#-------------------------------------------------------------------------------
# Name:        Extract elements from XML
# Purpose:
#
# Author:      xtermin8r
#
# Created:     10/06/2014
# Copyright:   (c) xtermin8r 2014
# Licence:     <your licence>
#-------------------------------------------------------------------------------
import urllib, urllib2
import re
import os
from re import findall
from xml.etree import ElementTree as ET

txtfile = open("E:\\Appz\\Vox\\payloads\\artist_videos.txt", "wb")
xmlin = "E:\Appz\Vox\Payloads\musicvideos.xml"
xmlout = "E:\\Appz\\Vox\\payloads\\ArtistVideos.xml"

#function: get rid of unwanted characters
def cfix(zx):

    f2 = re.sub( '\s+', ' ', zx).strip()
    #Remove Digits
    #f2 = re.sub(r"(^|\W)\d+", "", f2)

    f2 = f2.replace('xDR;', ' ')
    f2 = f2.replace(" -", " ")
    f2 = f2.replace("- ", " ")
    f2 = f2.replace(" - ", " ")
    f2 = f2.replace("-", " ")
    f2 = f2.replace(":", " ")
    f2 = f2.replace("_", " ")
    f2 = f2.replace("5.1", "")
    f2 = f2.replace(".", " ")
    f2 = f2.replace("!", " ")
    f2 = f2.replace("?", " ")
    f2 = f2.replace("@", " ")
    f2 = f2.replace("&#150", "-")
    f2 = f2.replace("1080p", " ")
    f2 = f2.replace("720p", " ")
    f2 = f2.replace("720P", " ")
    f2 = f2.replace("x264", " ")
    f2 = f2.replace("ac3", " ")
    f2 = f2.replace("AC3", " ")
    f2 = f2.replace("DTS", " ")
    f2 = f2.replace("DVD", " ")
    f2 = f2.replace("DvD", " ")
    f2 = f2.replace("VOB", " ")
    f2 = f2.replace("rip", " ")
    f2 = f2.replace("aac", " ")
    f2 = f2.replace("Rip", " ")
    f2 = f2.replace("hd", " ")
    f2 = f2.replace("HD", " ")
    f2 = f2.replace("Hd", " ")
    f2 = f2.replace("Hq", " ")
    f2 = f2.replace("BluRay", " ")
    f2 = f2.replace("Blu Ray", " ")
    f2 = f2.replace("1080i", " ")
    f2 = f2.replace("H264", " ")
    f2 = f2.replace("h264", " ")
    f2 = f2.replace("(", " ")
    f2 = f2.replace(")", " ")
    f2 = f2.replace("]", " ")
    f2 = f2.replace("[", " ")
    f2 = f2.replace("AlbumArtSmall", " ")
    f2 = f2.replace("folder", " ")
    f2 = f2.replace("AlbumArt", " ")
    f2 = re.sub( '\s+', ' ', f2).strip()
    global x
    x = f2
    return x

tree = ET.parse(xmlin)
root = tree.getroot()

#create the root </PayloadsRoot> <PayloadsRoot>
root_element = ET.Element("PayloadsRoot")

global t1
t1 = ""
n1 = 1

for data in root.findall('payload'):
    phrase = data.find('phrase').text
    value = data.find('value').text
    head, tail = os.path.split(value)
    value = ('.').join(tail.split('.')[:-1])
    #remove beginning digits
    value = re.sub('^[0-9]+.', '', value)
    #Remove empty lines
    #split before hyphen
    value = value.split('-', 1)[0]
    cfix(value)
    value = x
    if (value.lower() != t1.lower()):
        if t1 != value:
            if (value != ""):
                #remove beginning digits
                artist = re.sub('^[0-9]+.', '', value)

                #create the first subelemet <payload> </payload>
                pay_element = ET.SubElement(root_element, "payload")
                #create the first child <value> </value>
                child = ET.SubElement(pay_element, "value")
                child.text = str(n1)

                #create the second child <phrase> </phrase>
                child = ET.Element("phrase")

                child.text = artist
                #now append
                pay_element.append(child)

                child = ET.Element("subsetmatching")
                child.text = "true"
                #now append
                pay_element.append(child)

                n1 = n1 + 1
                #txtfile.write(str(artist) + "\n")
                txtfile.write(artist + "\n")
                #print(value)
    t1 = artist

txtfile.close()
def indent(elem, level=0):
    i = "\n" + level*'\t'
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + '\t'
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for elem in elem:
            indent(elem, level+1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

indent(root_element)
#View xml tree
print ( ET.tostring(root_element) )

output_file = open(xmlout, 'w' )
output_file.write( '<?xml version="1.0" encoding="utf-8"?>'+'\n' )
output_file.write( '<!--A VoxCommando Payload file-->' +'\n' )
output_file.write( ET.tostring(root_element) )
output_file.close()