Created
June 6, 2020 14:50
-
-
Save AJamesPhillips/3e841a058f5d6c802a8b63747db757a8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Takes text with the format: | |
# | |
# 00:05 | |
# Some subtitles | |
# 00:12 | |
# Some more text | |
# ... | |
# | |
# 61:20 | |
# More subtitle at 61 minutes, 20 seconds | |
# | |
# And groups it into `seconds_bucket` groups, for example: | |
# | |
# 00:05 | |
# Some subtitles Some more text | |
# ... | |
# | |
seconds_bucket = 60 | |
with open("file.txt", "r") as f: | |
text = f.read() | |
lines = text.split("\n") | |
lines_with_times = [] | |
def time_in_seconds(time): | |
[minutes, seconds] = time.split(":") | |
return int(minutes) * 60 + int(seconds) | |
def seconds_in_time(seconds): | |
seconds_remaining = seconds % 60 | |
minutes = int((seconds - seconds_remaining) / 60) | |
return "{}:{}".format(str(minutes).zfill(2), str(seconds_remaining).zfill(2)) | |
for (i, line) in enumerate(lines): | |
if (i % 2 == 0): | |
seconds = time_in_seconds(lines[i]) | |
lines_with_times.append((seconds, lines[i + 1])) | |
current_bucket = -1 | |
grouped_lines = [] | |
for line in lines_with_times: | |
if (line[0] > current_bucket): | |
current_bucket += seconds_bucket | |
grouped_lines.append([line[0], line[1]]) | |
else: | |
last = len(grouped_lines) - 1 | |
grouped_lines[last][1] += " " + line[1] | |
for group in grouped_lines: | |
print(seconds_in_time(group[0]) + "\n" + group[1]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment