vault backup: 2025-12-22 12:22:20

wip/download-subs.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+
+import subprocess
+import sys
+import os
+import glob
+
+def get_clipboard():
+    result = subprocess.run(['pbpaste'], capture_output=True, text=True)
+    return result.stdout.strip()
+
+def set_clipboard(text):
+    subprocess.run(['pbcopy'], input=text, text=True)
+
+def get_url_from_dialog():
+    applescript = '''
+    display dialog "Enter YouTube URL:" default answer "" with title "Download Swedish Subtitles" buttons {"Cancel", "OK"} default button "OK"
+    set userInput to text returned of result
+    return userInput
+    '''
+    try:
+        result = subprocess.run(['osascript', '-e', applescript], capture_output=True, text=True, check=True)
+        return result.stdout.strip()
+    except subprocess.CalledProcessError:
+        return None
+
+def clean_subtitles(srt_content):
+    lines = srt_content.strip().split('\n')
+    text_lines = []
+    seen_lines = set()
+
+    for line in lines:
+        line = line.strip()
+        if not line or line.isdigit() or '-->' in line:
+            continue
+        if line in seen_lines:
+            continue
+        seen_lines.add(line)
+        text_lines.append(line)
+
+    return ' '.join(text_lines)
+
+def download_subtitles(url):
+    cmd = [
+        'yt-dlp',
+        '--write-auto-sub',
+        '--sub-lang', 'sv',
+        '--skip-download',
+        '--convert-subs', 'srt',
+        '-o', '%(id)s.%(ext)s',
+        url
+    ]
+
+    subprocess.run(cmd, capture_output=True, text=True, check=True)
+
+    srt_files = glob.glob('*.sv.srt')
+
+    if srt_files:
+        subtitle_file = srt_files[0]
+        with open(subtitle_file, 'r', encoding='utf-8') as f:
+            raw_content = f.read()
+            cleaned_content = clean_subtitles(raw_content)
+        os.remove(subtitle_file)
+        return cleaned_content
+
+    sys.exit(1)
+
+if __name__ == '__main__':
+    url = get_clipboard()
+
+    if not url or 'youtube.com' not in url and 'youtu.be' not in url:
+        url = get_url_from_dialog()
+        if not url:
+            sys.exit(1)
+
+    subtitles = download_subtitles(url)
+    set_clipboard(subtitles)
+
+
+