#!/usr/bin/python

import re
import base64

def ASCIIDecode(string):
    i = 0
    l = len(string)
    ret = ''
    while i < l:
        c = string[i]
        if string[i:(i+2)] == '\\x':
            c = chr(int(string[(i+2):(i+4)],16))
            i+=3
        if string[i:(i+2)] == '\\u':
            c = chr(int(string[(i+2):(i+6)],16))
            i+=5
        ret = ret + str(c)
        i += 1

    return ret

#open file https://www.animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
fh = open('G:\\Python\\adndecode\\page.js', "r")
sHtmlContent = fh.read()#.decode('utf-16','replace')
fh.close()

#nettoyage
#sHtmlContent = sHtmlContent.decode('unicode_escape')
sHtmlContent = ASCIIDecode(sHtmlContent)
sHtmlContent = sHtmlContent.replace("['|\"]","[\\'|\"]")
sHtmlContent = sHtmlContent.replace("\n","\\n")

#print (sHtmlContent)
#fh = open('G:\\Python\\adndecode\\page.txt', "wb")
#fh.write((sHtmlContent).encode('utf-8') )
#fh.close()

#1 processing
r = re.search('^var (_0x[0-9a-f]+)=\[([^]]+)\];',sHtmlContent)
if not r:
    print('erreur 1')

V1 = r.group(1)
T1 = r.group(2)
sHtmlContent = sHtmlContent[r.end():]

T1 = T1.replace("'","").split(',')
i = 0
for j in T1:
    T1[i] = base64.b64decode(T1[i])
    i = i + 1
print (T1)

#2 eme processing
r = re.findall('(_0x[0-9a-f]+)\[.base64DecodeUnicode.\]',sHtmlContent)
if not r:
    print('erreur 2')

V2 = r[0]
print (V2)
r = re.findall( V2 + '\(.(0x[0-9a-f]+).\)',sHtmlContent)
if not r:
    print('erreur 3')
for i in r:
    print (i)
    remp = "'" + T1[ int(i, 16) ].decode("utf-8").replace("'",' ') + "'"
    print ( V2 + "('" + str(i)  + "') replace par " + remp  )
    sHtmlContent = sHtmlContent.replace( V2 + "('" + str(i)  + "')" , remp )


#Sauvegarde, desole pas trouve plus propre
fh = open('G:\\Python\\adndecode\\page.txt', "wb")
fh.write(sHtmlContent.encode('utf-8') )
fh.close()

#print (sHtmlContent)