(CkPython) OneNote - Get Page HTML Content

Download the HTML content of a OneNote page. Also iterates over the images and attachments on the OneNote page and downloads the content for each.

For more information, see https://docs.microsoft.com/en-us/graph/api/page-get?view=graph-rest-1.0

Chilkat Python Downloads

install with pip
pip3 install chilkat
or download... Python Module for Windows, MacOS, Linux, Alpine Linux, Solaris

import sys
import chilkat

# This example assumes the Chilkat API to have been previously unlocked.
# See Global Unlock Sample for sample code.

http = chilkat.CkHttp()

# Implements the following CURL command:

# curl -X GET https://graph.microsoft.com/v1.0/me/onenote/pages/{id}/content?includeIDs=true \
#   -H 'authorization: Bearer ACCESS_TOKEN'

# Use the following online tool to generate HTTP code from a CURL command
# Convert a cURL Command to HTTP Source Code

# Adds the "Authorization: Bearer ACCESS_TOKEN" header.
http.put_AuthToken("ACCESS_TOKEN")

http.SetUrlVar("page_id","0-d2298668edd74dccac7f821fa378bf64!41-3A33FCEB9B74CC15!20350")

sbResponseBody = chilkat.CkStringBuilder()
success = http.QuickGetSb("https://graph.microsoft.com/v1.0/me/onenote/pages/{$page_id}/content?includeIDs=true",sbResponseBody)
if (success == False):
    print(http.lastErrorText())
    sys.exit()

print("HTML content:")
print(sbResponseBody.getAsString())

respStatusCode = http.get_LastStatus()
print("Response Status Code = " + str(respStatusCode))
if (respStatusCode >= 400):
    print("Response Header:")
    print(http.lastHeader())
    print("Failed.")
    sys.exit()

# Let's get the images and attached files.
# Here's sample HTML content with 2 images and one PDF attachment:

# <html lang="en-US">
# 	<head>
# 		<title>A page with rendered images and an attached file</title>
# 		<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
# 		<meta name="created" content="2020-10-23T12:00:00.0000000" />
# 	</head>
# 	<body data-absolute-enabled="true" style="font-family:Calibri;font-size:11pt">
# 		<div id="div:{b130eb6c-638a-4f97-8f7e-b6d9e2e88bf9}{32}" data-id="_default" style="position:absolute;left:48px;top:120px;width:624px">
# 			<p id="p:{b130eb6c-638a-4f97-8f7e-b6d9e2e88bf9}{39}" style="margin-top:5.5pt;margin-bottom:5.5pt">Here&#39;s an image from an online source:</p>
# 			<img id="img:{ee18fe8d-b219-4baf-9b4d-4fc680579f0d}{1}" alt="an image on the page" width="500" height="500" src="https://graph.microsoft.com/v1.0/users('admin@chilkat.io')/onenote/resources/0-e71b45b763484921b4200e32c2439a47!1-3A33FCEB9B74CC15!20350/$value" data-src-type="image/jpeg" data-fullres-src="https://graph.microsoft.com/v1.0/users('admin@chilkat.io')/onenote/resources/0-e71b45b763484921b4200e32c2439a47!1-3A33FCEB9B74CC15!20350/$value" data-fullres-src-type="image/jpeg" />
# 			<p id="p:{b130eb6c-638a-4f97-8f7e-b6d9e2e88bf9}{43}" style="margin-top:5.5pt;margin-bottom:5.5pt">Here&#39;s an image uploaded as binary data:</p>
# 			<img id="img:{ee18fe8d-b219-4baf-9b4d-4fc680579f0d}{3}" alt="an image on the page" width="300" height="225" src="https://graph.microsoft.com/v1.0/users('admin@chilkat.io')/onenote/resources/0-a60516b962b842f2ae9bec75c16b31de!1-3A33FCEB9B74CC15!20350/$value" data-src-type="image/jpeg" data-fullres-src="https://graph.microsoft.com/v1.0/users('admin@chilkat.io')/onenote/resources/0-a60516b962b842f2ae9bec75c16b31de!1-3A33FCEB9B74CC15!20350/$value" data-fullres-src-type="image/jpeg" />
# 			<p id="p:{b130eb6c-638a-4f97-8f7e-b6d9e2e88bf9}{47}" style="margin-top:5.5pt;margin-bottom:5.5pt">Here&#39;s a file attachment:</p>
# 			<object data-attachment="FileName.pdf" type="application/pdf" data="https://graph.microsoft.com/v1.0/users('admin@chilkat.io')/onenote/resources/0-9e685efb33a24a6a8de1b9c707d28385!1-3A33FCEB9B74CC15!20350/$value" />
# 		</div>
# 	</body>
# </html>

xml = chilkat.CkXml()
xml.LoadSb(sbResponseBody,True)

# Iterate over each element in the XML.  Each time we find an "img" or "object", download the data.
# (The sbState is an object used to keep track of the current state of the traversal.)
sbState = chilkat.CkStringBuilder()

bd = chilkat.CkBinData()
while xml.NextInTraversal2(sbState) != False :

    if (xml.TagEquals("img") == True):
        print("img id: " + xml.getAttrValue("id"))
        url = xml.getAttrValue("src")
        bd.Clear()
        success = http.QuickGetBd(url,bd)
        if (success == False):
            print(http.lastErrorText())
            sys.exit()

        print("Downloaded from " + url)
        print("----")
        # If desired, bd.WriteFile to save the contents of bd to a file..

    if (xml.TagEquals("object") == True):
        print("data-attachment: " + xml.getAttrValue("data-attachment"))
        print("type: " + xml.getAttrValue("type"))
        url = xml.getAttrValue("data")
        bd.Clear()
        success = http.QuickGetBd(url,bd)
        if (success == False):
            print(http.lastErrorText())
            sys.exit()

        print("Downloaded from " + url)
        print("----")
        # If desired, bd.WriteFile to save the contents of bd to a file..

print("Success.")