Download piratepad documents as html files to a git repository

download_piratepad.py

#!/usr/bin/env python

import urllib2
import re
import subprocess
from time import strftime

url_list = [

]

def main():
    for url in url_list:
        doc = re.search('/\w*$',url).group()[1:]
        url = 'http://piratepad.net/ep/pad/export/'+doc+'/latest?format=html'
        http = urllib2.urlopen(url)
        with open(doc + '.html', 'w') as f:
            f.write(http.read())
        http.close()
        print 'Downloaded ' + url
    subprocess.check_call(['git', 'add', '.'])
    subprocess.check_call(['git', 'commit', '-a',
                           '-m Automated backup %s'%(
                            strftime("%Y-%m-%d %H:%M:%S"))])

if __name__ == '__main__':
    main()