initial commit

[oss/ljdump.git] / ljdump.py

diff --git a/ljdump.py b/ljdump.py
index 65903fda98df8427d0bafee6941339407edf4e7e..318b459978f923ee5a7fee33c2e0ff71fecafc12 100755 (executable)
--- a/ljdump.py
+++ b/ljdump.py
@@ -1,3 +1,51 @@
+#!/usr/bin/python
+#
+# ljdump.py - livejournal archiver
+# Greg Hewgill <greg@hewgill.com> http://hewgill.com
+# Version 1.0.3
+#
+# $Id$
+#
+# This program reads the journal entries from a livejournal (or compatible)
+# blog site and archives them in a subdirectory named after the journal name.
+#
+# The configuration is read from "ljdump.config". A sample configuration is
+# provided in "ljdump.config.sample", which should be copied and then edited.
+# The configuration settings are:
+#
+#   server - The XMLRPC server URL. This should only need to be changed
+#            if you are dumping a journal that is livejournal-compatible
+#            but is not livejournal itself.
+#
+#   username - The livejournal user name. A subdirectory will be created
+#              with this same name to store the journal entries.
+#
+#   password - The account password. This password is never sent in the
+#              clear; the livejournal "challenge" password mechanism is used.
+#
+# This program may be run as often as needed to bring the backup copy up
+# to date. Both new and updated items are downloaded.
+#
+# LICENSE
+#
+# This software is provided 'as-is', without any express or implied
+# warranty.  In no event will the author be held liable for any damages
+# arising from the use of this software.
+#
+# Permission is granted to anyone to use this software for any purpose,
+# including commercial applications, and to alter it and redistribute it
+# freely, subject to the following restrictions:
+#
+# 1. The origin of this software must not be misrepresented; you must not
+#    claim that you wrote the original software. If you use this software
+#    in a product, an acknowledgment in the product documentation would be
+#    appreciated but is not required.
+# 2. Altered source versions must be plainly marked as such, and must not be
+#    misrepresented as being the original software.
+# 3. This notice may not be removed or altered from any source distribution.
+#
+# Copyright (c) 2005 Greg Hewgill
+
 import codecs, md5, os, pprint, sys, xml.dom.minidom, xmlrpclib
 from xml.sax import saxutils
 
@@ -20,18 +68,40 @@ def dumpelement(f, name, e):
             f.write("<%s>%s</%s>\n" % (k, saxutils.escape(s), k))
     f.write("</%s>\n" % name)
 
-def writedump(itemid, event):
-    f = codecs.open("archive/"+itemid, "w", "UTF-8")
+def writedump(fn, event):
+    f = codecs.open(fn, "w", "UTF-8")
     f.write("""<?xml version="1.0"?>\n""")
     dumpelement(f, "event", event)
     f.close()
 
 config = xml.dom.minidom.parse("ljdump.config")
+Server = config.documentElement.getElementsByTagName("server")[0].childNodes[0].data
 Username = config.documentElement.getElementsByTagName("username")[0].childNodes[0].data
 Password = config.documentElement.getElementsByTagName("password")[0].childNodes[0].data
 
-server = xmlrpclib.ServerProxy("http://livejournal.com/interface/xmlrpc")
+print "Fetching journal entries for: %s" % Username
+try:
+    os.mkdir(Username)
+    print "Created subdirectory: %s" % Username
+except:
+    pass
+
+server = xmlrpclib.ServerProxy(Server)
+
+new = 0
+errors = 0
+
 last = ""
+f = open("%s/.last" % Username, "r")
+try:
+    last = f.readline()
+    if last[-1] == '\n':
+        last = last[:len(last)-1]
+    f.close()
+except:
+    pass
+origlast = last
+
 while True:
     r = server.LJ.XMLRPC.syncitems(dochallenge({
         'username': Username,
@@ -42,18 +112,28 @@ while True:
     if len(r['syncitems']) == 0:
         break
     for item in r['syncitems']:
-        #print item['item']
         if item['item'][0] == 'L':
-            if not os.access("archive/"+item['item'], os.F_OK):
-                try:
-                    e = server.LJ.XMLRPC.getevents(dochallenge({
-                        'username': Username,
-                        'ver': 1,
-                        'selecttype': "one",
-                        'itemid': item['item'][2:],
-                    }, Password))
-                    writedump(item['item'], e['events'][0])
-                except xmlrpclib.Fault, x:
-                    print "Error getting item: %s" % item['item']
-                    pprint.pprint(x)
+            print "Fetching journal entry %s (%s)" % (item['item'], item['action'])
+            try:
+                e = server.LJ.XMLRPC.getevents(dochallenge({
+                    'username': Username,
+                    'ver': 1,
+                    'selecttype': "one",
+                    'itemid': item['item'][2:],
+                }, Password))
+                writedump("%s/%s" % (Username, item['item']), e['events'][0])
+                new += 1
+            except xmlrpclib.Fault, x:
+                print "Error getting item: %s" % item['item']
+                pprint.pprint(x)
+                errors += 1
         last = item['time']
+f = open("%s/.last" % Username, "w")
+f.write("%s\n" % last)
+f.close()
+if origlast:
+    print "%d new entries (since %s)" % (new, origlast)
+else:
+    print "%d new entries" % new
+if errors > 0:
+    print "%d errors" % errors