bitsnaps/psv_decryptor.py

## psv_decryptor.py
# This script is inspired from: https://github.com/kigaita/PsvDecryptCore
# It allows you to decrypt psv video files for online developer training website
# The original code was written with .NET for Windows users, this one with Python tested for Mac users.

# *** Disclaimer ****
# Please only use it for your convenience so that you can watch the courses on your devices offline or for educational purposes.
# Piracy is strictly prohibited. Decrypted videos should not be uploaded to open servers, torrents, or other methods of mass distribution. Any consequences resulting from misuse of this tool are to be taken by the user.

# packages you may need to install:
# pip install python-magic
# pip install python-magic-bin
import sys, os, json, magic, hashlib, re

# check python version
if int(sys.version[0]) < 3:
    raise Exception("Must be using Python 3")

class Course:
    modules = []
    def __init__(self, name, id, title, level, hasLearningCheck):
        self.name = name
        self.id = id
        self.title = title
        self.level = level
        self.hasLearningCheck = hasLearningCheck
    def __str__(self):
        return 'Course(Name: ' + self.name+', Nbr Modules: ' + str(len(self.modules))+')' #', Title: '+self.title

class Module:
    index = 0
    clips = []
    def __init__(self, id, name, title, authorHandle, description, index):
        self.id = id
        self.title = title
        self.name = name
        self.authorHandle = authorHandle
        self.description = description
        self.index = index
    def get_indexed_file(self):
        return str(self.index) +'. '+ get_valid_filename(self.title)
    def __str__(self):
        return 'Module(id: ' + self.id+', name: ' + self.name+', Title: '+self.title+')'

class Clip:
    def __init__(self, id, name, title, index):
        self.id = id
        self.name = name
        self.title = title
        self.index = index
    def get_indexed_file(self):
        return str(self.index) +'. '+ get_valid_filename(self.title)+'.mp4'
    def get_file_name(self):
        return str(self.id).lower().replace('-','')+'.psv'
    def __str__(self):
        return 'Clip(id: ' + self.id+', name: ' + self.name+', Title: '+self.title+')'

def get_clips(json_data):
    clips = []
    for c in json_data:
        clip = Clip(c['id'],c['name'],c['title'],c['index'])
        clips.append(clip)
    return clips

def get_modules(json_data):
    modules = []
    i = 0
    if 'modules' in json_data:
        json_modules = json_data['modules']
        for m in json_modules:
            module = Module(m['id'],m['name'],m['title'],m['authorHandle'],m['description'], i)
            module.clips = get_clips(m['clips'])
            # print(module)
            modules.append(module)
            i = i + 1
    return modules

def read_json(filename):
    course = None
    collections = []
    # read json
    with open(filename, mode='r', encoding='utf-8') as f:
        try:
            json_data = json.loads(f.read())
        except Exception as e:
            raise Exception('Error in file: ' + filename)
            sys.exit(2)

        if 'header' in json_data:
            header = json_data['header']
            course = Course(header['name'], header['id'], header['title'], header['level'], header['hasLearningCheck'])
        elif 'collection' in json_data:
            collection = json_data['collection']
            for col in collection:
                if 'name' in col:
                    collections.append({'name':col['name'], 'id':col['id'],
                        'title':col['title'], 'level':col['level']})
                else:
                    if 'course' in col:
                        c = col['course']
                        course = Course(c['name'], c['id'], c['title'], c['level'], c['hasLearningCheck'])
                    else:
                        print('Cannot find "course" key in collection')
                        continue
        # add modules
        if course:
            course.modules = get_modules(json_data)
    # print('Nbr of Collection: '+str(len(collections)))
    return course

# image/jpeg
def get_file_type(filename):
    file_type = magic.from_file(filename, mime=True)
    return file_type

def get_valid_filename(s):
    return re.sub('[^\w_.)( -]', ' -', s)
    # return re.sub(r'(?u)[^-\w.]', '', s.strip().replace(' ', '_'))

def decrypt_psv(fpath, target_dir, target_fname):
    target_file_path = os.path.join(target_dir, target_fname)
    if os.path.exists(target_file_path):
        os.remove(target_file_path)
    print("Writing: %s" % target_file_path)
    with open(target_file_path, "wb") as ofh:
        for byte in bytearray(open(fpath, "rb").read()):
            # ofh.write(chr(byte ^ 101)) # TypeError: a bytes-like object is required, not 'str' (it works with python2)
            ofh.write(bytes(chr(byte ^ 101), 'iso_8859_1'))

