url normalization: strip utm_source

eserte · eserte · commit c992c5bcf7f3 · 2025-12-07T18:56:12.000+01:00
diff --git a/miscsrc/tk-bbbike-grep b/miscsrc/tk-bbbike-grep
@@ -416,6 +416,9 @@ sub url_normalizations {
     $url =~ s{(https://www.nd-aktuell.de/artikel/\d+\.).*}{$1};
     $url =~ s{(https://www.tagesspiegel.de/.*)\?.*}{$1};
     $url =~ s{(https://www.berlin.de/.*)\?ts=\d+\b}{$1};
+    # should be last
+    $url =~ s{([&?])utm_source=.*?(?=&|$)}{$1 eq '?' ? '?' : ''}e;
+    $url =~ s{\?$}{};
     $url;
 }
 

Original file line number	Diff line number	Diff line change
`@@ -416,6 +416,9 @@ sub url_normalizations {`
`416`	`416`	`$url =~ s{(https://www.nd-aktuell.de/artikel/\d+\.).*}{$1};`
`417`	`417`	`$url =~ s{(https://www.tagesspiegel.de/.)\?.}{$1};`
`418`	`418`	`$url =~ s{(https://www.berlin.de/.*)\?ts=\d+\b}{$1};`
	`419`	`+ # should be last`
	`420`	`+ $url =~ s{([&?])utm_source=.*?(?=&\|$)}{$1 eq '?' ? '?' : ''}e;`
	`421`	`+ $url =~ s{\?$}{};`
`419`	`422`	`$url;`
`420`	`423`	`}`
`421`	`424`