def _srt_gen_from_url(base_url, end_time=3660, verbose=True):
dt = 60
t0 = 0
t1 = t0 + dt
has_next = True
first = True
srt = ''
last_end = 0.0
while has_next:
if verbose:
print('fetching captions from ' + base_url +
'?t={}/{}'.format(t0, t1))
if first:
first = False
res = requests.get(base_url, params={'t': '{}/{}'.format(t0, t1)})
res.raise_for_status()
srt = res.text.replace(u'\ufeff', '')
else:
res = requests.get(base_url, params={'t': '{}/{}'.format(t0, t1)})
res.raise_for_status()
srt = res.text
t0 = t1 + 1
t1 = t1 + dt
has_next = t1 <= end_time
if srt:
cc = CaptionConverter()
cc.read(srt, SRTReader())
captions = cc.captions.get_captions(lang='en-US')
if first:
last_end = captions[-1].end
else:
for caption in captions:
caption.start += last_end
caption.end += last_end
last_end = captions[-1].end
srt = cc.write(SRTWriter())
yield srt.replace('\n\n', ' \n\n')
else:
yield ''
def route_subtitles(course_id, lecture_id):
subtitles_url = (
'https://class.coursera.org/%s-001/lecture/subtitles?q=%d_en' %
(course_id, lecture_id))
r = requests.get(subtitles_url)
try:
converter = CaptionConverter()
converter.read(r.text, SRTReader())
subtitles = converter.write(WebVTTWriter())
except CaptionReadNoCaptions:
subtitles = ''
return Response(subtitles, content_type='text/vtt')
def ttml2srt(ttml_file_path, srt_file_path=None):
"""Convert TTML subtitles to SubRip subtitles.
Arguments:
ttml_file_path {string} -- The path to the TTML file.
srt_file_path {string} -- The path to the SubRip file.
"""
converter = CaptionConverter()
with open(ttml_file_path, "r", encoding="utf8") as file:
converter.read(file.read(), DFXPReader())
if srt_file_path is None:
srt_file_path = ttml_file_path.replace(".xml", ".srt")
with open(srt_file_path, "wb") as file:
file.write(converter.write(SRTWriter()).encode("utf-8"))
def srt2ttml(srt_file_path, ttml_file_path=None):
"""Convert SubRip subtitles to TTML subtitles.
Arguments:
srt_file_path {string} -- The path to the SubRip file.
ttml_file_path {string} -- The path to the TTML file.
"""
converter = CaptionConverter()
with open(srt_file_path, "r", encoding="utf8") as file:
converter.read(file.read(), SRTReader())
if ttml_file_path is None:
ttml_file_path = srt_file_path.replace(".srt", ".xml")
with open(ttml_file_path, "wb") as file:
file.write(converter.write(DFXPWriter()).encode("utf-8"))
def _make_ts_from_srt(srt):
c = CaptionConverter()
srt = re.sub('$', ' ', srt).replace('\n\n', ' \n\n')
srt = unicodedata.normalize('NFC', srt)
srt = ''.join(i for i in srt
if unicodedata.category(i)[0] != 'C' or i == '\n')
c.read(srt, SRTReader())
ts = c.write(TranscriptWriter()).replace(u'>>> ', u'>>').replace('\n', ' ')
return ts.split('>>')
def ttml2srt(ttml_file_path: str, srt_file_path: Optional[str] = None) -> None:
"""Convert TTML subtitles to SubRip subtitles.
Arguments:
ttml_file_path {string} -- The path to the TTML file.
srt_file_path {string} -- The path to the SubRip file.
"""
file: Union[TextIO, BinaryIO]
converter = CaptionConverter()
encoding = Utils.detect_encoding(ttml_file_path)
with open(ttml_file_path, "r", encoding=encoding) as file:
converter.read(file.read(), DFXPReader())
if srt_file_path is None:
srt_file_path = ttml_file_path.replace(".xml", ".srt")
with open(srt_file_path, "wb") as file:
file.write(converter.write(SRTWriter()).encode(encoding))
def srt2sami(srt_file_path: str, sami_file_path: Optional[str] = None) -> None:
"""Convert SubRip subtitles to SAMI subtitles.
Arguments:
srt_file_path {string} -- The path to the SubRip file.
sami_file_path {string} -- The path to the SAMI file.
