#!/usr/bin/env python

import os
from os.path import join
from time import strptime, strftime
from string import replace,find,strip

template="""AUTHOR: patrick
TITLE: %s
STATUS: Publish
ALLOW COMMENTS: 1
CONVERT BREAKS: __default__
ALLOW PINGS: 0
PRIMARY CATEGORY:
CATEGORY:

DATE: %s
-----
BODY:
%s
-----
EXTENDED BODY:
%s
-----
EXCERPT:

-----
KEYWORDS:

-----


--------"""

def printTemplate(title,date,body,ext_body):
    #convert date DATE: 01/22/2004 10:07:19 PM
    date = replace(date,'-08:00','')
    date_format = '%Y-%m-%dT%H:%M:%S'
    date = strftime('%m/%d/%Y %I:%M:%S %p', strptime(date,date_format))
    print template % (title,date,body,ext_body)

def parseFile(file):
    #print "reading file %s" % file
    f=open(file,'r')
    title = ''
    title_key = '<dc:title>'
    date = ''
    date_key = '<dc:date>'

    body_start = '</h3>'
    read_body = False
    
    body_more = '<div id=\"more\">'
    body_end = '</div></div>'
    body = ''
    body_ext = ''
    
    read_body_ext = False
    for line in f:
	#print line,
	if find(line,title_key) >= 0 and title == '':
	    title = replace(strip(line),title_key,'')
	    title = replace(title,'</dc:title>','')
	    
	if find(line,date_key) >= 0 and date == '':
	    date = replace(strip(line),date_key,'')
	    date = replace(date,'</dc:date>','')

	if find(line,body_start) > 0 and read_body == False:
	    read_body = True
	    continue # skip first line

	if find(line,body_more) > 0 and read_body == True:
	    read_body_ext = True
	    continue # skip the more tag
	    
	if find(line,'div') > 0 and read_body == True:
	    #print 'end body false becase line is',line
	    read_body = False

	if read_body and not read_body_ext:
	    body = body + line 

	if read_body and read_body_ext:
	    body_ext = body_ext + line

    f.close()
    printTemplate(title,date,strip(body),body_ext)

def walktree(location):
    for root,dirs,files in os.walk(location):
	for name in files:
	    
	    if name != 'index.html':
		parseFile(join(root,name))
#title='Wordpress Rocks'
#date='2005-09-22T22:15:18-08:00'
#printTemplate(title,date,"another blog entry",'')

#parseFile('2005/01/world_vision_up.html')
#parseFile('2004/01/can_you_say_ica.html')
walktree('years/2005')