def get_markup(self, text):
# create a simple element so we can parse using etree
# since srt uses html like tags as markup
base = "<p>%s</p>" % text
el = etree.fromstring(base)
content = [el.text]
base_span = '<span %s>%s</span>'
for child in el.getchildren():
tag = child.tag
if tag == 'b':
content.append(base_span % ('fontWeight="bold"', child.text))
elif tag == 'i':
content.append(base_span % ('fontStyle="italic"', child.text))
elif tag == 'u':
content.append(base_span %
('textDecoration="underline"', child.text))
content.append(child.tail)
if el.tail:
content.append(el.tail.strip())
return "".join(filter(None, content)).replace("\n", "<br />")
register(SRTParser)
has_subs = False
total_items = len(xml)
for i,item in enumerate(xml):
duration = 0
start = int(float(item.get('start')) * 1000)
if hasattr(item, 'duration'):
duration = int(float(item.get('dur', 0)) * 1000)
elif i+1 < total_items:
# youtube sometimes omits the duration attribute
# in this case we're displaying until the next sub
# starts
next_item = xml[i+1]
duration = int(float(next_item.get('start')) * 1000) - start
else:
# hardcode the last sub duration at 3 seconds
duration = 3000
end = start + duration
text = item.text and unescape_html(item.text) or u''
self.sub_set.append_subtitle(start, end, text)
has_subs = True
if not has_subs:
raise ValueError("No subs")
except Exception as e:
raise SubtitleParserError(original_error=e)
return self.sub_set
register(YoutubeParser)
)
return output
def get_markup(self, text):
# create a simple element so we can parse using etree
# since srt uses html like tags as markup
base = "<p>%s</p>" % text
el = etree.fromstring(base)
content = [el.text]
base_span = '<span %s>%s</span>'
for child in el.getchildren():
tag = child.tag
if tag == 'b':
content.append(base_span % ('fontWeight="bold"', child.text))
elif tag == 'i':
content.append(base_span % ('fontStyle="italic"', child.text))
elif tag == 'u':
content.append(base_span % ('textDecoration="underline"', child.text))
content.append(child.tail)
if el.tail:
content.append(el.tail.strip())
return "".join(filter(None, content)).replace("\n", "<br />")
register(SRTParser)
else:
return None
def get_markup(self, text):
# create a simple element so we can parse using etree
# webvtt uses html like tags as markup
base = "<p>%s</p>" % text
el = etree.fromstring(base)
content = [el.text]
base_span = '<span %s>%s</span>'
for child in el.getchildren():
tag = child.tag
if tag == 'b':
content.append(base_span % ('fontWeight="bold"', child.text))
elif tag == 'i':
content.append(base_span % ('fontStyle="italic"', child.text))
elif tag == 'u':
content.append(base_span % ('textDecoration="underline"', child.text))
content.append(child.tail)
if el.tail:
content.append(el.tail.strip())
return "".join(filter(None, content)).replace("\n", "<br />")
register(WEBVTTParser)
class JSONParser(BaseTextParser):
file_type = 'json'
def __init__(self, input_string, pattern, language=None, flags=[], eager_parse=True):
self.input_string = input_string
self.pattern = pattern
self.language = language
super(JSONParser, self).__init__(input_string, pattern, language=language,
flags=[], eager_parse=eager_parse)
def to_internal(self):
if not hasattr(self, 'sub_set'):
self.sub_set = SubtitleSet(self.language)
try:
data = json.loads(self.input_string)
except ValueError:
raise SubtitleParserError("Invalid JSON data provided.")
# Sort by the ``position`` key
data = sorted(data, key=lambda k: k['position'])
for sub in data:
self.sub_set.append_subtitle(sub['start'], sub['end'],
sub['text'])
return self.sub_set
register(JSONParser)
eager_parse=True):
self.input_string = input_string
self.pattern = pattern
self.language = language
super(JSONParser, self).__init__(input_string,
pattern,
language=language,
flags=[],
eager_parse=eager_parse)
def to_internal(self):
if not hasattr(self, 'sub_set'):
self.sub_set = SubtitleSet(self.language)
try:
data = json.loads(self.input_string)
except ValueError:
raise SubtitleParserError("Invalid JSON data provided.")
# Sort by the ``position`` key
data = sorted(data, key=lambda k: k['position'])
for sub in data:
self.sub_set.append_subtitle(sub['start'], sub['end'],
sub['text'])
return self.sub_set
register(JSONParser)
