def __init__(self, index=0, start=None, end=None, text='', position=''):
try:
self.index = int(index)
except (TypeError, ValueError): # try to cast as int, but it's not mandatory
self.index = index
self.start = SubRipTime.coerce(start or 0)
self.end = SubRipTime.coerce(end or 0)
self.position = str(position)
self.text = str(text)
def __init__(self, index=0, start=None, end=None, text=u'', position=u''):
try:
self.index = int(index)
except ValueError:
raise InvalidIndex(repr(index))
self.start = SubRipTime.coerce(start or 0)
self.end = SubRipTime.coerce(end or 0)
self.position = unicode(position)
self.text = unicode(text)
def __init__(self, index=0, start=None, end=None, text='', position=''):
try:
self.index = int(index)
except (TypeError, ValueError): # try to cast as int, but it's not mandatory
self.index = index
self.start = SubRipTime.coerce(start or 0)
self.end = SubRipTime.coerce(end or 0)
self.position = str(position)
self.text = str(text)
def __init__(self, index=0, start=None, end=None, text=u'', position=u''):
try:
self.index = int(index)
except ValueError:
raise InvalidIndex(repr(index))
self.start = SubRipTime.coerce(start or 0)
self.end = SubRipTime.coerce(end or 0)
self.position = unicode(position)
self.text = unicode(text)
def convert(directory, filename):
index = 0
vtt_filepath = f"%s\\%s.vtt" % (directory, filename)
srt_filepath = f"%s\\%s.srt" % (directory, filename)
srt = open(srt_filepath, "w")
for caption in WebVTT().read(vtt_filepath):
index += 1
start = SubRipTime(0, 0, caption.start_in_seconds)
end = SubRipTime(0, 0, caption.end_in_seconds)
srt.write(
SubRipItem(index, start, end, html.unescape(
caption.text)).__str__() + "\n")
def from_string(cls, source):
match = cls.RE_ITEM.match(source)
if not match:
raise InvalidItem(source)
data = dict(match.groupdict())
for group in ('start', 'end'):
data[group] = SubRipTime.from_string(data[group])
return cls(**data)
def convert_sub(vtt_file):
index = 0
file_name, file_extension = os.path.splitext(vtt_file)
if not file_extension.lower() == ".vtt":
sys.stderr.write("Skipping %s.\n" % vtt_file)
raise Exception("VTT file could not be found.")
srt = open(file_name + ".srt", "w")
for caption in WebVTT().read(vtt_file):
index += 1
start = SubRipTime(0, 0, caption.start_in_seconds)
end = SubRipTime(0, 0, caption.end_in_seconds)
srt.write(
SubRipItem(index, start, end, html.unescape(
caption.text)).__str__() + "\n")
def is_passed(self, position):
"""Checks for the ending of the current subtitle.
:param int position: Position in media stream (in seconds)
:returns: Achievement of the subtitle ending
:rtype: boolean
"""
if (self.has_subtitle()
and SubRipTime(seconds=int(position)) >= self._subtitle.end):
return True
return False
def text_at_time(self, time):
"""
text_at_time()
Get text that, according to subtitles, should appear on screen
exactly at given time.
"""
time = SubRipTime.coerce(time)
for item in self:
if item.start <= time and time <= item.end:
return item.text
def get_video_length(path):
try:
process = subprocess.Popen(['avconv', '-i', path], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
stdout, stderr = process.communicate()
matches = re.search(r"Duration:\s{1}(?P<hours>\d+?):(?P<minutes>\d+?):(?P<seconds>\d+\.\d+?),", stdout, re.DOTALL).groupdict()
seconds = Decimal(matches['seconds']).quantize(Decimal('1.000'))
secsAndMilli = str(seconds).partition('.')
time = matches['hours'].zfill(2)+':'+matches['minutes'].zfill(2)+':'+secsAndMilli[0].zfill(2)+','+secsAndMilli[2].zfill(3)
return SubRipTime.from_string(time)
except AttributeError:
print "No such file: ",path
sys.exit(1)
def __init__(self, index=0, start=None, end=None, text=u'', position=u''):
self.index = int(index)
self.start = SubRipTime.coerce(start or 0)
self.end = SubRipTime.coerce(end or 0)
self.position = unicode(position)
self.text = unicode(text)
script = sys.argv[0]
args = sys.argv[1:]
def usage():
return "%s FILE...\n" % os.path.basename(script)
if len(args) < 1:
sys.stderr.write(usage())
sys.exit(1)
for arg in args:
index = 0
file_name, file_extension = os.path.splitext(arg)
if not file_extension.lower() == ".vtt":
sys.stderr.write("Skipping %s.\n" % arg)
continue
srt = open(file_name + ".srt", "w")
for caption in WebVTT().read(arg):
index += 1
start = SubRipTime(0, 0, caption.start_in_seconds)
end = SubRipTime(0, 0, caption.end_in_seconds)
srt.write(
SubRipItem(index, start, end, html.unescape(
caption.text)).__str__() + "\n")
parser.add_argument('output',
help='The file where the fixed subs should be saved')
parser.add_argument('-i', '--inputVideo1', nargs=1,
help='The first video file of the two to combine.')
parser.add_argument('-o', '--offset2', nargs=1,
help='Offset of second input file from end of first in format HH:MM:SS,mmm')
parser.add_argument('-e', '--encoding', nargs=1,
help='Encoding of the subtitle files, must be the same. Default is utf-8.')
args = parser.parse_args()
if not args.inputVideo1 and not args.offset2:
parser.error('One of -i/--inputVideo1 or -o/--offset2 are required')
sys.exit(1)
zeroTime = "00:00:00,000"
if args.inputVideo1:
length1Time = get_video_length(args.inputVideo1[0])
offset2Time = SubRipTime.from_string(zeroTime)
inVid1 = args.inputVideo1[0]
if args.offset2:
offset2Time = SubRipTime.from_string(args.offset2[0])
length1Time = SubRipTime.from_string(zeroTime)
offset2 = args.offset2[0]
inSubName1 = args.input1
inSubName2 = args.input2
outSubName = args.output
if args.encoding:
encoding = args.encoding[0]
else:
encoding = args.encoding
try:
inSub1 = SubRipFile.open(inSubName1,encoding)
except AttributeError:
print('Converting and validating subtitles...')
with open('subs.srt', 'w') as srt:
index = 0
for caption in WebVTT().read("subs.vtt"):
index += 1
for find, replace in unicode_fixes.items():
caption.text = re.sub(find,
replace,
caption.text,
flags=re.MULTILINE)
if caption.text.find('�') > -1:
raise Exception(
'FIXME: Found bad Unicode character at time index ' +
caption.start + ': ' + caption.text)
start = SubRipTime.from_ordinal(round(caption.start_in_seconds * 1000))
end = SubRipTime.from_ordinal(round(caption.end_in_seconds * 1000))
srt.write(
SubRipItem(index, start, end, html.unescape(
caption.text)).__str__() + "\n")
print('Downloading poster...')
poster_url = master_json['poster']
with urlopen(poster_url) as posterurl:
data = posterurl.read()
with open('cover.jpg', 'wb') as posterjpg:
posterjpg.write(data)
print('Downloading master playlist...')
master_playlist = m3u8.load(master_json['sources'][1]['src'])
