martin/Sharepoint-Download-Tool
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tilføj 429-håndtering, eksponentiel backoff og dybdebegrænsning

Browse Source 
- get_fresh_download_url: tilføjer 429-tjek med Retry-After og erstatter
  fast sleep(1) med eksponentiel backoff (2^attempt sekunder)
- process_item_list: tilføjer MAX_FOLDER_DEPTH=50 guard mod RecursionError
  ved unormalt dybe SharePoint-mappestrukturer
- README og CLAUDE.md opdateret med beskrivelse af nye adfærd

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Martin Tranberg
2026-03-27 15:16:12 +01:00
parent 3bb2b44477
commit 634b5ff151
3 changed files with 25 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
download_sharepoint.py
View File

@@ -15,6 +15,7 @@ from urllib.parse import urlparse, quote
MAX_WORKERS = 5
MAX_RETRIES = 5
CHUNK_SIZE = 1024 * 1024 # 1MB Chunks
MAX_FOLDER_DEPTH = 50
LOG_FILE = "sharepoint_download.log"
# Setup Logging
@@ -145,28 +146,34 @@ def get_fresh_download_url(app, drive_id, item_id):
try:
headers = get_headers(app)
response = requests.get(url, headers=headers, timeout=60)
if response.status_code == 429:
retry_after = int(response.headers.get("Retry-After", 2 ** attempt))
logger.warning(f"Throttled (429) in get_fresh_download_url. Waiting {retry_after}s...")
time.sleep(retry_after)
continue
if response.status_code == 401:
logger.info(f"Access Token expired during refresh (Attempt {attempt+1}). Forcing refresh...")
headers = get_headers(app, force_refresh=True)
response = requests.get(url, headers=headers, timeout=60)
response.raise_for_status()
data = response.json()
download_url = data.get('@microsoft.graph.downloadUrl')
if download_url:
return download_url, None
# If item exists but URL is missing, it might be a transient SharePoint issue
logger.warning(f"Attempt {attempt+1}: '@microsoft.graph.downloadUrl' missing for {item_id}. Retrying in 1s...")
time.sleep(1)
logger.warning(f"Attempt {attempt+1}: '@microsoft.graph.downloadUrl' missing for {item_id}. Retrying in {2 ** attempt}s...")
time.sleep(2 ** attempt)
except Exception as e:
if attempt == 2:
return None, str(e)
logger.warning(f"Attempt {attempt+1} failed: {e}. Retrying...")
time.sleep(1)
logger.warning(f"Attempt {attempt+1} failed: {e}. Retrying in {2 ** attempt}s...")
time.sleep(2 ** attempt)
return None, "Item returned but '@microsoft.graph.downloadUrl' was missing after 3 attempts."
@@ -236,7 +243,10 @@ def download_single_file(app, drive_id, item_id, local_path, expected_size, disp
return False, str(e)
# --- Main Traversal Logic ---
def process_item_list(app, drive_id, item_path, local_root_path, report, executor, futures):
def process_item_list(app, drive_id, item_path, local_root_path, report, executor, futures, depth=0):
if depth >= MAX_FOLDER_DEPTH:
logger.warning(f"Max folder depth ({MAX_FOLDER_DEPTH}) reached at: {item_path}. Skipping subtree.")
return
try:
auth_headers = get_headers(app)
encoded_path = quote(item_path)
@@ -257,7 +267,7 @@ def process_item_list(app, drive_id, item_path, local_root_path, report, executo
display_path = f"{item_path}/{item_name}".strip('/')
if 'folder' in item:
process_item_list(app, drive_id, display_path, local_path, report, executor, futures)
process_item_list(app, drive_id, display_path, local_path, report, executor, futures, depth + 1)
elif 'file' in item:
item_id = item['id']
download_url = item.get('@microsoft.graph.downloadUrl')