Migrate blog from wordpress into nikola

# you might need need `sudo apt-get install python-gdbm` on Debian
# install python2 and make sure sqlite is supported
sudo USE="sqlite" emerge -a =python-2* # Gentoo Linux

# one debian/ubuntu, you need: `apt-get install libxml2-dev libxslt1-dev python-dev libjpeg-dev` for lxml

# Not to mess up with root
export PATH=$PATH:$HOME/.local/bin

# Best way to get latest pip,
# see https://packaging.python.org/installing/#install-pip-setuptools-and-wheel
python ~/bin/get-pip.py --user # ~/.local/bin/pip

# install dependencies (requests is required by zen theme)
# sudo pip install markdown webassets phpserialize nikola requests
# "sudo pip install" could screw up my python setup on Gentoo Linux
# @see https://forums.gentoo.org/viewtopic-t-1006044-view-next.html?sid=931f7be2c16ac99fd85eb2940c0bf82b
# so install the python packages in my HOME directory might be better
# @see http://stackoverflow.com/questions/2915471/install-a-python-package-into-a-different-directory-using-pip
pip install --user markdown webassets phpserialize nikola requests

# create root directory of nikola
mkdir -p ~/.config/nikola;cd ~/.config/nikola

# import from wordpress dump
nicola import_wordpress my_wordpress_dump.xml

# since I use zen theme, I need install lessc
# obviously NodeJS is required
npm install -g less # use portable nodejs in $HOME is better

# I use zen theme, before intalling new theme, clean the legacy theme at first
rm -rf themes/zen/;nikola install_theme zen
# or rm -rf themes/zen/; http_proxy=http://127.0.0.1:8087 nikola install_theme zen at mainland China

# build the web site
nikola build

find -name '*.wp' -exec grep -l "\[sourcecode.*\<diff\>.*\]" {} \; |xargs sed -i 's/\[sourcecode.*\<diff\>.*\]/<pre class="brush: diff;">/g
find -name '*.wp' -exec grep -l "~~~~~~~~~~~~" {} \;|xargs sed -i "s%~~~~~~~~~~~~%</pre>%g"

#!/usr/bin/python
import getopt, sys, csv
def usage():
    print '''
NAME
    fix url mapping when migrate wordpress blog into nikola
Usage
    python fix-url-map.py [options]
'''[1:-1]

if __name__ == '__main__':
    try:
        opts, args = getopt.getopt(sys.argv[1:], "hf:x:", ["help", "file=","xml="])
    except getopt.GetoptError as err:
        # print help information and exit:
        print str(err) # will print something like "option -a not recognized"
        usage()
        sys.exit(2)

    file=""
    xml=""

    for o, a in opts:
        if o in ("-h", "--help"):
            usage()
            sys.exit()
        elif o in ("-f", "--file"):
            file= a
        elif o in ("-x", "--xml"):
            xml=a
        else:
            assert False, "unhandled option"

    with open(xml, 'r') as content_file:
        content = content_file.read()

    with open(file, 'rb') as csvfile:
         spamreader = csv.reader(csvfile, delimiter=',')
         for row in spamreader:
             content=content.replace(">"+row[0]+"<",">"+row[1]+"<")

    print content