python - 如何使用工作或学校帐户将 SharePoint Online (Office365) Excel 文件读入 Python，特别是 pandas？

Question

问题与下面的链接非常相​​似。 How to read SharePoint Online (Office365) Excel files in Python with Work or School Account?

基本上，我想将一个 excel 文件从 SharePoint 导入到 pandas 中以供进一步分析。

问题是当我运行下面的代码时出现以下错误。

XLRDError: Unsupported format, or corrupt file: Expected BOF record; found b'\r\n<!DOCT'

我的代码:

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

url = 'https://companyname.sharepoint.com/SitePages/Home.aspx'
username = 'fakeaccount@company.com'
password = 'password!'
relative_url = '/Shared%20Documents/Folder%20Number1/Folder%20Number2/Folder3/Folder%20Number%Four/Target_Excel_File_v4.xlsx?d=w8f97c2341898_random_numbers_and_letters_a065c12cbcsf=1&e=KXoU4s'


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()
  #this gives me a KeyError: 'Title'
  #print("Web title: {0}".format(web.properties['Title']))
  print('Authentication Successful')
else:
  print(ctx_auth.get_last_error())


import io
import pandas as pd

response = File.open_binary(ctx, relative_url)

#save data to BytesIO stream
bytes_file_obj = io.BytesIO()
bytes_file_obj.write(response.content)
bytes_file_obj.seek(0) #set file object to start

#read file into pandas dataframe
df = pd.read_excel(bytes_file_obj)

print(df)

Answer 1

对于那些在这个问题上像我一样结束的人，我发现必须将完整的 URL 指向 File，而不仅仅是路径:

#import all the libraries
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

#target url taken from sharepoint and credentials
url = 'https://company.sharepoint.com/Shared%20Documents/Folder%20Number1/Folder%20Number2/Folder3/Folder%20Number4/Target_Excel_File_v4.xlsx?cid=_Random_letters_and_numbers-21dbf74c'
username = 'Dumby_account@company.com'
password = 'Password!'

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")

response = File.open_binary(ctx, url)

#save data to BytesIO stream
bytes_file_obj = io.BytesIO()
bytes_file_obj.write(response.content)
bytes_file_obj.seek(0) #set file object to start

#read excel file and each sheet into pandas dataframe 
df = pd.read_excel(bytes_file_obj, sheetname = None)