X-Git-Url: https://wagner.pp.ru/gitweb/?a=blobdiff_plain;f=convertdump.py;h=f098a58f2a2e0b29fd0fbaca86ceb3a5a7e75509;hb=8c79e315b76bd83ec4d34b0644d450f84960f160;hp=f19be5f8243335c4ad1fa064b869a941be9a8cd1;hpb=a0580d0de808cd9aebda0e4b4a0538a3c83fba2f;p=oss%2Fljdump.git diff --git a/convertdump.py b/convertdump.py index f19be5f..f098a58 100755 --- a/convertdump.py +++ b/convertdump.py @@ -1,7 +1,36 @@ #!/usr/bin/python +# Copyright 2009, Sean M. Graham (www.sean-graham.com) +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are +# met: +# +# - Redistributions of source code must retain the above copyright notice, +# this list of conditions and the following disclaimer. +# +# - Redistributions in binary form must reproduce the above copyright notice, +# this list of conditions and the following disclaimer in the documentation +# and/or other materials provided with the distribution. +# +# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED +# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO +# EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, +# INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, +# OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, +# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + import xml.dom.minidom import os +import codecs +import sys +import getopt + from time import strptime, strftime def getNodeText(doc, nodename): @@ -19,22 +48,30 @@ def getNodeText(doc, nodename): return rc def appendTextNode(doc, parent, nodename, value): + nodeValue = value + + # make sure value is properly encoded + try: + bytes = nodeValue.encode("UTF-8") + except: + bytes = nodeValue.encode("cp1252") + nodeValue = unicode(bytes, "UTF-8") + element = doc.createElement(nodename) - if( value != "" ): - textNode = doc.createTextNode(value) + if( nodeValue != "" ): + textNode = doc.createTextNode(nodeValue) element.appendChild(textNode) parent.appendChild(element) -def addEntryForId(outDoc, username, id): +def addEntryForId(outDoc, element, username, id, includeSecure): entryFile = open("%s/L-%s" % (username,id), "r") inDoc = xml.dom.minidom.parse(entryFile) # Create an entry element entry = outDoc.createElement("entry") - ljElement.appendChild(entry) # Create an itemid element appendTextNode(outDoc, entry, "itemid", getNodeText(inDoc,"itemid")) @@ -50,12 +87,28 @@ def addEntryForId(outDoc, username, id): event = inDoc.getElementsByTagName("event")[0] appendTextNode(outDoc, entry, "event", getNodeText(event, "event")) - # Create an allowmask element (doesn't exist in pydump output if public) - try: - appendTextNode(outDoc, entry, "allowmask", - getNodeText(inDoc, "allowmask")) - except: - appendTextNode(outDoc, entry, "allowmask", "0") + security = getNodeText(inDoc, "security") + + if(security != ""): + # don't append this entry unless the user provided the argument + if(includeSecure == False): + print("omitting secure entry: L-%s" % id) + return + else: + if(security == "usemask"): + print("including allowmask entry: L-%s" % id) + + # Create an allowmask element + maskText = getNodeText(inDoc, "allowmask") + + if(maskText != ""): + appendTextNode(outDoc, entry, "allowmask", maskText) + else: + appendTextNode(outDoc, entry, "allowmask", "0") + else: + print("including private entry: L-%s" % id) + + appendTextNode(outDoc, entry, "security", security) # Create a taglist element appendTextNode(outDoc, entry, "taglist", getNodeText(inDoc, "taglist")) @@ -64,11 +117,12 @@ def addEntryForId(outDoc, username, id): # with it addCommentsForId(outDoc, entry, username, id) + element.appendChild(entry) + def addCommentsForId(outDoc, entry, username, id): try: commentFile = open("%s/C-%s" % (username,id), "r") - except: - # there are no comments for this entry + except IOError: # there are no comments for this entry return inDoc = xml.dom.minidom.parse(commentFile) @@ -118,38 +172,107 @@ def addCommentsForId(outDoc, entry, username, id): if(parentId != ""): appendTextNode(outDoc, outComment, "parent_itemid", parentId) +def usage(): + print( "Usage: convertdump.py [arguments]" ) + print( """ +This will convert a pydump archive into something compatible with the +WordPress LiveJournal importer. This is the same format used by the Windows +ljArchive exporter. + +Arguments: + -u --user username of archive to process [required] + -l --limit limit the number of entries in each xml file (default 250) + -i --insecure include private and protected entries in the output + -h --help show this help page + +Example: + ./convertdump.py --user stevemartin --limit 200 --insecure +""") + + +def main(argv): + username = "" + entryLimit = 250 + includeSecure = False; + + if( len(argv) == 0 ): + usage() + sys.exit(2) + + try: + opts, args = getopt.getopt(sys.argv[1:], "hu:l:i", ["help", + "user=", + "limit=", + "insecure"]) + except getopt.GetoptError, err: + # print help information and exit: + print str(err) # will print something like "option -a not recognized" + usage() + sys.exit(2) + + for o, a in opts: + if o == "-v": + verbose = True + elif o in ("-u", "--user"): + username = a + elif o in ("-l", "--limit"): + entryLimit = int(a) + elif o in ("-i", "--insecure"): + print( "Warning: Including secure entries in XML output" ) + includeSecure = True + elif o in ("-h", "--help"): + usage() + sys.exit() + else: + assert False, "unhandled option" + + userDir = os.listdir(username) + + highNum = -1 + entryArray = [] + + # get the list of entries + for file in userDir: + if file.startswith("L-"): + entryNum = int(file.replace("L-","")) + + entryArray.append(entryNum) + if( highNum < entryNum ): + highNum = entryNum + entryArray.sort() -# Create the minidom document -outDoc = xml.dom.minidom.Document() + # Create the minidom document + outDoc = xml.dom.minidom.Document() -# Create the base element -ljElement = outDoc.createElement("livejournal") -outDoc.appendChild(ljElement) + # Create the base element + ljElement = outDoc.createElement("livejournal") + outDoc.appendChild(ljElement) -userDir = os.listdir("grahams") + currentFileEntry = 0 -highNum = -1 -entryArray = [] + # start processing entries + for entry in entryArray: + addEntryForId(outDoc, ljElement, username, entry, includeSecure) -# get the list of entries -for file in userDir: - if file.startswith("L-"): - entryNum = int(file.replace("L-","")) + currentFileEntry += 1 - entryArray.append(entryNum) + if( currentFileEntry == entryLimit or entry == entryArray[-1] ): - if( highNum < entryNum ): - highNum = entryNum + f = open("%s - %s.xml" % (username, entry), "w") + tempXML = outDoc.toxml("UTF-8") + f.write(tempXML) + + currentFileEntry = 0 -entryArray.sort() + # Create the minidom document + outDoc = xml.dom.minidom.Document() -# start processing entries -for entry in entryArray: - print entry - addEntryForId(outDoc, "grahams", entry) + # Create the base element + ljElement = outDoc.createElement("livejournal") + outDoc.appendChild(ljElement) +if __name__ == "__main__": + main(sys.argv[1:]) -# Print our newly created XML -print outDoc.toprettyxml(indent=" ")