exception as e: - print(f"Critical error: {e}") - report.append({"Path": "GENERAL", "Error": str(e), "Timestamp": datetime.now().isoformat()}) + print(f"\nCRITICAL ERROR: {e}") + report = [{"Path": "GENERAL", "Error": str(e), "Timestamp": datetime.now().isoformat()}] + print_progress(force=True) + report_file = f"download_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv" with open(report_file, 'w', newline='', encoding='utf-8') as f: writer = csv.DictWriter(f, fieldnames=["Path", "Error", "Timestamp"]) writer.writeheader() writer.writerows(report) - print(f"\nProcess complete. Errors: {len(report)}") + print(f"\n\nProcess complete.") + print(f"Summary: {stats['total_checked']} items checked.") + print(f" - {stats['downloaded']} new files downloaded.") + print(f" - {stats['skipped']} existing files skipped.") + print(f" - {stats['failed']} errors encountered (see {report_file}).") if __name__ == "__main__": main()