mirror of
https://github.com/Hestia-Homes/survey-extraction.git
synced 2026-06-08 11:17:29 +00:00
40 lines
No EOL
1.2 KiB
Python
40 lines
No EOL
1.2 KiB
Python
from urllib.parse import unquote
|
|
|
|
class SharePointURLError(ValueError):
|
|
"""Custom error for SharePoint URL parsing issues."""
|
|
pass
|
|
|
|
|
|
def get_sharepoint_path(url):
|
|
try:
|
|
url_parts = url.split('/')
|
|
|
|
# Find the index of 'Forms'
|
|
forms_index = url_parts.index('Forms')
|
|
|
|
# Get the part after 'Forms'
|
|
after_forms = url_parts[forms_index + 1]
|
|
|
|
# Find 'id=' and extract after it
|
|
if 'id=' in after_forms:
|
|
id_part = after_forms.split('id=')[1]
|
|
|
|
# Only keep the path before '&' (to ignore other parameters)
|
|
id_path = id_part.split('&')[0]
|
|
|
|
# Decode the path
|
|
decoded_path = unquote(id_path)
|
|
|
|
# Remove the leading '/sites/xxx/Shared Documents/' part
|
|
parts = decoded_path.split('Shared Documents')
|
|
|
|
if len(parts) > 1:
|
|
final_path = parts[1].strip('/')
|
|
return final_path
|
|
else:
|
|
return decoded_path.strip('/')
|
|
else:
|
|
raise SharePointURLError(f"The URL does not contain 'id=' parameter. URL: {url}")
|
|
|
|
except (IndexError, ValueError) as e:
|
|
raise SharePointURLError(f"Error with SharePoint URL, please check {url}. Reason: {e}") |