# this directory should contains both: "fsCachedData" and "ClipDownloads"
source_dir = '/full/path/to/data/files'
target_dir = '/full/path/to/output/directory'

# loop through files
for root_dir, dirs, files in os.walk(source_dir):
    if os.path.basename(root_dir)=='fsCachedData':
        #Possible algorithms for filename (uuid4): str(uuid.uuid1()).upper()
        for filename in files:
            file_path = os.path.join(root_dir, filename)
            if not get_file_type(file_path).startswith('image/'):
                if not os.path.exists(file_path):
                    print('File: ', file_path, ' not found')
                    sys.exit(1)
                course = read_json(file_path)
                if course:
                    if not course.hasLearningCheck:
                        print(course.title,': DOES NOT HAVE LEARNING CHECK.')
                        continue
                    # Create course directory
                    course_path = os.path.join(target_dir, get_valid_filename(course.title))
                    if not os.path.exists(course_path):
                        print('Creating course dir: ' + course_path)
                        os.mkdir(course_path)
                    # Loop through modules
                    for module in course.modules:
                        module_path = os.path.join(course_path, module.get_indexed_file())
                        if not os.path.exists(module_path):
                            print('Creating module dir: ' + module_path)
                            os.mkdir(module_path)
                        # Loop through clips
                        for clip in module.clips:
                            clip_path = os.path.join(os.path.dirname(root_dir),os.path.join('ClipDownloads',clip.get_file_name()))
                            if os.path.exists(clip_path):
                                print('Course: ', course.title, ', Module: ', module.get_indexed_file())
                                print("Clip: ", clip.get_indexed_file(), ', path: ', clip_path)
                                decrypt_psv(clip_path, module_path, clip.get_indexed_file())
                            # else:
                            #     print('clip not found: ', clip_path)
	# This script is inspired from: https://github.com/kigaita/PsvDecryptCore
	# It allows you to decrypt psv video files for online developer training website
	# The original code was written with .NET for Windows users, this one with Python tested for Mac users.

	# * Disclaimer **
	# Please only use it for your convenience so that you can watch the courses on your devices offline or for educational purposes.
	# Piracy is strictly prohibited. Decrypted videos should not be uploaded to open servers, torrents, or other methods of mass distribution. Any consequences resulting from misuse of this tool are to be taken by the user.

	# packages you may need to install:
	# pip install python-magic
	# pip install python-magic-bin
	import sys, os, json, magic, hashlib, re

	# check python version
	if int(sys.version[0]) < 3:
	raise Exception("Must be using Python 3")

	class Course:
	modules = []
	def __init__(self, name, id, title, level, hasLearningCheck):
	self.name = name
	self.id = id
	self.title = title
	self.level = level
	self.hasLearningCheck = hasLearningCheck
	def __str__(self):
	return 'Course(Name: ' + self.name+', Nbr Modules: ' + str(len(self.modules))+')' #', Title: '+self.title

	class Module:
	index = 0
	clips = []
	def __init__(self, id, name, title, authorHandle, description, index):
	self.id = id
	self.title = title
	self.name = name
	self.authorHandle = authorHandle
	self.description = description
	self.index = index
	def get_indexed_file(self):
	return str(self.index) +'. '+ get_valid_filename(self.title)
	def __str__(self):
	return 'Module(id: ' + self.id+', name: ' + self.name+', Title: '+self.title+')'

	class Clip:
	def __init__(self, id, name, title, index):
	self.id = id
	self.name = name
	self.title = title
	self.index = index
	def get_indexed_file(self):
	return str(self.index) +'. '+ get_valid_filename(self.title)+'.mp4'
	def get_file_name(self):
	return str(self.id).lower().replace('-','')+'.psv'
	def __str__(self):
	return 'Clip(id: ' + self.id+', name: ' + self.name+', Title: '+self.title+')'