"""
file: Union[TextIO, BinaryIO]
converter = CaptionConverter()
encoding = Utils.detect_encoding(srt_file_path)
with open(srt_file_path, "r", encoding=encoding) as file:
converter.read(file.read(), SRTReader())
if sami_file_path is None:
sami_file_path = srt_file_path.replace(".srt", ".smi")
with open(sami_file_path, "wb") as file:
file.write(converter.write(SAMIWriter()).encode(encoding))
def main(argv):
inputfile = ''
try:
opts, args = getopt.getopt(argv, "hi:m", ["ifile="])
except getopt.GetoptError:
print('script2scc.py -i <inputfile>')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print('script2scc.py -i <inputfile>')
sys.exit()
elif opt in ("-i", "--ifile"):
inputfile = arg
file = open(inputfile, 'r', encoding='iso-8859-1')
technoleads_content = data = file.read()
converter = CaptionConverter()
converter.read(technoleads_content, TechnoleadsReader(lang='fr'))
# print (converter.write(WebVTTWriter()))
print(converter.write(SCCWriter()))
def subtitle(request, title, no):
t = re.sub('\(.*?\)', '', title)[:-1]
film = subscene.search(t, "English")
zip = requests.get(subscene.zipped_url(film.subtitles[int(no)]))
fp = StringIO(zip.content)
archive = zipfile.ZipFile(fp, 'r')
srt = archive.read(archive.namelist()[0])
soup = BeautifulSoup(srt)
# print(soup.originalEncoding)
converter = CaptionConverter()
unistring = unicode(srt.decode(soup.originalEncoding))
if "utf-8" in soup.originalEncoding:
unistring = unistring[1:]
converter.read(unistring, SRTReader())
html_parser = HTMLParser.HTMLParser()
return HttpResponse(html_parser.unescape(converter.write(WebVTTWriter()).encode('ascii', 'ignore')),
content_type="text/vtt")
def convert_subtitles_to_vtt(input_file: str, output_file: str):
"""Convert .srt subtitles to .vtt for web playback."""
logger.info(f'Converting {input_file} to {output_file}')
with open(input_file, mode='rb') as raw_input_content:
encoding = chardet.detect(raw_input_content.read())['encoding']
with open(input_file, mode='r', encoding=encoding) as srt_file:
srt_contents = str(srt_file.read())
converter = CaptionConverter()
try:
converter.read(srt_contents, SRTReader())
except CaptionReadNoCaptions:
logger.exception(f'Failed to convert {input_file} to {output_file}')
return False # Likely UTF-16 subtitles
vtt_captions = converter.write(WebVTTWriter())
with open(output_file, mode='w', encoding='utf-8-sig') as vtt_file:
vtt_file.write(vtt_captions)
return True
def from_srt(input_f, output_f):
"""
Takes an input SRT file or filename and writes out VTT contents to the given
output file or filename
"""
with vtt_open(input_f, 'r') as f:
orig = f.read()
detect = chardet.detect(orig)
encoding = detect['encoding']
confidence = detect['confidence']
default_subrip_encoding = 'cp1252' # standard for SubRip files
if confidence < 0.9:
encoding = default_subrip_encoding
backups = [default_subrip_encoding,'utf8']
while True:
try:
print "ENCODING: " + encoding
contents = orig.decode(encoding)
break
except UnicodeDecodeError as e:
if len(backups) is 0:
raise
break
encoding = backups.pop(0)
# caption converter seems to have a tough time with the BOM on
# Python < 2.7.8, so ditch it if it exists.
contents = contents[3:] if contents[:3] == codecs.BOM_UTF8 else contents
converter = CaptionConverter()
converter.read(contents, SRTReader())
contents = converter.write(WebVTTWriter())
with vtt_open(output_f, 'w') as o:
o.write(contents.encode('utf-8')[:-1])
from pycaption import SCCReader
from pycaption import WebVTTWriter
from pycaption import SCCWriter
from pycaption import CaptionConverter
from pycaption import TechnoleadsReader
from pprint import pprint
# file=open('journal.scc','r')
# scc_content = data=file.read()
# pycaps = SCCReader().read(scc_content, lang='fr')
# converter = CaptionConverter()
# converter.read(scc_content, SCCReader())
# print (converter.write(SCCWriter()))
# print (converter.write(WebVTTWriter()))
# pprint(pycaps)
file = open('conseiller_Le_GA00120742_MF0HP.txt', 'r', encoding='iso-8859-1')
technoleads_content = data = file.read()
converter = CaptionConverter()
converter.read(technoleads_content, TechnoleadsReader(lang='fr'))
# print (converter.write(WebVTTWriter()))
print(converter.write(SCCWriter()))
