Dustin/jp_text_parsing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

subtitle parser can match webvtt and srt formats

Browse Source
This commit is contained in:
Nitsud Yarg 2026-05-17 22:02:36 -07:00
parent 69b07f3383
commit 99a109b130
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
subtitle_processor.py
View File

@ -63,6 +63,10 @@ def main():
notes_lines.append('##### ' + lines[i].strip() + " `" + lines[i+1].strip() + "`" + "\n") notes_lines.append('##### ' + lines[i].strip() + " `" + lines[i+1].strip() + "`" + "\n")
i+=2 i+=2
continue 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]): if has_japanese(lines[i]):
print(lines[i]) print(lines[i])
result = analyze(lines[i],vocab) result = analyze(lines[i],vocab)