Python pysrt.open方法代码示例

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def extract_labels(srt, samples):
    subs = pysrt.open(srt)
    labels = np.zeros(samples)
    for sub in subs:
        start = timeToPos(sub.start)
        end = timeToPos(sub.end)+1
        for i in range(start, end):
            if i < len(labels):
                labels[i] = 1

    return labels 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def __init__(self, media, path):
        self.media = media
        self.path = path
        self.subs = pysrt.open(self.path, encoding=self._find_encoding()) 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def _find_encoding(self):
        data = None
        with open(self.path, "rb") as f:
            data = f.read()
        det = chardet.detect(data)
        return det.get("encoding") 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def write_to_file(self, output_path: Opt[str] = None):
        util.touch(output_path)
        sub_rip_file = pysrt.open(output_path, encoding='utf-8')

        for index, sub in enumerate(self.subtitles):
            start_time = pysrt.SubRipTime.from_ordinal(sub.start_time * 1000)
            end_time = pysrt.SubRipTime.from_ordinal(sub.end_time * 1000)
            next_sub = pysrt.SubRipItem(index=index, text=sub.text, start=start_time, end=end_time)
            sub_rip_file.append(next_sub)

        sub_rip_file.save(output_path, encoding='utf-8')

        return output_path 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def generateDatasets(train_files, cut_data, len_mfcc, step_mfcc, hop_len, freq):
    
    X, Y = [], []
    
    for tf in train_files:

        train_data, labels = generateSingleDataset(tf, cut_data, len_mfcc, step_mfcc, hop_len, freq)
                
        X.append(train_data)
        Y.append(labels)
        
    X = np.concatenate(X)
    Y = np.concatenate(Y)
        
    if cut_data:
        filename = STORE_DIR + 'dataset_CUT_' + str(freq) + '_' + str(hop_len) + '_' + str(len_mfcc) + '_' + str(step_mfcc) + '_' + str(X.shape[0]) + '_' + str(X.shape[1]) + '_' + str(X.shape[2]) + '.pickle'
    else:
        filename = STORE_DIR + 'dataset_' + str(freq) + '_' + str(hop_len) + '_' + str(len_mfcc) + '_' + str(step_mfcc) + '_' + str(X.shape[0]) + '_' + str(X.shape[1]) + '_' + str(X.shape[2]) + '.pickle'
    print filename
    with open(filename, 'w') as f:
        pickle.dump([X, Y], f)
        
    return X, Y


# Generate a dataset from all available files 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def sotreResults(results, v):
# %%
    import pickle
    
    with open('test_results_'+v+'.pickle', 'w') as f:
        pickle.dump(results, f)


# %% 

# Plot stored training statistics. Look for the best model 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def load_srt(srt_dir, srt_cache_path):
    """
    return: A python dict, the keys are the video names, the entries are lists,
            each contains all the text from a .srt file
    sub_times are the start time of the sentences.
    """
    if os.path.exists(srt_cache_path):
        print("Found srt data cache, loading ...")
        return load_json(srt_cache_path)

    print("Loading srt files from %s ..." % srt_dir)
    srt_paths = glob.glob(os.path.join(srt_dir, "*.srt"))
    name2sub_text = {}
    name2sub_time = {}
    for i in tqdm(range(len(srt_paths))):
        subs = pysrt.open(srt_paths[i], encoding="iso-8859-1")
        if len(subs) == 0:
            subs = pysrt.open(srt_paths[i])

        text_list = []
        sub_time_list = []
        for j in range(len(subs)):
            cur_sub = subs[j]
            cur_str = cur_sub.text
            cur_str = "(<UNKNAME>:)" + cur_str if cur_str[0] != "(" else cur_str
            cur_str = cur_str.replace("\n", " ")
            text_list.append(cur_str)
            sub_time_list.append(
                60 * cur_sub.start.minutes + cur_sub.start.seconds + 0.001 * cur_sub.start.milliseconds)

        key_str = os.path.splitext(os.path.basename(srt_paths[i]))[0]
        name2sub_text[key_str] = text_list
        name2sub_time[key_str] = sub_time_list
    srt_data = {"sub_text": name2sub_text, "sub_time": name2sub_time}
    save_json(srt_data, srt_cache_path)
    return srt_data 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def find_summary_regions(srt_filename, duration=30, language="english"):
    """ Find important sections

    Args:
        srt_filename(str): Name of the SRT FILE
        duration(int): Time duration
        language(str): Language of subtitles (default to English)

    Returns:
        list: segment of subtitles as "summary"

    """
    srt_file = pysrt.open(srt_filename)

    enc = chardet.detect(open(srt_filename, "rb").read())['encoding']
    srt_file = pysrt.open(srt_filename, encoding=enc)

    # generate average subtitle duration
    subtitle_duration = time_regions(
        map(srt_segment_to_range, srt_file)) / len(srt_file)
    # compute number of sentences in the summary file
    n_sentences = duration / subtitle_duration
    summary = summarize(srt_file, n_sentences, language)
    total_time = time_regions(summary)
    too_short = total_time < duration
    if too_short:
        while total_time < duration:
            n_sentences += 1
            summary = summarize(srt_file, n_sentences, language)
            total_time = time_regions(summary)
    else:
        while total_time > duration:
            n_sentences -= 1
            summary = summarize(srt_file, n_sentences, language)
            total_time = time_regions(summary)
    return summary 

# 需要导入模块: import pysrt [as 别名]
# 或者: from pysrt import open [as 别名]
def parseSrtAndSetItems(self):
        try:
            self.items = pysrt.open(self.filePath, encoding='utf8')
            return 0
        except:
            return 11