(feature-extractor) Add mail.ru counter to non-adtech trackers

This commit is contained in:
Viktor Lofgren 2023-08-15 19:10:43 +02:00
parent df85468c01
commit d8073f0dde

View File

@ -23,8 +23,12 @@ public class FeatureExtractor {
private static final List<String> innocentTrackers = List.of(
"twitter.com",
"bing.com",
"msn.com");
private static final List<String> adtechTrackers = List.of("adform.net",
"msn.com",
"mail.ru/counter"
);
private static final List<String> adtechTrackers = List.of(
"publir.com",
"adform.net",
"connect.facebook",
"facebook.com/tr",
"absbygoogle.com",
@ -222,6 +226,12 @@ public class FeatureExtractor {
String scriptText = scriptTag.html();
if (scriptText.contains("_ga=") || scriptText.contains("ga('create'")) {
features.add(HtmlFeature.TRACKING);
}
if (scriptText.contains("_tmr")) {
features.add(HtmlFeature.TRACKING);
}
if (scriptText.contains("'pd.js'")) {
features.add(HtmlFeature.PARDOT);
}