def select_subtitles_file(self, fn):
if not os.path.isfile(fn):
def f():
dialog = Gtk.MessageDialog(self.win, 0, Gtk.MessageType.ERROR, Gtk.ButtonsType.CLOSE, "File Not Found")
dialog.format_secondary_text("Could not find subtitles file: %s" % fn)
dialog.run()
dialog.destroy()
GLib.idle_add(f)
return
fn = os.path.abspath(fn)
ext = fn.split('.')[-1]
display_name = os.path.basename(fn)
if ext=='vtt':
with open(fn) as f:
self.subtitles = f.read()
else:
with open(fn,'rb') as f:
caps = f.read()
try: caps = caps.decode()
except UnicodeDecodeError: caps = caps.decode('latin-1')
if caps.startswith('\ufeff'): # BOM
caps = caps[1:]
converter = pycaption.CaptionConverter()
converter.read(caps, pycaption.detect_format(caps)())
self.subtitles = converter.write(pycaption.WebVTTWriter())
pos = len(self.subtitle_store)
self.subtitle_store.append([display_name, pos-2, self.subtitles])
self.subtitle_combo.set_active(pos)
def write_captions(content, options):
writer_kwargs = {
'video_width':
int(options.video_width) if options.video_width else None, # noqa
'video_height':
int(options.video_height) if options.video_height else None # noqa
}
if options.sami:
print(
pycaption.SAMIWriter(
**writer_kwargs).write(content).encode("utf-8")) # noqa
if options.dfxp:
print(
pycaption.DFXPWriter(
**writer_kwargs).write(content).encode("utf-8")) #noqa
if options.srt:
print(
pycaption.SRTWriter(
**writer_kwargs).write(content).encode("utf-8")) # noqa
if options.transcript:
print(
pycaption.TranscriptWriter(
**writer_kwargs).write(content).encode("utf-8")) # noqa
if options.vtt:
print(
pycaption.WebVTTWriter(
**writer_kwargs).write(content).encode("utf-8")) # noqa
if options.unpositioned_dfxp:
print(
pycaption.dfxp.SinglePositioningDFXPWriter(
**writer_kwargs).write(content).encode("utf-8"))
def gen_thumbnail(self):
container = self.fn.lower().split(".")[-1]
thumbnail_fn = None
subtitle_ids = []
if container in ('aac', 'mp3', 'wav'):
cmd = ['ffmpeg', '-i', self.fn, '-f', 'ffmetadata', '-']
else:
thumbnail_fn = tempfile.mkstemp(suffix='.jpg',
prefix='gnomecast_thumbnail_')[1]
os.remove(thumbnail_fn)
cmd = [
'ffmpeg', '-y', '-i', self.fn, '-f', 'mjpeg', '-vframes', '1',
'-ss', '27', '-vf', 'scale=600:-1', thumbnail_fn
]
self.ffmpeg_desc = output = subprocess.check_output(
cmd, stderr=subprocess.STDOUT)
for line in output.decode().split('\n'):
line = line.strip()
if line.startswith('Duration:'):
self.duration = parse_ffmpeg_time(line.split()[1].strip(','))
if line.startswith('Stream') and 'Subtitle' in line:
id = line.split()[1].strip('#').replace(':', '.')
id = id[:id.index('(')]
subtitle_ids.append(id)
print('subtitle_ids', subtitle_ids)
def f():
if thumbnail_fn:
self.thumbnail_image.set_from_file(thumbnail_fn)
os.remove(thumbnail_fn)
self.win.resize(1, 1)
self.update_status()
GLib.idle_add(f)
new_subtitles = []
for subtitle_id in subtitle_ids:
srt_fn = tempfile.mkstemp(suffix='.srt',
prefix='gnomecast_subtitles_')[1]
output = subprocess.check_output([
'ffmpeg', '-y', '-i', self.fn, '-vn', '-an',
'-codec:s:%s' % subtitle_id, 'srt', srt_fn
],
stderr=subprocess.STDOUT)
with open(srt_fn) as f:
caps = f.read()
print('caps', caps)
converter = pycaption.CaptionConverter()
converter.read(caps, pycaption.detect_format(caps)())
subtitles = converter.write(pycaption.WebVTTWriter())
new_subtitles.append((subtitle_id, subtitles))
os.remove(srt_fn)
def f():
pos = len(self.subtitle_store)
for id, subs in new_subtitles:
self.subtitle_store.append([id, pos - 2, subs])
pos += 1
GLib.idle_add(f)
def write_captions(content, options):
if options.sami:
print pycaption.SAMIWriter().write(content).encode("utf-8")
if options.dfxp:
print pycaption.DFXPWriter().write(content).encode("utf-8")
if options.srt:
print pycaption.SRTWriter().write(content).encode("utf-8")
if options.vtt:
print pycaption.WebVTTWriter().write(content).encode("utf-8")
if options.transcript:
print pycaption.TranscriptWriter().write(content).encode("utf-8")
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 write_captions(content, options):
if options.scc:
print(pycaption.SCCWriter().write(content))
if options.sami:
print(pycaption.SAMIWriter().write(content))
if options.dfxp:
print(pycaption.DFXPWriter().write(content))
if options.srt:
print(pycaption.SRTWriter().write(content))
if options.vtt:
print(pycaption.WebVTTWriter().write(content))
if options.transcript:
# import TranscriptWriter only if necessary, since it requires additional dependencies
from pycaption.transcript import TranscriptWriter
print(TranscriptWriter().write(content))
def write_captions(content, options, lang='', filename=''):
if options.sami:
print pycaption.SAMIWriter().write(content).encode("utf-8")
if options.dfxp:
print pycaption.DFXPWriter().write(content).encode("utf-8")
if options.webvtt:
location = os.getcwd()
f = open(location + '/captions/' + filename + '_' + lang + '.vtt',
'w') #Save vtt files into captions folder
f.write(pycaption.WebVTTWriter().write(content, lang).encode("utf-8"))
# print pycaption.WebVTTWriter().write(content, lang).encode("utf-8")
if options.srt:
print pycaption.SRTWriter().write(content).encode("utf-8")
if options.transcript:
print pycaption.TranscriptWriter().write(content).encode("utf-8")
def select_subtitles_file(self, fn):
ext = fn.split('.')[-1]
display_name = os.path.basename(fn)
if ext == 'vtt':
with open(fn) as f:
self.subtitles = f.read()
else:
with open(fn) as f:
caps = f.read()
if caps.startswith('\ufeff'): # BOM
caps = caps[1:]
converter = pycaption.CaptionConverter()
converter.read(caps, pycaption.detect_format(caps)())
self.subtitles = converter.write(pycaption.WebVTTWriter())
pos = len(self.subtitle_store)
self.subtitle_store.append([display_name, pos - 2, self.subtitles])
self.subtitle_combo.set_active(pos)
def convert_to_vtt(caps):
"""Convert subtitles to WebVTT format
Note that if the subtitles are already in VTT format, nothing is done.
