added legacy scripts as reference

2026-09-10 07:41:07 +00:00
parent 78e8a7decf
commit 51b878486f
2 changed files with 95 additions and 0 deletions
@@ -0,0 +1,67 @@
+import re
+import sys
+import os
+from datetime import timedelta
+
+def format_timestamp(timestamp):
+  hours, remainder = divmod(timestamp.total_seconds(), 3600)
+  minutes, seconds = divmod(remainder, 60)
+  milliseconds = timestamp.microseconds // 1000
+  return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d},{int(milliseconds):03d}"
+
+def lrc_to_srt(lrc_filename, srt_filename):
+  with open(lrc_filename, 'r', encoding='utf-8') as lrc_file:
+    lrc_content = lrc_file.readlines()
+
+  srt_content = []
+  subtitle_counter = 1
+  previous_end_time = None
+
+  for i, line in enumerate(lrc_content):
+    match = re.match(r'\[(\d{2}):(\d{2})\.(\d{2})\](.*)', line)
+    ## Explanation to the regex:
+    ## \[           (\d{2})             :       (\d{2})             \.    (\d{2})               \]        (.*)
+    ## bracket      minutes (2 digits)  colon   seconds (2 digits)  dot   millisecs (2 digits)  bracket   lyrical line (can be blank)
+    if match:
+      print(f'debug: matched line {line.strip()}')
+      start_minutes = int(match.group(1))
+      start_seconds = int(match.group(2))
+      start_milliseconds = int(match.group(3)) * 10
+      print(f'matched text: {match.group(4)}')
+
+      start_time = timedelta(minutes=start_minutes, seconds=start_seconds, milliseconds=start_milliseconds)
+      if len(srt_content) > 0:
+        # srt_content[-1] += f"{format_timestamp(start_time - timedelta(milliseconds=1))}\n"
+        srt_content[-1] += f"{format_timestamp(start_time)}\n"
+        srt_content.append(f"{subtitle_text}\n\n")
+
+      srt_content.append(f"{subtitle_counter}\n")
+      srt_content.append(f"{format_timestamp(start_time)} --> ")
+
+      subtitle_text = match.group(4).strip()
+      subtitle_counter += 1
+      previous_end_time = start_time
+
+  if previous_end_time is not None:
+    srt_content[-1] += f"{format_timestamp(previous_end_time)}\n"
+    srt_content.append(f"{subtitle_text}\n\n")
+    
+
+  with open(srt_filename, 'w', encoding='utf-8') as srt_file:
+    srt_file.writelines(srt_content)
+
+  print(f"Conversion from LRC to SRT completed. SRT file saved as '{srt_filename}'.")
+
+if __name__ == "__main__":
+  if not(len(sys.argv) == 3 or len(sys.argv) == 2):
+    print("Usage: python lrc2srt.py <input_lrc_file> <output_srt_file>")
+    print("or: python lrc2srt.py <input_lrc_file>")
+    print("If no output file name is supplied, the input file name will be used by default.")
+  else:
+    lrc_filename = sys.argv[1]
+    if len(sys.argv) == 3:
+      srt_filename = sys.argv[2]
+    else:
+      raw_filename, ext = os.path.splitext(lrc_filename)
+      srt_filename = raw_filename + '.srt'  
+    lrc_to_srt(lrc_filename, srt_filename)