def search_movie_subtitle(movie, language):
"""find subtitle for a movie base on assigned language
if a language has not be assigned 'english' will be supplied by the Movie class
Args:
movie (Movie): The movie whose subtitle is to be searched.
language (str): The subtitle language.
"""
url = 'https://subscene.com/subtitles/' + movie.slug() + '/' + language
response = requests.get(url)
response.raise_for_status()
soup = bs4.BeautifulSoup(response.text, "html.parser")
del response
subtitles = []
selection = soup.findAll('td', attrs={'class': 'a1'})
for td in selection:
title = str(td.findAll(
'span', attrs={'class':
None})[0].contents[0]).encode('utf-8').strip()
url = str(td.find('a')['href']).strip()
lang = str(td.find('span').contents[0]).encode('utf-8').strip()
temp = Subtitle(title, url, lang)
subtitles.append(temp)
return subtitles
def setupMediaExtractor(self, i):
movie_name = self.clients[i]['movie_name']
self.clients[i]['video_extractor'] = VideoCapturer(movie_name)
video_extractor = self.clients[i]['video_extractor']
fps = video_extractor.fps
frame_count = video_extractor.frame_count
self.clients[i]['audio_extractor'] = AudioCapturer(
movie_name, fps, frame_count)
if self.clients[i]['subtitle_file'] is not None:
self.clients[i]['subtitle'] = Subtitle(
frame_count, fps, self.clients[i]['subtitle_file'])
def load_subtitle(path, aqt_file):
print "Loading %s%s" % (path, aqt_file)
subtitles = []
with open('%s%s' % (path, aqt_file), 'r') as f:
while True:
lines = read_next_lines(f, 4)
if lines:
sub = Subtitle(lines[1], lines[0], lines[2])
subtitles.append(sub)
else:
break
return subtitles
def get_subtitles(file_rows: list) -> list:
result = []
timeline_raw = ''
subtitle_raw = ''
for i, file_row in enumerate(file_rows):
if Subtitle.is_timeline(file_row):
timeline_raw = file_row
if Subtitle.is_subtitle_string(file_row):
subtitle_raw = file_row
if timeline_raw != '' and subtitle_raw != '':
result.append(Subtitle(SubtitleString(subtitle_raw), TimeLine(timeline_raw)))
timeline_raw = ''
subtitle_raw = ''
return result
def main(in_subt, out_subt):
assert in_subt != ""
assert out_subt != ""
parser = Parser()
normalizer = Normalizer()
lemma_filter = Filter()
try:
f = codecs.open(in_subt, 'r', encoding='utf8')
text = f.read()
f.close()
except IOError:
sys.exit("The subtitle could not be found in the path you provided.")
parser.parse(text)
normalizer.normalize(parser.get_text())
lemma_filter.clean_lemmas(normalizer.get_lemmas())
new_sub = Subtitle(parser.get_indexes(), parser.get_times(),
parser.get_text(), lemma_filter.get_final_lemmas(),
lemma_filter.get_dict(), out_subt)
new_sub.create_subtitle()
def parse(self, content):
subtitles = []
number = None
start_time = None
end_time = None
text = ""
self.i = 0
ch = content[self.i]
token_count = len(self.analyser.tokens)
while self.i < len(content):
move_cursor = self.analyser.read_char(ch)
# 检查是否有新的token被读到了
if len(self.analyser.tokens) > token_count:
token_count += 1
new_token = self.analyser.tokens[-1]
assert isinstance(new_token, SrtToken)
# 根据当前state分析
if self.state == SrtParser.start_state:
# 期待输入为标号类型
if new_token.type != SrtToken.TYPE_COUNTER:
print("ERROR, TYPE COUNTER NEEDED BUT", new_token.type,
"FOUND")
return
print("COUNTER", new_token.value)
number = int(new_token.value)
# 跳转到标号态
self.state = SrtParser.counter_state
elif self.state == SrtParser.counter_state:
if new_token.type != SrtToken.TYPE_TIMESTAMP:
print("ERROR, TYPE TIMESTAMP NEEDED BUT",
new_token.type, "FOUND")
return
print("START TIME", new_token.value)
start_time = new_token.value
# 跳转到开始时间态
self.state = SrtParser.start_time_state
elif self.state == SrtParser.start_time_state:
if new_token.type != SrtToken.TYPE_TIME_ARROW:
print("ERROR, TYPE ARROW NEEDED BUT", new_token.type,
"FOUND")
return
print(new_token.value)
# 跳转到 --> 态
self.state = SrtParser.arrow_state
elif self.state == SrtParser.arrow_state:
if new_token.type != SrtToken.TYPE_TIMESTAMP:
print("ERROR, TYPE TIMESTAMP NEEDED BUT",
new_token.type, "FOUND")
return
print("END TIME", new_token.value)
end_time = new_token.value
# 结束时间态
self.state = SrtParser.end_time_state
elif self.state == SrtParser.end_time_state or self.state == SrtParser.text_state:
# 接受任意非换行符字符串(即空行)
# print("TYPE:", new_token.type, [new_token.value])
if new_token.value != "\n":
# 进入字幕态
self.state = SrtParser.text_state
print("TEXT:", new_token.value)
if not new_token.value.endswith("\n"):
new_token.value += "\n"
text += new_token.value
else:
# 跳到起始态
self.state = SrtParser.start_state
print("------- END OF A BLOCK OF SUBTITLE -------")
# 生成新的subtitle对象
subtitle = Subtitle(number, start_time, end_time, text)
subtitles.append(subtitle)
# 清空数据
number = None
start_time = end_time = None
text = ""
if move_cursor:
self.i += 1
if self.i < len(content):
ch = content[self.i]
else:
break
print("Tokens:")
for token in self.analyser.tokens:
print(token)
return subtitles
def subtitles(self) -> List[Path]: try: return [Subtitle(subtitle) for subtitle in self.subtitles_path.iterdir()] except FileNotFoundError: return []
from turtle_graphics import TextMarker
screen = turtle.Screen()
width, height = screen.window_width(), screen.window_height()
canvas = screen.getcanvas()
left, top = 100, 100
geom = '{}x{}+{}+{}'.format(width, height, left, top)
canvas.master.geometry(geom)
screen.title("U.S. States Game | 0/50 ")
image = "blank_states_img.gif"
screen.addshape(image)
turtle.shape(image)
subtitle = Subtitle()
states = States()
states.new_game_memory()
game_is_on = True
while game_is_on:
screen.update()
sleep(0.1)
# ADD TEXT TO SCREEN
score = states.last_score()
answer = screen.textinput(title=f"Guess a State | {score}/50 ",
prompt=" What's another state's name?\n")
# BREAK OUT ON EXIT
if answer.title() == "Exit":
states.states_to_learn()
'-p',
dest='path_folder',
type=str,
required=True,
help='Path folder to find .str files')
self.parser.add_argument('--overwrite_file',
'--o',
'-o',
dest='overwrite_file',
type=str,
required=True,
help='Overwrite the file')
self.args = self.parser.parse_args()
def get_params(self):
return self.args
if __name__ == '__main__':
Credits()
params = Parameters().get_params()
files = HandleFiles(params.path_folder, ".srt").find_files()
for file in files:
print(f'File: "{file}"')
sub = Subtitle(file)
try:
print(params.overwrite_file)
sub.run(params.overwrite_file)
except:
pass
