From 9368061b747758c73b10cd6b8c6821d027d99119 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ABl=20=27Kubat=27=20MARTIN?= <mael.martin31@gmail.com> Date: Sun, 11 Aug 2019 12:06:57 +0200 Subject: [PATCH] Adding a simple parser to get the timed text from an ass file --- .gitignore | 1 + karaUtils.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) create mode 100755 karaUtils.py diff --git a/.gitignore b/.gitignore index cd9449a..91d19bc 100644 --- a/.gitignore +++ b/.gitignore @@ -3,3 +3,4 @@ !README.md !extractWav.sh !extractAss.sh +!karaUtils.py diff --git a/karaUtils.py b/karaUtils.py new file mode 100755 index 0000000..36dbd9f --- /dev/null +++ b/karaUtils.py @@ -0,0 +1,28 @@ +#!/usr/bin/env python3 +import re +import sys + +try: + FILE = sys.argv[1] +except IndexError: + print("usage : %s inputFile.py" % sys.argv[0]) + +with open(FILE, 'r') as f: + CONTENT = f.read() + +LINES_KARA = re.compile(r"Comment:.*(\d+:\d{2}:\d{2}.\d{2}),(\d+:\d{2}:\d{2}.\d{2}),.*,karaoke,(.*)\n"); +print(LINES_KARA) + +LINES = { + 'start': set(), + 'end': set(), + 'text': set() +} + +for line in LINES_KARA.findall(CONTENT): + print(line) + LINES['start'] = line[0] + LINES['end'] = line[1] + LINES['text'] = line[2] + +print(LINES) -- GitLab