From b17a24c0474f2542662f9c570d9b902b5ae1e2ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Geoffrey=20=E2=80=9CFrogeye=E2=80=9D=20Preud=27homme?= Date: Tue, 12 Nov 2019 13:58:17 +0100 Subject: [PATCH] Added more trackers and their clients --- regexes.py | 15 +++- websites/adobe-experience-cloud_clients.list | 1 + websites/akamai_clients.list | 75 ++++++++++++++++ websites/at-internet_clients.list | 90 ++++++++++++++++++++ websites/criteo_clients.list | 82 ++++++++++++++++++ websites/keyade_clients.list | 20 +++++ websites/np6_clients.list | 20 +++++ 7 files changed, 299 insertions(+), 4 deletions(-) create mode 100644 websites/adobe-experience-cloud_clients.list create mode 100644 websites/akamai_clients.list create mode 100644 websites/at-internet_clients.list create mode 100644 websites/criteo_clients.list create mode 100644 websites/keyade_clients.list create mode 100644 websites/np6_clients.list diff --git a/regexes.py b/regexes.py index 11fff4b..0e48441 100644 --- a/regexes.py +++ b/regexes.py @@ -7,8 +7,15 @@ List of regex matching first-party trackers. # Syntax: https://docs.python.org/3/library/re.html#regular-expression-syntax REGEXES = [ - r'^.+\.eulerian\.net\.$', - r'^.+\.criteo\.com\.$', - r'^.+\.keyade\.com\.$', - r'^.+\.omtrdc\.net\.$', + r'^.+\.eulerian\.net\.$', # Eulerian + r'^.+\.criteo\.com\.$', # Criteo + r'^.+\.dnsdelegation\.io\.$', # Criteo + r'^.+\.keyade\.com\.$', # Keyade + r'^.+\.omtrdc\.net\.$', # Adobe Experience Cloud + r'^.+\.bp01\.net\.$', # NP6 + r'^.+\.ati-host\.net\.$', # Xiti (AT Internet) + r'^.+\.at-o\.net\.$', # Xiti (AT Internet) + r'^.+\.edgkey\.net\.$', # Edgekey (Akamai) + r'^.+\.akaimaiedge\.net\.$', # Edgekey (Akamai) + r'^.+\.storetail\.io\.$', # Storetail (Criteo) ] diff --git a/websites/adobe-experience-cloud_clients.list b/websites/adobe-experience-cloud_clients.list new file mode 100644 index 0000000..f5af315 --- /dev/null +++ b/websites/adobe-experience-cloud_clients.list @@ -0,0 +1 @@ +https://www.ubs.com/ diff --git a/websites/akamai_clients.list b/websites/akamai_clients.list new file mode 100644 index 0000000..069c028 --- /dev/null +++ b/websites/akamai_clients.list @@ -0,0 +1,75 @@ +http://ao.com/ +https://www.asus.com/ +http://www.absolut.com/ +http://www.adobe.com/ +http://www.afterbuzztv.com/ +http://www.airbnb.com/ +http://www.alliantcreditunion.org/ +http://www.ankama-games.com/ +http://www.attraqt.com/ +http://www.audi.com/ +http://www.autotrader.com/ +http://www.bangkokbank.com/ +http://www.banzai.it/ +http://www.bestbuy.com/ +http://www.bigfishgames.com/ +http://www.bostonscientific.com/ +http://www.radio-canada.ca/ +https://www.cashflows.com/ +http://www.concur.com/ +http://www.chinesecio.com/ +http://corporate.crownmedia.com/ +https://watch.dazn.com/ +http://www.disa.mil/ +https://www.douglas.de/ +http://www.ets.org/ +http://www.easy-forex.com/ +http://www.fiat.com/ +http://www.fidor.com/ +http://www.frankandoak.com/ +http://www.fubo.tv/ +https://corp.gree.net/ +https://www.gymgrossisten.com/ +http://www.halfpricedrapes.com/ +https://www.hotstar.com/ +https://www.iqiyi.com/ +http://www.iracing.com/ +http://www.mallgroup.com/ +https://www.investisdigital.com/ +https://www.linenchest.com/ +https://www.luisaviaroma.com/ +https://www.mcnc.org/ +http://www.mauijim.com/ +https://www.mediacorp.sg/ +http://www.cr.mufg.jp/ +http://www.nbcolympics.com/ +https://www.ndtv.com/ +http://www.nrcs.usda.gov/ +http://www.oshean.org/ +https://www.ocado.com/ +http://www.ottogroup.com/ +https://watch.dazn.com/ +http://www.philips.com/ +http://www.printplanet.de/ +http://www.rabobank.com/ +https://corp.roblox.com/ +http://www.sinet.com.kh/ +http://www.schneider.de/ +https://thewest.com.au/ +https://www.shopdirect.com/ +http://www.siemens.com/ +http://www.sky.it/ +https://www.sc.com/ +http://www.stylesha.re/ +http://www.tv2.dk/ +http://www.grammy.org/ +https://www.topcon.co.jp/ +http://www.usnews.com/ +http://www.ubisoft.com/ +http://www.unionbankph.com/ +http://www.urbn.com/ +http://www.waters.com/ +https://www.xero.com/ +https://www.esky.com/ +https://www.iheartmedia.com/ + diff --git a/websites/at-internet_clients.list b/websites/at-internet_clients.list new file mode 100644 index 0000000..23472b7 --- /dev/null +++ b/websites/at-internet_clients.list @@ -0,0 +1,90 @@ +https://www.rte.ie/ +https://www.bbc.com/ +https://www.saint-gobain.com/ +https://www.sbb.ch/ +http://www.rfi.fr/ +https://www.france24.com/ +https://www.mc-doualiya.com/ +https://www.francemediasmonde.com/ +https://www.kmmediagroup.co.uk/ +https://www.europages.fr/ +https://www.ovh.com/ +http://www.sa.areva.com/ +https://www.orano.group/ +https://www.evaluate.com/ +https://www.laposte.fr/ +https://www.colissimo.fr/ +https://www.nrjmobile.fr/ +https://www.parisaeroport.fr/ +https://www.michelin.fr/ +https://www.groupeseb.com/ +https://www.seb.fr/ +https://www.corkinternationalairporthotel.com/ +https://www.donedeal.ie/ +https://rmc.bfmtv.com/ +https://rmcsport.bfmtv.com/ +https://www.mma.fr/ +http://banquepopulaire.fr/ +https://www.printempsfrance.com/ +https://www.pagesjaunes.fr/ +https://www.nocibe.fr/ +https://e24.no/ +https://www.01net.com/ +https://www.europe1.fr/ +https://www.meilleurtaux.com/ +https://www.nexity.fr/ +https://www.bestwestern.com/content/ +https://www.allsuites-apparthotel.com/ +https://www.apec.fr/ +https://www.cadremploi.fr/ +https://www.eni.com/ +https://mappy.com/ +https://www.arte.tv/ +https://conseil-constitutionnel.fr/ +https://www.lcl.fr/ +https://www.axa.fr/ +https://www.huffpost.com/ +https://www.challenges.fr/ +https://www.netto.fr/ +https://www.boursorama-banque.com/ +https://www.marianne.net/ +https://www.mediapart.fr/ +https://www.tifco.com/ +https://www.thalys.com/ +https://schibsted.com/ +https://www.se.com/ +https://www.gouvernement.fr/ +https://www.afm-telethon.fr/ +https://www.pneus-online.fr/ +https://www.lepoint.fr/ +http://www.e-leclerc.com/ +https://www.logic-immo.com/ +https://www.longchamp.com/ +https://www.maaf.fr/ +https://www.futuroscope.com/ +https://www.infojobs.net/ +https://www.intermarche.com/ +https://www.supercasino.fr/ +https://www.chronopost.fr/ +https://www.cic.fr/ +https://www.courrierinternational.com/ +https://www.credit-agricole.fr/ +https://www.telekom.com/ +https://www.bfmtv.com/ +https://www.caisse-epargne.fr/ +https://www.calor.fr/ +https://www.groupebayard.com/fr/ +https://www.bayard-jeunesse.com/ +https://www.radiofrance.fr/ +https://www.liberation.fr/ +https://www.nrj.fr/ +https://www.lemonde.fr/ +https://www.societegenerale.fr/ +https://www.pole-emploi.fr/accueil/ +https://www.tf1.fr/ +https://www.leboncoin.fr/ +https://groupebpce.com/ +https://www.france.tv/ +https://www.total.com/ +http://www.lagardere.com/ +https://rakuten.com/ diff --git a/websites/criteo_clients.list b/websites/criteo_clients.list new file mode 100644 index 0000000..6130613 --- /dev/null +++ b/websites/criteo_clients.list @@ -0,0 +1,82 @@ +http://www.dholic.co.jp/ +https://materialesdefabrica.com/ +https://www.lecreuset.com/ +https://www.intersport.fr/ +https://www.feiradamadrugadasp.com.br/ +https://www.wetteronline.de/ +https://www.wolfandbadger.com/ +https://www.readers.com/ +https://www.fossil.com/ +https://www.gemo.fr/ +https://www.burda-forward.de/ +https://www.bakeca.it/ +https://www.sarenza.com/ +https://www.mytoys.com/ +https://tour2000.co.kr +https://theluxurycloset.com/ +https://www.lovebonito.com/ +https://www.bever.nl/ +https://www.shipt.com/ +https://www.petermanningnyc.com/ +https://www.fashionvalet.com/ +https://remixshop.com/ +https://lagirl.co.kr/ +https://www.avva.com.tr/ +https://www.stella.nl/ +https://www.maiutazas.hu/ +http://www.dynacraftwheels.com/ +https://www.itaka.pl/ +https://www.inveon.com.tr/ +https://www.dr.com.tr/ +http://www.lfmall.co.kr/ +https://www.beymen.com/ +https://www.reebok.com/ +https://www.mlmparts.com/ +https://www.flyin.com/ +https://www.garantibbva.com.tr/ +http://www.fiat.com.tr/ +https://warburtons.co.uk/ +http://www.shark.com/ +https://www.latam.com/ +https://agilone.com/ +https://www.clarks.co.uk/ +https://www.joom.com/ +https://www.adjust.com/ +https://www.tugo.com.vn/ +https://www.tatacliq.com/ +https://www.valmano.de/ +https://www.ab-inbev.com/ +https://www.sephora.com/ +https://www.sephora.fr/ +https://www.officedepot.com/ +http://www.officedepot.eu/ +https://www.officedepot.fr/ +https://www.journey.com.tr/ +https://group.jumia.com/ +https://www.jumia.com.ng/ +http://us.vibram.com/ +http://eu.vibram.com/ +https://sssports.com/ +https://www.theiconic.com.au/ +https://spiegel.media/ +https://www.halfpricedrapes.com/ +https://striderbikes.com/ +https://www.promod.fr/ +https://www.philips.com/ +https://www.hp.com/ +https://www.edmunds.com/ +https://www.kkfashion.vn/ +https://www.newlook.com/ +https://www.fragrancenet.com/ +https://www.microsoft.com/ +https://xbox.com/ +https://www.nykaa.com/ +https://www.cheapoair.com/ +https://www.diageo.com/ +https://trimfit.com/ +https://www.vax.co.uk/ +https://www.laredoute.fr/ +https://www.newlook.com/ +https://www.softsurroundings.com/ +https://www.ebay.fr/ + diff --git a/websites/keyade_clients.list b/websites/keyade_clients.list new file mode 100644 index 0000000..5cd4a1e --- /dev/null +++ b/websites/keyade_clients.list @@ -0,0 +1,20 @@ +https://www.allianz.fr/ +http://www.belambra.fr/ +https://www.macif.fr/ +https://www.butagaz.fr/ +http://www.cartier.fr/ +https://www.isilines.fr/ +http://www.jaeger-lecoultre.com/ +http://www.laredoute.fr/ +https://www.lesfurets.com/ +https://www.louvrehotels.com/ +http://www.mars.com/ +https://www.meetic.fr/ +https://www.nikon.fr/ +https://www.norauto.fr/ +https://www.groupe-psa.com/ +https://www.rueducommerce.fr/ +https://www.transavia.com/ +https://www.truffaut.com/ +https://www.uniqlo.com/ +https://www.vancleefarpels.com/ diff --git a/websites/np6_clients.list b/websites/np6_clients.list new file mode 100644 index 0000000..71f227f --- /dev/null +++ b/websites/np6_clients.list @@ -0,0 +1,20 @@ +https://www.harmonie-mutuelle.fr/ +https://www.henkel.fr/ +https://www.canalplus.com/ +http://www.casino.fr/ +https://www.alinea.com/ +https://www.enedis.fr/ +https://www.ubisoft.com/ +https://perfectstaycom.zendesk.com/ +https://www.perfectstay.com/ +https://www.bricodepot.fr/ +https://www.sfr.fr/ +http://www.prismamedia.com/ +https://www.odalys-vacances.com/ +https://www.macif.fr/ +https://www.cofinoga.fr/ +https://www.boursorama-banque.com/ +https://mabanque.bnpparibas/ +https://www.oui.sncf/ +https://www.younited-credit.com/ +