A Pilgrim's Journal

Advogato also has XMLRPC, with which you can do programmatic access to your diary. I do this in the hope that it saves advogato bandwidth.

Below is a small python beginner script that I cooked up just for this task. It checks the dates of the posts and saves the new ones as individual files.

If someone finds it useful, please feel free to use it. You can download it here.

 #!/usr/bin/python

 import xmlrpclib
import os
import difflib

 def Download(filename, entry):
        print "Downloading: " + filename
        out = open(filename, "w")
        create, update = server.diary.getDates("cdfrey", entry)
        out.write("%s\n" % update)
        out.write(server.diary.get("cdfrey", entry))
        out.close()

 def GetTimestamp(filename):
        inf = open(filename, "r")
        s = inf.readline()
        inf.close()
        return s[0:len(s)-1]

 def Update(filename, entry):
        print "Updating: " + filename
        filetime = GetTimestamp(filename)
        webcreated, webupdated = server.diary.getDates("cdfrey", entry)
        if( filetime != webupdated ):
                print "Entry %d is out of date" % entry
                if os.access(filename + ".bak", 0):
                        os.unlink(filename + ".bak")
                os.rename(filename, filename + ".bak")
                Download(filename, entry)

                 oldf = open(filename + ".bak", "r")
                newf = open(filename, "r")
                oldl = oldf.readlines()
                newl = newf.readlines()
                print ''.join(difflib.unified_diff(oldl, newl))


 path = "/home/cdfrey/text/advogato/posts/"
server = xmlrpclib.Server("http://www.advogato.org/XMLRPC")

 entryCount = server.diary.len("cdfrey")

 for entry in range(entryCount):
        filename = path + "advogato.%03d" % entry
        if os.access(filename, 0):
                Update(filename, entry)
        else:
                Download(filename, entry)