d

cmdlet/get_url.py

@@ -7,7 +7,7 @@ from typing import Any, Dict, List, Sequence, Optional, Set, Tuple
 import sys
 import re
 from fnmatch import fnmatch
-from urllib.parse import urlparse
+from urllib.parse import urlparse, parse_qsl, urlencode, urlunparse
 from . import _shared as sh
 
 Cmdlet, SharedArgs, parse_cmdlet_args, get_field, normalize_hash = (
@@ -67,6 +67,35 @@ class Get_Url(Cmdlet):
         """
         url = str(url or "").strip()
 
+        # Strip fragment (e.g., #t=10) before matching
+        url = url.split("#", 1)[0]
+
+        # Strip common time/tracking query params for matching
+        try:
+            parsed = urlparse(url)
+        except Exception:
+            parsed = None
+
+        if parsed is not None and parsed.query:
+            time_keys = {"t", "start", "time_continue", "timestamp", "time", "begin"}
+            tracking_prefixes = ("utm_",)
+            try:
+                pairs = parse_qsl(parsed.query, keep_blank_values=True)
+                filtered = []
+                for key, val in pairs:
+                    key_norm = str(key or "").lower()
+                    if key_norm in time_keys:
+                        continue
+                    if key_norm.startswith(tracking_prefixes):
+                        continue
+                    filtered.append((key, val))
+                if filtered:
+                    url = urlunparse(parsed._replace(query=urlencode(filtered, doseq=True)))
+                else:
+                    url = urlunparse(parsed._replace(query=""))
+            except Exception:
+                pass
+
         # Remove protocol (http://, https://, ftp://, etc.)
         url = re.sub(r"^[a-z][a-z0-9+.-]*://", "", url, flags=re.IGNORECASE)