subtitle parser can match webvtt and srt formats

2026-05-17 22:02:36 -07:00 · 2026-05-17 22:02:36 -07:00 · 99a109b130
commit 99a109b130
parent 69b07f3383
1 changed files with 4 additions and 0 deletions
--- a/subtitle_processor.py
+++ b/subtitle_processor.py
@ -63,6 +63,10 @@ def main():
            notes_lines.append('##### ' + lines[i].strip() + " `" + lines[i+1].strip() + "`" + "\n")
            i+=2
            continue
+        if re.fullmatch(r'(\d{2,}:)*\d{2,}:\d{2,}[,.]\d{3,}\s*-->\s*(\d{2,}:)*\d{2,}:\d{2,}[,.]\d{3,}' , lines[i].strip()):
+            notes_lines.append('##### ' " `" + lines[i].strip() + "`" + "\n")
+            i+=1
+            continue
        if has_japanese(lines[i]):
            print(lines[i])
            result = analyze(lines[i],vocab)