(Ruby) 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 Ruby Downloads

install from rubygems.org
gem install chilkat
or download... Ruby Library for Windows, MacOS, Linux, Alpine Linux

require 'chilkat'

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

http = Chilkat::CkHttp.new()

# 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.new()
success = http.QuickGetSb("https://graph.microsoft.com/v1.0/me/onenote/pages/{$page_id}/content?includeIDs=true",sbResponseBody)
if (success == false)
    print http.lastErrorText() + "\n";
    exit
end

print "HTML content:" + "\n";
print sbResponseBody.getAsString() + "\n";

respStatusCode = http.get_LastStatus()
print "Response Status Code = " + respStatusCode.to_s() + "\n";
if (respStatusCode >= 400)
    print "Response Header:" + "\n";
    print http.lastHeader() + "\n";
    print "Failed." + "\n";
    exit
end

# 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.new()
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.new()

bd = Chilkat::CkBinData.new()
while xml.NextInTraversal2(sbState) != false

    if (xml.TagEquals("img") == true)
        print "img id: " + xml.getAttrValue("id") + "\n";
        url = xml.getAttrValue("src")
        bd.Clear()
        success = http.QuickGetBd(url,bd)
        if (success == false)
            print http.lastErrorText() + "\n";
            exit
        end

        print "Downloaded from " + url + "\n";
        print "----" + "\n";
        # If desired, bd.WriteFile to save the contents of bd to a file..
    end

    if (xml.TagEquals("object") == true)
        print "data-attachment: " + xml.getAttrValue("data-attachment") + "\n";
        print "type: " + xml.getAttrValue("type") + "\n";
        url = xml.getAttrValue("data")
        bd.Clear()
        success = http.QuickGetBd(url,bd)
        if (success == false)
            print http.lastErrorText() + "\n";
            exit
        end

        print "Downloaded from " + url + "\n";
        print "----" + "\n";
        # If desired, bd.WriteFile to save the contents of bd to a file..
    end

end

print "Success." + "\n";