mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 17:41:15 +00:00
59e850bbd9
### Description Update all other connectors to use the new downstream architecture that was recently introduced for the s3 connector. Closes #1313 and #1311
120 lines
4.4 KiB
ReStructuredText
120 lines
4.4 KiB
ReStructuredText
Sharepoint
|
|
==========
|
|
Connect Sharepoint to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
|
|
|
|
First you'll need to install the Sharepoint dependencies as shown here.
|
|
|
|
.. code:: shell
|
|
|
|
pip install "unstructured[sharepoint]"
|
|
|
|
Run Locally
|
|
-----------
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
unstructured-ingest \
|
|
sharepoint \
|
|
--client-id "<Microsoft Sharepoint app client-id>" \
|
|
--client-cred "<Microsoft Sharepoint app client-secret>" \
|
|
--site "<e.g https://contoso.sharepoint.com or https://contoso.admin.sharepoint.com to process all sites within tenant>" \
|
|
--files-only "Flag to process only files within the site(s)" \
|
|
--output-dir sharepoint-ingest-output \
|
|
--num-processes 2 \
|
|
--verbose
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import subprocess
|
|
|
|
command = [
|
|
"unstructured-ingest",
|
|
"sharepoint",
|
|
"--client-id", "<Microsoft Sharepoint app client-id>",
|
|
"--client-cred", "<Microsoft Sharepoint app client-secret>",
|
|
"--site", "<e.g https://contoso.sharepoint.com or https://contoso.admin.sharepoint.com to process all sites within tenant>",
|
|
"--files-only", "Flag to process only files within the site(s)",
|
|
"--output-dir", "sharepoint-ingest-output",
|
|
"--num-processes", "2",
|
|
"--verbose",
|
|
]
|
|
|
|
# Run the command
|
|
process = subprocess.Popen(command, stdout=subprocess.PIPE)
|
|
output, error = process.communicate()
|
|
|
|
# Print output
|
|
if process.returncode == 0:
|
|
print('Command executed successfully. Output:')
|
|
print(output.decode())
|
|
else:
|
|
print('Command failed. Error:')
|
|
print(error.decode())
|
|
|
|
Run via the API
|
|
---------------
|
|
|
|
You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``.
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
unstructured-ingest \
|
|
sharepoint \
|
|
--client-id "<Microsoft Sharepoint app client-id>" \
|
|
--client-cred "<Microsoft Sharepoint app client-secret>" \
|
|
--site "<e.g https://contoso.sharepoint.com or https://contoso.admin.sharepoint.com to process all sites within tenant>" \
|
|
--files-only "Flag to process only files within the site(s)" \
|
|
--output-dir sharepoint-ingest-output \
|
|
--num-processes 2 \
|
|
--verbose \
|
|
--partition-by-api \
|
|
--api-key "<UNSTRUCTURED-API-KEY>"
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import subprocess
|
|
|
|
command = [
|
|
"unstructured-ingest",
|
|
"sharepoint",
|
|
"--client-id", "<Microsoft Sharepoint app client-id>",
|
|
"--client-cred", "<Microsoft Sharepoint app client-secret>",
|
|
"--site", "<e.g https://contoso.sharepoint.com or https://contoso.admin.sharepoint.com to process all sites within tenant>",
|
|
"--files-only", "Flag to process only files within the site(s)",
|
|
"--output-dir", "sharepoint-ingest-output",
|
|
"--num-processes", "2",
|
|
"--verbose",
|
|
"--partition-by-api",
|
|
"--api-key", "<UNSTRUCTURED-API-KEY>",
|
|
]
|
|
|
|
# Run the command
|
|
process = subprocess.Popen(command, stdout=subprocess.PIPE)
|
|
output, error = process.communicate()
|
|
|
|
# Print output
|
|
if process.returncode == 0:
|
|
print('Command executed successfully. Output:')
|
|
print(output.decode())
|
|
else:
|
|
print('Command failed. Error:')
|
|
print(error.decode())
|
|
|
|
Additionally, you will need to pass the ``--partition-endpoint`` if you're running the API locally. You can find more information about the ``unstructured`` API `here <https://github.com/Unstructured-IO/unstructured-api>`_.
|
|
|
|
For a full list of the options the CLI accepts check ``unstructured-ingest sharepoint --help``.
|
|
|
|
NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
|