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 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))