def _parse(self, lines):
self._compute_blocks(lines)
for block in self.blocks:
if self._is_cue_block(block):
caption = self._parse_cue_block(block)
self.captions.append(caption)
elif self._is_comment_block(block):
continue
elif self._is_style_block(block):
if self.captions:
raise MalformedFileError(
'Style block defined after the first cue in line {}.'.
format(block.line_number))
style = Style()
style.lines = block.lines[1:]
self.styles.append(style)
else:
if len(block.lines) == 1:
raise MalformedCaptionError(
'Standalone cue identifier in line {}.'.format(
block.line_number))
else:
raise MalformedCaptionError(
'Missing timing cue in line {}.'.format(
block.line_number + 1))
def _read_content(self, file):
with open(file, encoding='utf-8') as f:
lines = [line.rstrip() for line in f.readlines()]
if not lines:
raise MalformedFileError('The file is empty.')
return lines
def _read_content(self, file):
with open(file, 'rb') as f:
raw = f.read(32)
encoding = chardet.detect(raw)['encoding']
with open(file, encoding=encoding) as f:
lines = [line.rstrip() for line in f.readlines()]
if not lines:
raise MalformedFileError('The file is empty.')
return lines
def _read_content(self, file):
first_bytes = min(32, os.path.getsize(file))
with open(file, 'rb') as f:
raw = f.read(first_bytes)
if raw.startswith(codecs.BOM_UTF8):
encoding = 'utf-8-sig'
else:
encoding = 'utf-8'
with open(file, encoding=encoding) as f:
lines = [line.rstrip('\n') for line in f.readlines()]
if not lines:
raise MalformedFileError('The file is empty.')
return lines
def _validate(self, lines):
if not self._validate_timeframe_line(lines[0]):
raise MalformedFileError('The file does not have a valid format')
def _validate(self, lines):
if not re.match('WEBVTT', lines[0]):
raise MalformedFileError('The file does not have a valid format')
def _validate(self, lines):
if len(lines
) < 2 or lines[0] != '1' or not self._validate_timeframe_line(
lines[1]):
raise MalformedFileError('The file does not have a valid format.')
def _validate(self, lines):
if 'WEBVTT' not in lines[0]:
raise MalformedFileError('The file does not have a valid format')