0

I want to exctract data from Sharepoint using Python 2.7.3. Here is my code:

import requests
import urlparse
import json
from requests_ntlm import HttpNtlmAuth
user_credentials = {
    'username' : 'my_username',
    'password' : 'my_password',
    'domain' : 'my_domain'
}
# Creating a class for Authentication
class UserAuthentication:
    def __init__(self, username, password, domain, site_url):
        self.__username = username
        self.__password = password
        self.__domain = domain
        self.__site_url = site_url
        self.__ntlm_auth = None

    def authenticate(self):
        login_user = self.__domain + "\\" + self.__username  
        user_auth = HttpNtlmAuth(login_user, self.__password)
        self.__ntlm_auth = user_auth
        # Create header for the http request
        my_headers = {
            'accept' : 'application/json;odata=verbose',
             'content-type' : 'application/json;odata=verbose',
             'odata' : 'verbose',
             'X-RequestForceAuthentication' : 'true'
        }
        # Sending http get request to the sharepoint site
        result = requests.get(self.__site_url, auth=user_auth, headers=my_headers, verify=False)
        # Requests ignore verifying the SSL certificates if you set verify to False
        # Checking the status code of the requests
        if result.status_code == requests.codes.ok:  # Value of requests.codes.ok is 200
            return True
        else:
             result.raise_for_status()
    def sharepoint_get_request(self, endpoint_uri):
        headers = {
            'accept' : 'application/json;odata=verbose',
            'content-type' : 'application/json;odata=verbose',
            'odata' : 'verbose',
            'X-RequestForceAuthentication' : 'true'
        }
        url = urlparse.urljoin(self.__site_url, endpoint_uri)
        result = requests.get(url, auth=self.__ntlm_auth, headers=headers, 
        verify=False)
        return result

if __name__ == "__main__":
    username = user_credentials['username']
    password = user_credentials['password']
    domain = user_credentials['domain']
    site_url = "https://sharepoint.com/sites/my_sharepoint"
    auth_object = UserAuthentication(username, password, domain, site_url)
    result = auth_object.authenticate()
    if result:
        print("Successfully login to sharepoint site")    
    # Want information about a specific list
    listname = "my_list"
    endpoint_uri = "_api/web/lists/getbytitle('" + listname + "')"
    result = auth_object.sharepoint_get_request(endpoint_uri)
    print result.status_code #200
    list_info = result.json()   # ValueError: No JSON object could be decoded
    result = auth_object.sharepoint_get_request(endpoint_uri)
    for element in result.json()['d']['results']:
        print("{}".format(element['Title']))

I can successfully login to sharepoint site, the status code of "sharepoint_get_request" result is 200, but the problem is that result.json() gives me the error: ValueError: No JSON object could be decoded.

How is it possible that a 200 status code result has no valid json object? Could it be a HTML page? In this case how can I parse HTML page in Python 2.7.3?

Thank you in advance

ale.C
  • 1
  • 1
  • 4

1 Answers1

0

Solved using the following python library: Office365-REST-Python-Client-master

https://github.com/vgrem/Office365-REST-Python-Client

To connect to Sharepoint I use the following code:

from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext

parse_obj = urlparse.urlparse(url)
path = parse_obj.path
ctx_auth = AuthenticationContext(url=url)
result = ctx_auth.acquire_token_for_user(username = username, 
                                   password = password)
ctx = ClientContext(url, ctx_auth)
if (ctx_auth.provider.FedAuth == None or 
    ctx_auth.provider.rtFa == None):
        print "Cookies generation fails. Check username and password"

To access to Sharepoint folders:

folders = ctx.web.folders        
ctx.load(folders)
ctx.execute_query()

Or to a specific folder and files:

folder = ctx.web.get_folder_by_server_relative_url(url)
ctx.load(folder)
ctx.execute_query()

files = folder.files
ctx.load(files)
ctx.execute_query()
for cur_file in files:
    file_name = cur_file.properties["Name"]
ale.C
  • 1
  • 1
  • 4