Conversion from Wordpres to PyBlosxom

#!/usr/bin/env python
#
# Convert Wordpress entries and comments to PyBlosxom ones.
# Copyright (C) 2006  Alec Berryman <alec-93qrncnF8/[email protected]>
#
# This program is free software; you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation; either version 2 of the License, or (at your option) any later
# version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
# details.
#
# You should have received a copy of the GNU General Public License along with
# this program; if not, write to the Free Software Foundation, Inc., 51 Franklin
# Street, Fifth Floor, Boston, MA 02110-1301, USA.
#
#
# You should have the linebreaks, pyfilenamemtime, and comments plugins.
#
# Usage: fill in the configuration variables below and run the script.  You'll
# see two new subdirectories, by default 'entries' and 'comments'.
#
#
# The conversion process doesn't consider Wordpress category information.
# Wordpress entries may be filed under multiple categories; this doesn't work in
# PyBlosxom.  Instead, all entries are dumped in one folder and comments in
# another; you'll need to sort through them manually afterwards.  After I sorted
# the entries into categories, I ran the following bash script to place the
# comments where they needed to go:
#
# for cat in activities computers life opinion travel; do
#    for entry in $(find ~/log/entries/${cat}/ -type f -exec basename {} .txt \;); do
#        mv -v ~/tmp/tmp/comments/${entry}* ~/log/comments/${cat}/ 2>/dev/null;
#    done;
# done
#
# Adjust as needed.
#
#      -- Alec Berryman <alec-93qrncnF8/[email protected]>, 2006-03-19


### Configuration
mysql_hostname = ""
mysql_username = ""
mysql_password = ""
mysql_database = ""
entries_output_folder = "entries"
comments_output_folder = "comments"

import MySQLdb
import sys
import os
import time
import re
import string

### Helping functions

def except_fatal(e):
    "Handle fatal exceptions"
    print "Error %d: %s" % (e[0], e[1])
    sys.exit(1)

WPTIME_MATCH = re.compile('([0-9]{4})-([0-1][0-9])-([0-3][0-9]) ([0-2][0-9]):([0-5][0-9])')
wp_pyfilenamemtime = {}
def wp2pyfilenamemtime(wptime):
    "Convert Wordpress-style times to pyfilenamemtime-style ones."
    if wp_pyfilenamemtime.has_key(str(wptime)):
        return wp_pyfilenamemtime[str(wptime)]
    else:
        match = WPTIME_MATCH.search(str(wptime))
        if match:
            groups = match.groups()
            wp_pyfilenamemtime[str(wptime)] = "%s-%s-%s-%s-%s" % \
                                              (groups[0], groups[1], \
                                               groups[2], groups[3], groups[4])
            return wp_pyfilenamemtime[str(wptime)]
        else:
            except_fatal([1, "Couldn't parse Wordpress date/time"])

wp_epoch = {}
def wp2epoch(wptime):
    "Convert Wordpress-style times to seconds since the Epoch."
    if wp_epoch.has_key(str(wptime)):
        return wp_epoch[str(wptime)]
    else:
        match = WPTIME_MATCH.search(str(wptime))
        if match:
            groups = match.groups()
            wp_epoch[str(wptime)] = time.mktime((int(groups[0]), \
                                                 int(groups[1]), \
                                                 int(groups[2]), \
                                                 int(groups[3]), \
                                                 int(groups[4]), \
                                                 0, 0, 0, -1))
            return wp_epoch[str(wptime)]
        else:
            except_fatal([1, "Couldn't parse Wordpress date/time"])

def make_dir(directory):
    "Make a directory if it doesn't exist."
    try:
        if os.path.isdir(directory):
            except_fatal([1, "directory exists"])
        else:
            os.mkdir(directory)
    except IOError, e:
        except_fatal(e)

def sanitize(body):
    """Sanitize the comment body.

    Convert newlines to '<br />'; html-ize '<' and '>'.
    """
    body = string.replace(body, '\r\n', '\n')
    body = string.replace(body, '\r', '\n')
    body = string.replace(body, '\n', '<br />')
    body = string.replace(body, '<', '&lt;')
    body = string.replace(body, '>', '&gt;')
    return body

### main

id_to_nametime = {}

try:
    # connect up
    db = MySQLdb.connect(host=mysql_hostname, user=mysql_username,
                         passwd=mysql_password, db=mysql_database)
    cursor = db.cursor()


    # entries
    select_query = "SELECT post_name, post_date, post_title, post_content, ID" + \
                   " FROM wp_posts" + \
                   ' WHERE wp_posts.post_status = "publish"'
    cursor.execute(select_query)
    make_dir(entries_output_folder)
    rows = cursor.fetchall()
    for row in rows:
        # construct the filename, pyfilenamemtime-style
        entryname = os.path.join(entries_output_folder, "%s-%s.txt" % (row[0], wp2pyfilenamemtime(row[1])))
        
        # construct the entry
        contents = "%s\n#parser linebreaks\n\n%s\n" % (row[2], row[3])
        
        # write it to a file
        entry = file(entryname, 'w')
        entry.write(contents)
        entry.close()

        # build a dict of ID:(post_name,time) for comments
        id_to_nametime[str(row[4])] = (row[0], wp2pyfilenamemtime(row[1]))
        

    # comments
    select_query = "SELECT comment_post_ID, comment_author, comment_author_email," + \
                   "       comment_author_url, comment_author_IP, comment_date_gmt," + \
                   "       comment_content" + \
                   " FROM wp_comments" + \
                   ' WHERE wp_comments.comment_approved = "1"'
    cursor.execute(select_query)
    make_dir(comments_output_folder)
    rows = cursor.fetchall()
    for row in rows:
        # construct the filename, pyfilenamemtime-style plus epoch seconds
        filename = "%s-%s-%s.cmt" % (id_to_nametime[str(row[0])][0], \
                                     id_to_nametime[str(row[0])][1], \
                                     wp2epoch(row[5]))
        commentname = os.path.join(comments_output_folder, filename)

        # construct the entry
        contents = '<?xml version="1.0" encoding="utf-8"?>\n'
        contents += '<item>\n'
        contents += '<title>%s</title>\n' % id_to_nametime[str(row[0])][0]
        contents += '<ipaddress>%s</ipaddress>\n' % row[4]
        contents += '<author>%s</author>\n' % row[1]
        contents += '<link>%s</link>\n' % row[3]
        contents += '<email>%s</email>\n' % row[2]
        contents += '<source></source>\n' # XXX what's this field for?
        contents += '<pubDate>%s</pubDate>\n' % wp2epoch(row[5])
        contents += '<description>%s</description>\n' % sanitize(row[6])
        contents += '</item>\n'
        
        # write it to a file
        comment = file(commentname, 'w')
        comment.write(contents)
        comment.close()
    
except IOError, e:
    except_fatal(e)

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.2.2 (FreeBSD)

iD8DBQFEHeZ6Aud/2YgchcQRAhi0AJ0ZF1oBLinvWYom8HAFvxgabBICAgCcD+vj
dSAR8aogw0EAYgY5oSBYM/s=
=HgnX
-----END PGP SIGNATURE-----