	def get_clips(json_data):
	clips = []
	for c in json_data:
	clip = Clip(c['id'],c['name'],c['title'],c['index'])
	clips.append(clip)
	return clips

	def get_modules(json_data):
	modules = []
	i = 0
	if 'modules' in json_data:
	json_modules = json_data['modules']
	for m in json_modules:
	module = Module(m['id'],m['name'],m['title'],m['authorHandle'],m['description'], i)
	module.clips = get_clips(m['clips'])
	# print(module)
	modules.append(module)
	i = i + 1
	return modules

	def read_json(filename):
	course = None
	collections = []
	# read json
	with open(filename, mode='r', encoding='utf-8') as f:
	try:
	json_data = json.loads(f.read())
	except Exception as e:
	raise Exception('Error in file: ' + filename)
	sys.exit(2)

	if 'header' in json_data:
	header = json_data['header']
	course = Course(header['name'], header['id'], header['title'], header['level'], header['hasLearningCheck'])
	elif 'collection' in json_data:
	collection = json_data['collection']
	for col in collection:
	if 'name' in col:
	collections.append({'name':col['name'], 'id':col['id'],
	'title':col['title'], 'level':col['level']})
	else:
	if 'course' in col:
	c = col['course']
	course = Course(c['name'], c['id'], c['title'], c['level'], c['hasLearningCheck'])
	else:
	print('Cannot find "course" key in collection')
	continue
	# add modules
	if course:
	course.modules = get_modules(json_data)
	# print('Nbr of Collection: '+str(len(collections)))
	return course

	# image/jpeg
	def get_file_type(filename):
	file_type = magic.from_file(filename, mime=True)
	return file_type

	def get_valid_filename(s):
	return re.sub('[^\w_.)( -]', ' -', s)
	# return re.sub(r'(?u)[^-\w.]', '', s.strip().replace(' ', '_'))

	def decrypt_psv(fpath, target_dir, target_fname):
	target_file_path = os.path.join(target_dir, target_fname)
	if os.path.exists(target_file_path):
	os.remove(target_file_path)
	print("Writing: %s" % target_file_path)
	with open(target_file_path, "wb") as ofh:
	for byte in bytearray(open(fpath, "rb").read()):
	# ofh.write(chr(byte ^ 101)) # TypeError: a bytes-like object is required, not 'str' (it works with python2)
	ofh.write(bytes(chr(byte ^ 101), 'iso_8859_1'))

	# this directory should contains both: "fsCachedData" and "ClipDownloads"
	source_dir = '/full/path/to/data/files'
	target_dir = '/full/path/to/output/directory'

	# loop through files
	for root_dir, dirs, files in os.walk(source_dir):
	if os.path.basename(root_dir)=='fsCachedData':
	#Possible algorithms for filename (uuid4): str(uuid.uuid1()).upper()
	for filename in files:
	file_path = os.path.join(root_dir, filename)
	if not get_file_type(file_path).startswith('image/'):
	if not os.path.exists(file_path):
	print('File: ', file_path, ' not found')
	sys.exit(1)
	course = read_json(file_path)
	if course:
	if not course.hasLearningCheck:
	print(course.title,': DOES NOT HAVE LEARNING CHECK.')
	continue
	# Create course directory
	course_path = os.path.join(target_dir, get_valid_filename(course.title))
	if not os.path.exists(course_path):
	print('Creating course dir: ' + course_path)
	os.mkdir(course_path)
	# Loop through modules
	for module in course.modules:
	module_path = os.path.join(course_path, module.get_indexed_file())
	if not os.path.exists(module_path):
	print('Creating module dir: ' + module_path)
	os.mkdir(module_path)
	# Loop through clips
	for clip in module.clips:
	clip_path = os.path.join(os.path.dirname(root_dir),os.path.join('ClipDownloads',clip.get_file_name()))
	if os.path.exists(clip_path):
	print('Course: ', course.title, ', Module: ', module.get_indexed_file())
	print("Clip: ", clip.get_indexed_file(), ', path: ', clip_path)
	decrypt_psv(clip_path, module_path, clip.get_indexed_file())
	# else:
	# print('clip not found: ', clip_path)