Args:
caps (str or unicode)
Returns:
caps (unicode): None if the format could not be detected.
"""
if isinstance(caps, str):
caps = caps.decode('utf-8')
caps = caps.strip(u"\ufeff").strip(u"\n").strip(u"\r")
sub_reader = pycaption.detect_format(caps)
if sub_reader is None:
return None
if sub_reader != pycaption.WebVTTReader:
caps = pycaption.WebVTTWriter().write(sub_reader().read(caps))
return caps
def convert_to_vtt(path):
"""
Convert a subtitles file from any format (e.g: srt) to vtt. This is
necessary for use with videojs, which supports only vtt subtitles.
"""
caps = open(path, 'rb').read()
try:
caps = caps.decode('utf8')
except UnicodeDecodeError:
# Attempt to read with custom encoding
detected = chardet.detect(caps)
caps = caps.decode(detected['encoding'])
caps = caps.strip("\ufeff").strip("\n").strip("\r")
sub_reader = pycaption.detect_format(caps)
if sub_reader is None:
return None
if sub_reader != pycaption.WebVTTReader:
read_caps = sub_reader().read(caps)
caps = pycaption.WebVTTWriter().write(read_caps)
return caps
def update_subtitles(self):
subtitle_ids = []
cmd = ['ffprobe', '-i', self.fn]
output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
for line in output.decode().split('\n'):
line = line.strip()
if line.startswith('Stream') and 'Subtitle' in line:
id = line.split()[1].strip('#').replace(':','.')
id = id[:id.index('(')]
subtitle_ids.append(id)
print('subtitle_ids', subtitle_ids)
new_subtitles = []
for subtitle_id in subtitle_ids:
srt_fn = tempfile.mkstemp(suffix='.srt', prefix='gnomecast_subtitles_')[1]
output = subprocess.check_output(['ffmpeg', '-y', '-i', self.fn, '-vn', '-an', '-codec:s:%s' % subtitle_id, 'srt', srt_fn], stderr=subprocess.STDOUT)
with open(srt_fn) as f:
caps = f.read()
#print('caps', caps)
converter = pycaption.CaptionConverter()
converter.read(caps, pycaption.detect_format(caps)())
subtitles = converter.write(pycaption.WebVTTWriter())
new_subtitles.append((subtitle_id, subtitles))
os.remove(srt_fn)
def f():
self.subtitle_store.clear()
self.subtitle_store.append(["No subtitles.", -1, None])
self.subtitle_store.append(["Add subtitle file...", -2, None])
self.subtitle_combo.set_active(0)
pos = len(self.subtitle_store)
for id, subs in new_subtitles:
self.subtitle_store.append([id, pos-2, subs])
pos += 1
GLib.idle_add(f)
ext = self.fn.split('.')[-1]
sexts = ['vtt', 'srt']
for sext in sexts:
if os.path.isfile(self.fn[:-len(ext)] + sext):
self.select_subtitles_file(self.fn[:-len(ext)] + sext)
break
def upload_subtitle(public_video_id, subtitle_public_id, language_code,
content):
"""
Convert subtitle to VTT and upload it.
Args:
public_video_id (str)
subtitle_id (str)
language_code (str)
content (bytes)
"""
# Note: if this ever raises an exception, we should convert it to SubtitleInvalid
content = content.decode('utf-8')
# Convert to VTT, whatever the initial format
content = content.strip("\ufeff\n\r")
sub_reader = pycaption.detect_format(content)
if sub_reader is None:
raise exceptions.SubtitleInvalid("Could not detect subtitle format")
if sub_reader != pycaption.WebVTTReader:
content = pycaption.WebVTTWriter().write(sub_reader().read(content))
backend.get().upload_subtitle(public_video_id, subtitle_public_id,
language_code, content)
def write_captions(content, output_filename):
with open(output_filename, 'w') as output_file:
output_file.write(
pycaption.WebVTTWriter().write(content).encode("utf-8"))
print("Generate " + output_filename)
