def read_captions(captions, options):
reader_kwargs = {
'read_invalid_positioning': options.read_invalid_positioning
}
scc_reader = pycaption.SCCReader(**reader_kwargs)
srt_reader = pycaption.SRTReader(**reader_kwargs)
sami_reader = pycaption.SAMIReader(**reader_kwargs)
dfxp_reader = pycaption.DFXPReader(**reader_kwargs)
vtt_reader = pycaption.WebVTTReader(**reader_kwargs)
if scc_reader.detect(captions):
if options.lang:
return scc_reader.read(captions,
lang=options.lang,
offset=int(options.offset))
else:
return scc_reader.read(captions, offset=int(options.offset))
elif srt_reader.detect(captions):
return srt_reader.read(captions)
elif sami_reader.detect(captions):
return sami_reader.read(captions)
elif dfxp_reader.detect(captions):
return dfxp_reader.read(captions)
elif vtt_reader.detect(captions):
return vtt_reader.read(captions)
else:
raise Exception('No caption format detected :(')
def main(argv):
inputfile = ''
inputType = ''
outputType = ''
try:
opts, args = getopt.getopt(argv, "h:i:f:t:")
except getopt.GetoptError:
print('test.py -i <inputfile> -f <intputType> -t <outputType>')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print('test.py -i <inputfile> -f <intputType> -t <outputType>')
sys.exit()
elif opt in ("-i", "--ifile"):
inputfile = arg
elif opt in ("-f", "--sfile"):
inputType = arg
elif opt in ("-t", "--tfile"):
outputType = arg
if inputType == outputType:
print('Error: input type and output type are same format')
sys.exit(1)
with io.open(inputfile) as f:
str1 = f.read()
inputValue = inputType.lower()
if inputValue == 'scc':
c = pycaption.SCCReader().read(str1)
elif inputValue == 'srt':
c = pycaption.SRTReader().read(str1)
elif inputValue == 'dfxp':
c = pycaption.DFXPReader().read(str1)
elif inputValue == 'webvtt':
c = pycaption.WebVTTReader().read(str1)
else:
print('Error: invalid input type. <srt/scc/webvtt/dfxp> allowed')
sys.exit(1)
outputValue = outputType.lower()
if outputValue == 'scc':
print(pycaption.SCCWriter().write(c))
elif outputValue == 'srt':
print(pycaption.SRTWriter().write(c))
elif outputValue == 'dfxp':
print(pycaption.DFXPWriter().write(c))
elif outputValue == 'webvtt':
print(pycaption.WebVTTWriter().write(c))
else:
print('Error: invalid output type. <srt/scc/webvtt/dfxp> allowed')
sys.exit(1)
def test_captions(): srt_caps = '''1 00:00:09,209 --> 00:00:12,312 This is an example SRT file,which, while extremely short,is still a valid SRT file. 2 00:00:19,209 --> 00:00:22,312 This is an example SRT file,which, while extremely short,is still a valid SRT file. ''' converter = pycaption.CaptionConverter() converter.read(srt_caps,pycaption.SRTReader()) print(converter.write(pycaption.WebVTTWriter()))
def read_captions(captions, options):
scc_reader = pycaption.SCCReader()
srt_reader = pycaption.SRTReader()
sami_reader = pycaption.SAMIReader()
dfxp_reader = pycaption.DFXPReader()
if scc_reader.detect(captions):
if options.lang:
return scc_reader.read(captions, lang=options.lang,
offset=int(options.offset))
else:
return scc_reader.read(captions, offset=float(options.offset))
elif srt_reader.detect(captions):
return srt_reader.read(captions)
elif sami_reader.detect(captions):
return sami_reader.read(captions)
elif dfxp_reader.detect(captions):
return dfxp_reader.read(captions)
else:
raise Exception('No caption format detected :(')
def run(self):
for input_file in self.input_files:
input_file_name = os.path.basename(input_file)
input_type = os.path.splitext(input_file)[1].lower()[1:]
output_file = os.path.join(
self.output_folder,
os.path.splitext(input_file_name)[0] + '.' + self.output_type)
output_file_name = os.path.basename(output_file)
if os.path.exists(output_file) and not self.overwrite_on:
self.log_signal.emit("{}을 건너뜁니다...".format(input_file_name))
continue
self.log_signal.emit("{}을 읽습니다...".format(input_file_name))
with open(output_file, 'w',
encoding=self.output_encoding) as file_out:
reader = None
encoding = None
content = None
with open(input_file, 'rb') as file_in:
encoding = chardet.detect(file_in.read())['encoding']
with open(input_file, 'r', encoding=encoding) as file_in:
content = file_in.read()
if input_type == "smi":
reader = pycaption.SAMIReader().read(content)
elif input_type == "srt":
reader = pycaption.SRTReader().read(content)
if self.output_type == "smi":
file_out.write(pycaption.SAMIWriter().write(reader))
elif self.output_type == "srt":
file_out.write(pycaption.SRTWriter().write(reader))
elif self.output_type == "txt":
file_out.write(TextWriter().write(reader))
elif self.output_type == "ats":
open(output_file, 'wb').write(AtsWriter().write(reader))
self.log_signal.emit("{}으로 변환했습니다".format(output_file_name))
def read_captions(input_filename):
byte_chunk = os.path.getsize(input_filename)
raw = open(input_filename, 'rb').read(byte_chunk)
if raw.startswith(codecs.BOM_UTF8):
encoding = 'utf-8-sig'
else:
result = chardet.detect(raw)
encoding = result['encoding']
try:
captions = io.open(input_filename, 'r', encoding=encoding).read()
except UnicodeDecodeError as e:
print(e.message + " from file - " + input_filename)
raise e
srt_reader = pycaption.SRTReader()
if srt_reader.detect(captions):
return srt_reader.read(captions)
else:
raise Exception('Illegal srt format %s :(' % input_filename)