64 lines
1.6 KiB
Python
64 lines
1.6 KiB
Python
|
|
def parse_vtt(file_path):
|
|
with open(file_path, 'r', encoding='utf-8') as file:
|
|
content = file.read()
|
|
|
|
# Split the content into lines
|
|
lines = content.strip().split('\n')
|
|
parsed_captions = []
|
|
|
|
# Skip the first line if it is the WebVTT header
|
|
if lines[0] == 'WEBVTT':
|
|
lines = lines[1:]
|
|
|
|
# Process each caption block
|
|
for i in range(len(lines)):
|
|
if '-->' in lines[i]: # This line contains the timing
|
|
time = lines[i].strip()
|
|
text = lines[i + 1].strip() if i + 1 < len(lines) else ''
|
|
parsed_captions.append({
|
|
'time': time,
|
|
'text': text
|
|
})
|
|
|
|
return parsed_captions
|
|
|
|
def remove_duplicates(subtitles):
|
|
no_dupes = list()
|
|
prev = subtitles[0]
|
|
# print(type(prev), ":", prev)
|
|
for caption in subtitles:
|
|
if prev["text"] != str() and caption["text"] != prev["text"]:
|
|
# print(prev)
|
|
no_dupes.append(prev)
|
|
prev = caption
|
|
return no_dupes
|
|
|
|
def export_to_vtt(subtitles, output_file_path):
|
|
with open(output_file_path, 'w', encoding='utf-8') as file:
|
|
# Write the WebVTT header
|
|
file.write("WEBVTT\n\n")
|
|
|
|
for subtitle in subtitles:
|
|
# Assuming subtitle has 'time' and 'text' keys
|
|
time = subtitle['time']
|
|
text = subtitle['text']
|
|
|
|
# Write the formatted subtitle
|
|
file.write(f"{time}\n{text}\n\n")
|
|
|
|
if __name__ == "__main__":
|
|
import sys
|
|
|
|
|
|
vtt_file_path = sys.argv[1]
|
|
print(vtt_file_path)
|
|
|
|
export_to_vtt(
|
|
remove_duplicates(
|
|
parse_vtt(vtt_file_path)
|
|
), "output.vtt"
|
|
)
|
|
|
|
|