Retrieve all properties for a SharePoint document(type)

sps-grab-SPSPeople-info.py

import requests
import json


url = 'https://server/_api/search/postquery'

# X-RequestDigest required for Anti XSRF
headers = {
	'X-RequestDigest':'0x4CF763CCDD37BC34BCEBC236D8C3A14D2B0852792487F30E57C9C46F668D31D461ED7C61FBA3D52DA19ACC6F797EED95B243A414D7A1BA6C736BDBD50A0D0A83,09 Mar 2020 13:32:05 -0000',
	'Content-Type': 'application/json;odata=verbose',
	'Accept': 'application/json;odata=verbose',
}

# Arguments: SelectProperties result from get-properties.py
args = {
    "request":
    {
        "Querytext": "-ContentClass=urn:content-class:SPSPeople",

        "SelectProperties":
        {
	        "results":
	        [
	        	"Path", "Other"
			]
        },
        "RowLimit": 500,
        "RowsPerPage": 500,
        "StartRow": 0,
        "TrimDuplicates": True,
        "SourceId": "5dc9f503-801e-4ced-8a2c-5d1237132419"
    }
}

rowrequest = 0
totalrows = None # We don't know the total amount yet
r = requests.post(url, headers=headers, json=args)
while True:
	print('{0}/{1}'.format(rowrequest, totalrows))
	if r.status_code == 200:
		data = r.json()

		# How many rows do we need to retrieve
		totalrows = data['d']['postquery']['PrimaryQueryResult']['RelevantResults']['TotalRows']
		rowcount = data['d']['postquery']['PrimaryQueryResult']['RelevantResults']['RowCount']

		output = []
		# Convert weird Microsoft format to something normal/usable. Leave out empty properties.
		for item in data['d']['postquery']['PrimaryQueryResult']['RelevantResults']['Table']['Rows']['results']:
			d = {i['Key']:i['Value'] for i in item['Cells']['results'] if i['Value'] is not None and i['Value'] != ''}
			output.append(d)

		# Write the output (per-page) to the /tmp/ directory.
		json.dump(output, open('/tmp/SPSPeople-{0:08d}.json'.format(rowrequest), 'w'), indent=4)

		if (rowrequest + rowcount) >= totalrows:
			break
		else:
			rowrequest += rowcount
			break
		args['request']['StartRow'] = rowrequest
	r = requests.post(url, headers=headers, json=args)

sps-properties.py

# https://social.technet.microsoft.com/wiki/contents/articles/51949.sharepoint-2013-search-query-apis.aspx
# https://web.archive.org/web/20140205043809/http://blogs.technet.com/b/searchguys/archive/2013/12/11/how-to-all-managed-properties-of-a-document.aspx
import requests

url = "https://server/_api/search/query"

sourceids = '''
e7ec8cee-ded8-43c9-beb5-436b54b31e84
5dc9f503-801e-4ced-8a2c-5d1237132419
e1327b9c-2b8c-4b23-99c9-3730cb29c3f7
48fec42e-4a92-48ce-8363-c2703a40e67d
5c069288-1d17-454a-8ac6-9c642a065f48
b09a7990-05ea-4af9-81ef-edfab16c4e31
203fba36-2763-4060-9931-911ac8c0583b
8413cd39-2156-4e00-b54d-11efd9abdb89
78b793ce-7956-4669-aa3b-451fc5defebf
5e34578e-4d08-4edc-8bf3-002acf3cdbcc
38403c8c-3975-41a8-826e-717f2d41568a
97c71db1-58ce-4891-8b64-585bc2326c12
ba63bbae-fa9c-42c0-b027-9a878f16557c
ec675252-14fa-4fbe-84dd-8d098ed74181
9479bf85-e257-4318-b5a8-81a180f5faa1
'''
sourceids = sourceids.strip().split('\n')

contentclasses = '''
urn:content-class:SPSSearchQuery
urn:content-class:SPSListing:News
urn:content-class:SPSPeople
urn:content-classes:SPSCategory
urn:content-classes:SPSListing
urn:content-classes:SPSPersonListing
urn:content-classes:SPSTextListing
urn:content-classes:SPSSiteListing
urn:content-classes:SPSSiteRegistry
'''

contentclasses = contentclasses.strip().split('\n')

params = {
	"Querytext" : "'ContentClass=urn:content-class:SPSPeople'",
	"SelectProperties" : "'Path'",
	"SourceId" : "'5dc9f503-801e-4ced-8a2c-5d1237132419'",
	"refiners" : "'managedproperties(filter=5000/0/*)'",
}

headers = {'Accept': 'application/json'}


contentproperties = {}
for contentclass in contentclasses:
	params['Querytext'] = "'ContentClass={0}'".format(contentclass)
	properties = []
	for sourceid in sourceids:
		r = requests.get(url, params=params, headers=headers)
		data = r.json()
		params['SourceId'] = "'{0}'".format(sourceid)

		if 'PrimaryQueryResult' in data and data['PrimaryQueryResult']['RefinementResults']:
			refinements = data['PrimaryQueryResult']['RefinementResults']['Refiners'][0]['Entries']
			for refinement in refinements:
				properties.append(refinement['RefinementName'])
	if len(properties) > 0:
		contentproperties[contentclass] = set(properties)