on 06-21-2015 7:33 PM
Hi,
can anyone help me with this issue? I am unable to download SAP Notes from python with my SCN Id.
I tried several ways to do this, for example:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests
from requests.auth import HTTPBasicAuth
asapnote = "http://service.sap.com/sap/support/notes/1775242"
username = "S00XXXXXX"
password = "XXXXXXXXX"
r = requests.get(asapnote, auth=HTTPBasicAuth(username, password), allow_redirects=True)
print ("RC: %d" % r.status_code)
print (r.headers['content-type'])
print (r.encoding)
print (r.encoding)
print (r.text)
But I always get the following:
RC: 401
text/html
ISO-8859-1
I am interested in extract 'Symptom' and 'Other tems' sections and build my own database of terms to search quickly.
Is this possible?
Thanks in advance
Thanks to this recipe [1] I've been able to download SAP Notes from SAP.
The code:
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
# File: sapnote.py
import urllib2
import sys
import re
import base64
from urlparse import urlparse
asapnote = "http://service.sap.com/sap/support/notes/1775242"
username = "S00XXXXXXXX"
password = "XXXXXXXXXXX"
req = urllib2.Request(asapnote)
try:
handle = urllib2.urlopen(req)
except IOError, e:
pass # here we *want* to fail
else:
# If we don't fail then the page isn't protected
print "This page isn't protected by authentication."
sys.exit(1)
if not hasattr(e, 'code') or e.code != 401:
# we got an error - but not a 401 error
print "This page isn't protected by authentication."
print 'But we failed for another reason.'
sys.exit(1)
authline = e.headers['www-authenticate']
# this gets the www-authenticate line from the headers
# which has the authentication scheme and realm in it
authobj = re.compile(r'''(?:\s*www-authenticate\s*:)?\s*(\w*)\s+realm=['"]([^'"]+)['"]''', re.IGNORECASE)
# this regular expression is used to extract scheme and realm
matchobj = authobj.match(authline)
if not matchobj:
# if the authline isn't matched by the regular expression
# then something is wrong
print 'The authentication header is badly formed.'
print authline
sys.exit(1)
scheme = matchobj.group(1)
realm = matchobj.group(2)
# here we've extracted the scheme
# and the realm from the header
if scheme.lower() != 'basic':
print 'This example only works with BASIC authentication.'
sys.exit(1)
base64string = base64.encodestring('%s:%s' % (username, password))[:-1]
authheader = "Basic %s" % base64string
req.add_header("Authorization", authheader)
try:
handle = urllib2.urlopen(req)
except IOError, e:
# here we shouldn't fail if the username/password is right
print "It looks like the username or password is wrong."
sys.exit(1)
sapnote = handle.read()
print sapnote
But the html source code is awful:
<html>
<head>
<title>1775242 - SAP Solution Manager 7.1 SP8 - Basic functions</title>
<link rel="Shortcut Icon" type="image/x-icon" href="http://www.sap.com/SAPFavicon.ico" />
<link rel="icon" type="image/ico" href="http://www.sap.com/SAPFavicon.ico">
<script language="JavaScript">
var frame_A="25D24E0DFABDFD4996AB0A2039A0D59D_A";
function startBSPApplication(name)
{
doc=window.frames[name].document;
doc.writeln('<html><body onload="document.f.submit();">');
doc.writeln('<form id="f" name="f" target="25D24E0DFABDFD4996AB0A2039A0D59D_A" method="POST" action="/sap/bc/bsp/sno/ui/main.do?param=69765F6D6F64653D3030312669765F7361706E6F7465735F6E756D6265723D3137373532343226">');
doc.writeln('<input type="hidden" name="param" value="69765F6D6F64653D3030312669765F7361706E6F7465735F6E756D6265723D3137373532343226">');
doc.writeln('<input type="hidden" name="bspapplicationffields" value="cGFyYW09Njk3NjVGNkQ2RjY0NjUzRDMwMzAzMTI2Njk3NjVGNzM2MTcwNkU2Rjc0NjU3MzVGNkU3NTZENjI2NTcyM0QzMTM3MzczNTMyMzQzMjI2">');
doc.writeln('<table border="0" width="100%" height="100%"><tr><td align="CENTER" valign="MIDDLE"><span style="font-family:Arial,sans-serif;">Loading...</span></td></tr></table>');
doc.writeln('</form></body></html>');
doc.close();
}
function exitBSPApplication()
{
var myDoc;
var el;
var sid;
var name;
var app;
var ns;
try
{
myDoc = window.frames[frame_A].document;
el = myDoc.forms[0].sid;
sid = el.value;
el = myDoc.forms[0].cookie_name;
name = el.value;
el = myDoc.forms[0].appl_name;
app = el.value;
el = myDoc.forms[0].appl_ns;
ns = el.value;
}
catch(err)
{}
var url="/sap/bc/bsp/sno/ui_entry/sessionexit.htm?application_list[1].exit_url=/sap(bD1lbiZjPTAwMQ==)/bc/bsp/sno/ui_entry/entry.htm%3Fsap-sessioncmd=logoff";
url+="&sid=" + sid;
url+="&name=" + name;
url+="&app=" + app;
url+="&ns=" + ns;
var win_prop = "";
try
{
//win_prop = "height=100,width=400,top="+(screen.height-100)/2+",left="+(screen.width-400)/2;
}
catch(err)
{
win_prop = "height=100,width=400";
}
win_prop = "height=100,width=400";
var out = window.open(url,'_blank',win_prop);
document.getElementById("25D24E0DFABDFD4996AB0A2039A0D59D_FRAMESET").onunload = null;
}
</script>
</head>
<frameset id="25D24E0DFABDFD4996AB0A2039A0D59D_FRAMESET" rows="*,0" onload="startBSPApplication('25D24E0DFABDFD4996AB0A2039A0D59D_A');" onunload="exitBSPApplication();" FRAMEBORDER=0 FRAMESPACING=0 BORDER=0>
<frame name="25D24E0DFABDFD4996AB0A2039A0D59D_A" src="entry_default_content.htm" NORESIZE SCROLLING=AUTO MARGINHEIGHT=0 MARGINWIDTH=0>
<noframes>This browser does not support frames.</noframes>
</frameset>
</html>
I do not understand why SAP has to obfuscate the code in this way. Why not serve only html without frames neither server side scripting? What do they have to hide?
So, I am done.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
To those interested in this topic, I've started to develop an application which help the SAP Consultants to manage their SAP Notes and share them.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.