Using WordPress Export

I bragged recently to a colleague at work that I mostly avoid posts about wordpress. I finally sucumbed, but this will hopefully be actually useful to someone. I have my filk blog, and sometimes I sing in areas which do not have internet. I wanted a quick way to dump it all to a static directory. The script below still has bugs when dealing with unicode, but mostly, it works pretty well, and it is useful to me.

import os, optparse
from xml.dom import minidom

def parseXML(fin):
    s =
    # HACK: sometimes &nbsp; appears where it should not. Override
    s = s.replace('&nbsp;', ' ')
    return minidom.parseString(s)

def items(dom):
    for element in dom.getElementsByTagName('item'):
        post_name_node, = element.getElementsByTagName('wp:post_name')
        post_name = post_name_node.childNodes[0].wholeText
        content_node, = element.getElementsByTagName('content:encoded')
        content = content_node.childNodes[0].wholeText
        yield post_name, content.replace('\n', '<br />\n')

parser = optparse.OptionParser()
parser.add_option('-i', '--input-file', dest='input_file')
parser.add_option('-d', '--output-dir', dest='output_dir')

(options, args) = parser.parse_args()

if not options.input_file or not options.output_dir:
    parser.error('-i and -d are mandatory')
if os.path.exists(options.output_dir):
    parser.error('%s already exists -- will not overwrite' % options.output_dir)

dom = parseXML(file(options.input_file))
index = file(os.path.join(options.output_dir, 'index.html'), 'w')
print >>index, '<html><body><ul>'
for name, content in items(dom):
    fp = file(os.path.join(options.output_dir, name)+'.html', 'w')
    print "writing",  name
    print >> index, '<li><a href="%(name)s.html">%(name)s</a></li>' % vars()

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: