svg-parse

svg-parse.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+"""
+svg_extract.py  –  dump every title + id pair found in an SVG file
+usage:  python3 svg_extract.py input.svg [> pairs.txt]
+"""
+
+import sys, re, html
+
+def main():
+    if len(sys.argv) != 2:
+        sys.exit("Usage: python3 svg_extract.py file.svg")
+
+    with open(sys.argv[1], encoding='utf-8') as f:
+        data = f.read()
+
+    # fast & simple regex: captures id and title in any order
+    pattern = re.compile(
+        r'<[^>]*?\b(id=["\'](?P<id>[^"\']+)["\'])[^>]*?\b(title=["\'](?P<title>[^"\']+)["\'])'
+        r'|'
+        r'<[^>]*?\b(title=["\'](?P<title2>[^"\']+)["\'])[^>]*?\b(id=["\'](?P<id2>[^"\']+)["\'])',
+        re.I
+    )
+
+    seen = set()
+    for m in pattern.finditer(data):
+        id_val   = html.unescape(m.group('id')   or m.group('id2'))
+        title_val = html.unescape(m.group('title') or m.group('title2'))
+        if (id_val, title_val) not in seen:       # avoid duplicates
+            seen.add((id_val, title_val))
+            print(f"{title_val}\t{id_val}")
+
+if __name__ == '__main__':
+    main()