Skip to content

Commit

Permalink
Merge pull request #204 from Cerberus98/new_domains_list
Browse files Browse the repository at this point in the history
Updates the corrector email list
  • Loading branch information
MattDietz authored Aug 22, 2018
2 parents 27f3d56 + ad65343 commit 28d7680
Showing 1 changed file with 82 additions and 78 deletions.
160 changes: 82 additions & 78 deletions flanker/addresslib/corrector.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,177 +30,191 @@ def suggest(word, cutoff=0.77):
return guess[0]
return word


MOST_COMMON_DOMAINS = [
# mailgun :)
'mailgun.net',
# big esps
# The Top 200 domains from 30mm open events gathered during the
# last 30 days prior to 8/22/2018
'126.com',
'163.com',
'account.tradeshift.com',
'aim.com',
'airwallex.com',
'alice.it',
'aol.co.uk',
'ameritech.net',
'anz.com',
'aol.com',
'apple.com',
'asu.edu',
'att.net',
'azet.sk',
'bain.com',
'bell.net',
'bellsouth.net',
'berkeley.edu',
'bigpond.com',
'bigpond.com.au',
'bigpond.net.au',
'bk.ru',
'bluewin.ch',
'blueyonder.co.uk',
'bol.com.br',
'btinternet.com',
'btopenworld.com',
'cableone.net',
'centrum.sk',
'centurylink.net',
'centurytel.net',
'cfl.rr.com',
'charter.com',
'charter.net',
'citi.com',
'colemanrg.com',
'columbia.edu',
'comcast.net',
'compass.com',
'cornell.edu',
'cox.net',
'cs.com',
'cpp.edu',
'cytonn.com',
'deloitte.com',
'det.nsw.edu.au',
'docomo.ne.jp',
'earthlink.net',
'email.com',
'email.cz',
'email.it',
'edumail.vic.gov.au',
'eim.ae',
'email.arizona.edu',
'embarqmail.com',
'emirates.net.ae',
'excite.com',
'fastwebnet.it',
'exploretrip.com',
'ext.uber.com',
'ezweb.ne.jp',
'free.fr',
'freemail.hu',
'freenet.de',
'frontier.com',
'frontiernet.net',
'fuse.net',
'g.austincc.edu',
'ge.com',
'gmail.com',
'gmx.at',
'gmx.ch',
'gmx.com',
'gmx.de',
'gmx.net',
'google.com',
'googlemail.com',
'gs.com',
'guest.booking.com',
'hanmail.net',
'home.nl',
'hotmail.be',
'hotmail.ca',
'hotmail.co.jp',
'hotmail.co.nz',
'hotmail.co.uk',
'hotmail.com',
'hotmail.com.ar',
'hotmail.com.au',
'hotmail.de',
'hotmail.es',
'hotmail.fr',
'hotmail.gr',
'hotmail.it',
'hotmail.nl',
'hotmail.no',
'hotmail.se',
'hughes.net',
'i.softbank.jp',
'icloud.com',
'iinet.net.au',
'inbox.lv',
'inbox.ru',
'interia.pl',
'indeedemail.com',
'internationalsos.com',
'internode.on.net',
'iprimus.com.au',
'jhu.edu',
'jtbap.com',
'juno.com',
'kw.com',
'laposte.net',
'libero.it',
'limetray.com',
'list.ru',
'live.be',
'live.ca',
'live.co.uk',
'live.com',
'live.com.ar',
'live.com.au',
'live.com.mx',
'live.de',
'live.dk',
'live.fr',
'live.it',
'live.nl',
'live.no',
'live.se',
'lynk.co.in',
'mac.com',
'mail.com',
'mail.ru',
'marketplace.amazon.com',
'marriott.com',
'mavs.uta.edu',
'mchsi.com',
'mckinsey.com',
'me.com',
'microsoft.com',
'mergermarket.com',
'mindspring.com',
'montaportal.nl',
'msn.com',
'msu.edu',
'naver.com',
'nc.rr.com',
'netscape.net',
'netspace.net.au',
'netzero.com',
'netzero.net',
'neuf.fr',
'nhs.net',
'ntlworld.com',
'o2.pl',
'online.no',
'optimum.net',
'optonline.net',
'optusnet.com.au',
'orange.fr',
'ostrovok.ru',
'ou.edu',
'outlook.com',
'outlook.com.au',
'outlook.de',
'outlook.es',
'outlook.fr',
'outlook.it',
'ozemail.com.au',
'pacbell.net',
'planet.nl',
'paisabazaar.com',
'pegipegi.com',
'prodigy.net',
'prodigy.net.mx',
'protonmail.com',
'ptd.net',
'pwc.com',
'q.com',
'qiniu.com',
'qq.com',
'rambler.ru',
'reagan.com',
'rediffmail.com',
'rev.com',
'roadrunner.com',
'rocketmail.com',
'rogers.com',
'rothschild.com',
'royallepage.ca',
'sasktel.net',
'savaari.com',
'sbcglobal.net',
'seznam.cz',
'sfr.fr',
'shaw.ca',
'sky.com',
'skynet.be',
'springspa.com',
'stanford.edu',
'student.sbccd.edu',
'suddenlink.net',
'swbell.net',
'sympatico.ca',
't-online.de',
'talktalk.net',
'telefonica.net',
'tampabay.rr.com',
'telenet.be',
'telfort.nl',
'telia.com',
'telus.net',
'telusplanet.net',
'tiscali.co.uk',
'tiscali.it',
'ukr.net',
'terra.com.br',
'tpg.com.au',
'twc.com',
'umich.edu',
'umn.edu',
'uol.com.br',
'usa.net',
'usc.edu',
'utexas.edu',
'uw.edu',
'vepl.com',
'verizon.net',
'videotron.ca',
'virgilio.it',
'virgin.net',
'virginmedia.com',
'vt.edu',
'wanadoo.fr',
'web.de',
'windowslive.com',
'westnet.com.au',
'wi.rr.com',
'windstream.net',
'wp.pl',
'xs4all.nl',
'xtra.co.nz',
'y7mail.com',
'ya.ru',
'yahoo.ca',
'yahoo.co.id',
'yahoo.co.in',
Expand All @@ -213,24 +227,14 @@ def suggest(word, cutoff=0.77):
'yahoo.com.br',
'yahoo.com.hk',
'yahoo.com.mx',
'yahoo.com.my',
'yahoo.com.ph',
'yahoo.com.sg',
'yahoo.com.tw',
'yahoo.de',
'yahoo.es',
'yahoo.fr',
'yahoo.gr',
'yahoo.ie',
'yahoo.in',
'yahoo.it',
'yahoo.no',
'yahoo.se',
'yandex.com',
'yandex.ru',
'ymail.com',
'ziggo.nl',
'zoominternet.net'
'ymail.com'
]

# domains that the corrector doesn't fix that we should fix
Expand Down

0 comments on commit 28d7680

Please sign in to comment.