How to download a file from Sharepoint with python - python

I need to download a file from sharepoint using user credentials (rather that client credentials).
I've tried this:
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
from office365.sharepoint.files.file import File
root_url = "https://company-my.sharepoint.com"
full_url = "https://company-my.sharepoint.com/personal/Documents/AB.csv"
ctx = ClientContext(root_url)
ctx.with_user_credentials(<my_email>,
<my_password)
response = File.open_binary(ctx, full_url)
print(response.content)
The response I am getting is
*b'{"error":{"code":"-2147024809, System.ArgumentException","message":{"lang":"en-US","value":"serverRelativePath\\r\\nParameter
name: Specified value is not supported for the serverRelativePath
parameter."}}}'*

Related

Pandas: Problem while trying reading Excel File from a sharepoint site

I am trying to read an excel file from SharePoint to python and I get the following error:
ValueError: Excel file format cannot be determined, you must specify an engine manually.
The python script goes something like that:
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
from office365.sharepoint.files.file import File
import io
import pandas as pd
url = "https://company.sharepoint.com/:x:/r/sites/A_team/"
username = 'myemail#mail.com'
password = 'password'
relative_url = "sites/A_team/Documents_python/Folder/Book.xlsx"
ctx_auth = AuthenticationContext(url)
if ctx_auth.acquire_token_for_user(username, password):
ctx = ClientContext(url, ctx_auth)
web = ctx.web
ctx.load(web)
ctx.execute_query()
print("Authentication successful")
else:
print(ctx_auth.get_last_error())
response = File.open_binary(ctx, relative_url)
bytes_file_obj = io.BytesIO()
bytes_file_obj.write(response.content)
bytes_file_obj.seek(0) #set file object to start
pd.read_excel(bytes_file_obj)
Does anyone have an idea what should I do?
I tried to add an engine, but then I get the following error:
BadZipFile: File is not a zip file

How to Download a PDF File from Online SharePoint using python?

How to Download a PDF File from Online SharePoint using python?
I've tried this code: but whenever I try this it downloads a broken file
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
from office365.sharepoint.files.file import File
url = "SharePointFilePath"
username= "Username"
password= "Password"
ctx_auth = AuthenticationContext(url)
ctx_auth.acquire_token_for_user(username, password)
ctx = ClientContext(url, ctx_auth)
response = File.open_binary(ctx, "SharepointURL")
with open("file.pdf","wb") as local_file:
local_file.write(response.content)
You need to write, not to read:
with open("file.pdf","wb") as local_file:
local_file.write(response.content)
Use another flag 'wb' instead of 'rb' and write method instead of read
with open('file.pdf', 'wb') as f:
f.write(response.content)
Read about flags

File Download from Sharepoint using Python

I am trying to download an excel file from Sharepoint with the office365 module. Here's my code.
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
from office365.sharepoint.file import File
app_settings = {
'url': 'https://xxxxx/sites/DownloadFiles',
'client_id': 'xxxxxx',
'client_secret': 'xxxxxx',
}
if name == 'main':
ctx_auth = AuthenticationContext(url=app_settings['url'])
ctx_auth.acquire_token_for_app(client_id=app_settings['client_id'],
client_secret=app_settings['client_secret'])
ctx = ClientContext(app_settings['url'], ctx_auth)
path = "F:\myexcel.xlsx"
response = File.open_binary(ctx, "/Shared%20Documents/myexcel.xlsx")
response.raise_for_status()
with open(path, "wb") as local_file:
local_file.write(response.content)
When I run that code, I get the following error:
400 Client Error: Bad Request for url: https://xxx/DownloadFiles/_api/web/getfilebyserverrelativeurl('/Shared%20Documents/myexcel.xlsx')/%5C$value
I am able to reproduce the same issue on my SPO.
Please modify the code as below to fix it:
response = File.open_binary(ctx, "/sites/{abc}/Shared%20Documents/source.txt")
Such as i want to download file from a site collection like "https://xxxx.sharepoint.com/sites/abc", the serverrelativeurl is "/sites/abc"
You can get the serverrelativeurl via '_spPageContextInfo' object:
And there is another SharePoint library 'shareplum' that provided some easy ways to operate files, you may have a try.
Best Regards,
Baker Kong

Download a compressed zip file from URL

I have a problem statement where I have to login to a website and then download a zip file. I have written the below code so far to login to website(able to print authentication successful message) and create a session. How can I download the zip file now ?
import requests
import urllib
import urllib.request
import zipfile
import io
import shutil
post_login_url = 'https://www.ims-dm.com/mvc/page/customer-sign-in/cgi/cookie.php'
request_url = 'http://www.ims-dm.com/cgi/securedownload.php?p=WPNFTPD#prodtype=wpn/WPN-FULL-20180306.TXT.zip'
payload = {
'sendusername':'xxxxxxxxxx',
'password':'xxxxxx'
}
with requests.Session() as session:
post = session.post(post_login_url,data=payload)
if post.status_code == 200:
print("Authentication sucessful !!")
url = session.get(request_url)

Download xlsx with request w/pem cert

Im having abit of issue downloading an xlsx file over https.
Here my code to scrape the sight to get the download url, but its seems to redirect me to a new site. but when i put the link in my browswer, it downloads the file straight away.
Is there something im doing wrong?
here is the code i used for scraping the site:
import contextlib
import OpenSSL.crypto
import os
import requests
import ssl
import tempfile
import http.client
import shutil
from OpenSSL import crypto
import pem
import html2text
url = "https://signonssl.site.com"
base_url = "basedownloadurl"
p12_cert = "cert_path"
password = "password"
#contextlib.contextmanager
def pfx_to_pem(p12_path, pfx_password):
''' Decrypts the .p12 file to be used with requests. '''
with tempfile.NamedTemporaryFile(suffix='.pem') as t_pem:
f_pem = open(t_pem.name, 'wb')
pfx = open(p12_path, 'rb').read()
p12 = OpenSSL.crypto.load_pkcs12(pfx, pfx_password)
f_pem.write(OpenSSL.crypto.dump_privatekey(OpenSSL.crypto.FILETYPE_PEM, p12.get_privatekey()))
f_pem.write(OpenSSL.crypto.dump_certificate(OpenSSL.crypto.FILETYPE_PEM, p12.get_certificate()))
ca = p12.get_ca_certificates()
f_pem.close()
yield t_pem.name
with pfx_to_pem(p12_cert, password) as cert:
html_response = requests.get(url, cert=cert).content.decode("utf-8")
htmlconv = html2text.html2text(html_response).split("name")[1]
dl_link = htmlconv.split(")")[0].split("(")[1]
dl = requests.get(dl_link, cert=cert, stream=True, allow_redirects=False)
output = open('test.xlsx', 'wb')
output.write(dl.content)
output.close()
Any guidance is much appreciated.
Thanks!
Pon

Categories

Resources