azuresharepointmicrosoft-graph-apisharepoint-onlineazure-ad-graph-api
how to get files of a specific folder path in sharepoint using /lists graphapi
i was able to get folders of a specific folder path using /drives but in /lists it will return files also not just folders unlike /drives , i already made a python script to retrieve files from documents in sharepoint , but now i need to get files of a specific folder not the whole documents folders
here is the graph api url to retrieve folders from a specific path
here is my python script to get files and folders using /lists
async def fetch_file_details(session, url, headers):
async with session.get(url, headers=headers) as response:
print(f"headers {response.headers} ")
return await response.json()
async def get_all_images_in_library(accessToken, siteId, libraryId, batch_size=15):
url = f"https://graph.microsoft.com/v1.0/sites/{siteId}/lists/{libraryId}/items?top={batch_size}"
headers = {
'Authorization': f'Bearer {accessToken}',
'Accept': 'application/json',
'Prefer': 'HonorNonIndexedQueriesWarningMayFailRandomly'
}
async with aiohttp.ClientSession() as session:
while url:
async with session.get(url, headers=headers) as response:
if response.status != 200:
print(f"Failed to fetch: {response.status}")
retry_after = response.headers.get('Retry-After')
throttle_limit_percentage = response.headers.get('x-ms-throttle-limit-percentage')
throttle_scope = response.headers.get('x-ms-throttle-scope')
throttle_reason = response.headers.get('x-ms-throttle-reason')
print(f"headers {response.headers} ")
if retry_after:
print(f"Retry-After: {retry_after} seconds")
if throttle_limit_percentage:
print(f"Throttle Limit Percentage: {throttle_limit_percentage}%")
if throttle_scope:
print(f"Throttle Scope: {throttle_scope}")
if throttle_reason:
print(f"Throttle Reason: {throttle_reason}")
break
data = await response.json()
items = data.get('value', [])
if not items:
break
tasks = []
for item in items:
webUrl = item.get('webUrl', '')
if webUrl.lower().endswith(('.jpg', '.jpeg', '.png', '.gif')):
fileDetailsUrl = f"https://graph.microsoft.com/v1.0/sites/{siteId}/lists/{libraryId}/items/{item['id']}?expand=fields"
task = fetch_file_details(session, fileDetailsUrl, headers)
tasks.append(task)
if tasks:
batch_results = await asyncio.gather(*tasks)
yield batch_results
await asyncio.sleep(0.1)
url = data.get('@odata.nextLink')
my question is how can i get files and folders from a specific path using /lists ?
Solution
For sample, I have a folder structure like below and uploaded few images in animals folder:
To get the files of a specific folder path in SharePoint using /lists, modify the code like below:
import aiohttp
import asyncio
# Fetch file details helper function
async def fetch_file_details(session, url, headers):
async with session.get(url, headers=headers) as response:
if response.status == 200:
return await response.json()
else:
print(f"Failed to fetch details for URL: {url}, Status: {response.status}")
return None
# Function to get all items in the document library (no folder filter)
async def get_all_items_in_library(accessToken, siteId, libraryId, batch_size=15):
# URL without folder filter
url = f"https://graph.microsoft.com/v1.0/sites/{siteId}/lists/{libraryId}/items?top={batch_size}"
headers = {
'Authorization': f'Bearer {accessToken}',
'Accept': 'application/json',
'Prefer': 'HonorNonIndexedQueriesWarningMayFailRandomly'
}
async with aiohttp.ClientSession() as session:
while url:
async with session.get(url, headers=headers) as response:
if response.status != 200:
print(f"Failed to fetch: {response.status}")
retry_after = response.headers.get('Retry-After')
throttle_limit_percentage = response.headers.get('x-ms-throttle-limit-percentage')
throttle_scope = response.headers.get('x-ms-throttle-scope')
throttle_reason = response.headers.get('x-ms-throttle-reason')
print(f"headers {response.headers}")
if retry_after:
print(f"Retry-After: {retry_after} seconds")
if throttle_limit_percentage:
print(f"Throttle Limit Percentage: {throttle_limit_percentage}%")
if throttle_scope:
print(f"Throttle Scope: {throttle_scope}")
if throttle_reason:
print(f"Throttle Reason: {throttle_reason}")
break
data = await response.json()
items = data.get('value', [])
if not items:
break
tasks = []
for item in items:
webUrl = item.get('webUrl', '')
# If the file is an image (jpg, png, etc.), fetch its details
if webUrl.lower().endswith(('.jpg', '.jpeg', '.png', '.gif')):
fileDetailsUrl = f"https://graph.microsoft.com/v1.0/sites/{siteId}/lists/{libraryId}/items/{item['id']}?expand=fields"
task = fetch_file_details(session, fileDetailsUrl, headers)
tasks.append(task)
# Process the batch of file details
if tasks:
batch_results = await asyncio.gather(*tasks)
yield batch_results
# Move to the next page if there is one
url = data.get('@odata.nextLink')
# Throttling, wait a bit before the next request
await asyncio.sleep(0.1)
# Function to format and display the file details
def format_and_display_file_details(files):
for file in files:
if file:
web_url = file.get('webUrl', 'No URL')
# Check if the webUrl matches the desired pattern
if web_url.startswith("https://YourDomain.sharepoint.com/sites/RukSite/Shared%20Documents/General/index/images/animals/"):
file_name = file.get('fields', {}).get('FileLeafRef', 'Unknown')
file_size = file.get('fields', {}).get('FileSizeDisplay', 'Unknown size')
created_by = file.get('createdBy', {}).get('user', {}).get('displayName', 'Unknown')
created_date = file.get('createdDateTime', 'Unknown')
modified_by = file.get('lastModifiedBy', {}).get('user', {}).get('displayName', 'Unknown')
modified_date = file.get('lastModifiedDateTime', 'Unknown')
print(f"\nFile: {file_name}")
print("-" * 25)
print(f"- **Web URL**: {web_url}")
print(f"- **File Size**: {file_size} bytes")
print(f"- **Created By**: {created_by}")
print(f"- **Created Date**: {created_date}")
print(f"- **Last Modified By**: {modified_by}")
print(f"- **Last Modified Date**: {modified_date}")
print("-" * 25)
# Example usage
async def main():
access_token = 'YourAccessToken' # Your access token here
site_id = 'SiteID' # Your site ID
library_id = 'ListID' # Your document library list ID
# Fetch and process images in the library (no folder filter)
async for batch in get_all_items_in_library(access_token, site_id, library_id):
format_and_display_file_details(batch)
# Run the script
asyncio.run(main())
I got the files successfully in animals folder:
