gman 4.5.0 → 4.5.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (5) hide show
  1. checksums.yaml +4 -4
  2. data/config/domains.txt +177 -29
  3. data/gman.gemspec +2 -1
  4. data/script/vendor-se +54 -0
  5. metadata +17 -2
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: a172d1b966cc4024dbedfe36a23bc8b3e6719ed2
4
- data.tar.gz: 7149f379f8c5a2db46f2f7835c060bad855d864b
3
+ metadata.gz: 6c04cf1cc8a034c1216ccfd9df50871b7902bded
4
+ data.tar.gz: 879c362206dc25fcf0a81d1ab59dae48c1a7f409
5
5
  SHA512:
6
- metadata.gz: efe3d26459c71897a6862807ced317f1b52d865e57bd732344f494ab45eba76522636c3c3013adfc94a383a9c9ae1e2aed426bd08ecacd8d2ff5c9437109d955
7
- data.tar.gz: e8a51ae511157081d9bc0a8344f7af466e082ce54123e6b49c06f5d8d6db2a1fb301ea07b38413ab140c27531c2ad20a75d7ef4e7bec2dcb8a20401052f48b31
6
+ metadata.gz: 4b2ea15e51636ff031545605038d3d3b2fab2492c5d6faa14708a98dd1523afc54eab36d65104215fdcfd04ec181829850f4c9cdccc6baa93727cc06a90507ac
7
+ data.tar.gz: f75fdd572e23edaeaa035f0bbeaf3015efe789c37c3de42087f909a94119a53e7bbd2e149d1a1d846d1beb53e757e1bc0009483528dfa0cae9dfc44cf5be1525
data/config/domains.txt CHANGED
@@ -93,7 +93,6 @@ bromont.com
93
93
  brooks.ca
94
94
  brownsburgchatham.ca
95
95
  buchananvillage.zxq.net
96
- buffalonarrows.net
97
96
  burksfalls.net
98
97
  burnaby.ca
99
98
  burnsticklakesummervillage.ca
@@ -164,7 +163,6 @@ city.kawarthalakes.on.ca
164
163
  city.kenora.on.ca
165
164
  city.kimberley.bc.ca
166
165
  city.langley.bc.ca
167
- city.melville.sk.ca
168
166
  city.mississauga.on.ca
169
167
  city.owen-sound.on.ca
170
168
  city.peterborough.on.ca
@@ -259,7 +257,6 @@ dinosaurvalley.com
259
257
  discoverkl.ca
260
258
  discovermiddleton.ca
261
259
  discoverminnedosa.com
262
- discoverstlawrence.com
263
260
  discoverwinnipegosis.com
264
261
  district.kent.bc.ca
265
262
  district.mackenzie.bc.ca
@@ -584,7 +581,6 @@ morinville.ca
584
581
  morristurnberry.ca
585
582
  mountainviewcounty.com
586
583
  mountpearl.ca
587
- mountstewartpei.ca
588
584
  mrcabitibi.qc.ca
589
585
  msjb.qc.ca
590
586
  munargyle.com
@@ -610,7 +606,6 @@ municipalitehopetown.ca
610
606
  municipaliteremigny.qc.ca
611
607
  municipalitesaintsulpice.com
612
608
  municipality.frontenacislands.on.ca
613
- municipality.killarney.on.ca
614
609
  municipalityofmcdougall.com
615
610
  municipalityofshelburne.ca
616
611
  muniles.ca
@@ -1048,7 +1043,6 @@ town.newmarket.on.ca
1048
1043
  town.outlook.sk.ca
1049
1044
  town.oxford.ns.ca
1050
1045
  town.parrsboro.ns.ca
1051
- town.penetanguishene.on.ca
1052
1046
  town.perth.on.ca
1053
1047
  town.petrolia.on.ca
1054
1048
  town.portmcneill.bc.ca
@@ -1183,7 +1177,6 @@ tudorandcashel.com
1183
1177
  tumblerridge.ca
1184
1178
  turnervalley.ca
1185
1179
  twp.beckwith.on.ca
1186
- twp.puslinch.on.ca
1187
1180
  twp.seguin.on.ca
1188
1181
  twp.southwold.on.ca
1189
1182
  twp.stclair.on.ca
@@ -1816,7 +1809,6 @@ stadt-werther.de
1816
1809
  stadt-wetter.de
1817
1810
  stadt-willich.de
1818
1811
  stadt-zuelpich.de
1819
- stadt.sundern.de
1820
1812
  stadtlohn.de
1821
1813
  stadtverwaltung-bornheim.de
1822
1814
  staedteregion-aachen.de
@@ -1995,6 +1987,7 @@ gov.sa
1995
1987
  gov.sb
1996
1988
  gov.sc
1997
1989
  gov.sd
1990
+ gov.se
1998
1991
  gov.sg
1999
1992
  gov.sh
2000
1993
  gov.sl
@@ -2016,6 +2009,7 @@ gov.vn
2016
2009
  gov.ws
2017
2010
  gov.za
2018
2011
  government.bg
2012
+ government.se
2019
2013
  govt.nz
2020
2014
  gub.uy
2021
2015
  lg.jp
@@ -2077,6 +2071,180 @@ mod.uk
2077
2071
  // non-us sub-divisions
2078
2072
  ega.or.th
2079
2073
 
2074
+ // Swedish Administrative Authorities
2075
+ kammarkollegiet.se
2076
+ arn.se
2077
+ arbetsformedlingen.se
2078
+ arbetsgivarverket.se
2079
+ av.se
2080
+ arvsfonden.se
2081
+ bo.se
2082
+ bfn.se
2083
+ bolagsverket.se
2084
+ boverket.se
2085
+ bra.se
2086
+ brottsoffermyndigheten.se
2087
+ epn.se
2088
+ csn.se
2089
+ datainspektionen.se
2090
+ do.se
2091
+ domstol.se
2092
+ ehalsomyndigheten.se
2093
+ ekobrottsmyndigheten.se
2094
+ esv.se
2095
+ elegnamnden.se
2096
+ elsakerhetsverket.se
2097
+ energimarknadsinspektionen.se
2098
+ ersattningsnamnden.se
2099
+ ekn.se
2100
+ fmi.se
2101
+ fi.se
2102
+ finanspolitiskaradet.se
2103
+ folkebernadotteacademy.se
2104
+ folkhalsomyndigheten.se
2105
+ forskarskattenamnden.se
2106
+ formas.se
2107
+ fas.se
2108
+ fortv.se
2109
+ levandehistoria.se
2110
+ fmv.se
2111
+ fra.se
2112
+ fxm.se
2113
+ fhs.se
2114
+ forsvarsmakten.se
2115
+ undom.se
2116
+ forsakringskassan.se
2117
+ genteknik.se
2118
+ gih.se
2119
+ harpsund.se
2120
+ havochvatten.se
2121
+ hsan.se
2122
+ ilo.org
2123
+ iaf.se
2124
+ inspsf.se
2125
+ isp.se
2126
+ ifau.se
2127
+ irf.se
2128
+ sofi.se
2129
+ justitiekanslern.se
2130
+ kemi.se
2131
+ kommers.se
2132
+ konj.se
2133
+ konkurrensverket.se
2134
+ konstnarsnamnden.se
2135
+ konsumentverket.se
2136
+ kriminalvarden.se
2137
+ kronofogden.se
2138
+ kb.se
2139
+ kkh.se
2140
+ kmh.se
2141
+ kustbevakningen.se
2142
+ karnavfallsfonden.se
2143
+ lagradet.se
2144
+ lantmateriet.se
2145
+ lsh.se
2146
+ slv.se
2147
+ lotteriinspektionen.se
2148
+ lakemedelsverket.se
2149
+ lansstyrelsen.se
2150
+ y.lst.se
2151
+ mi.se
2152
+ migrationsverket.se
2153
+ modernamuseet.se
2154
+ handisam.se
2155
+ mia.eu
2156
+ kulturanalys.se
2157
+ radioochtv.se
2158
+ msb.se
2159
+ mtm.se
2160
+ tillvaxtanalys.se
2161
+ ungdomsstyrelsen.se
2162
+ vardanalys.se
2163
+ yhmyndigheten.se
2164
+ nationalmuseum.se
2165
+ nrm.se
2166
+ naturvardsverket.se
2167
+ nfh.se
2168
+ sst.a.se
2169
+ namndenmotdiskriminering.se
2170
+ prv.se
2171
+ pensionsmyndigheten.se
2172
+ polar.se
2173
+ polisen.se
2174
+ pts.se
2175
+ presstodsnamnden.se
2176
+ regeringen.se
2177
+ revisorsnamnden.se
2178
+ raa.se
2179
+ riksarkivet.se
2180
+ riksgalden.se
2181
+ riksutstallningar.se
2182
+ rymdstyrelsen.se
2183
+ rattshjalp.se
2184
+ rmv.se
2185
+ sameskolstyrelsen.se
2186
+ sametinget.se
2187
+ sida.se
2188
+ skatterattsnamnden.se
2189
+ skatteverket.se
2190
+ svo.se
2191
+ skolfi.se
2192
+ overklagandenamnden.se
2193
+ socialstyrelsen.se
2194
+ spsm.se
2195
+ statensansvarsnamnd.se
2196
+ sbu.se
2197
+ arkitekturmuseet.se
2198
+ energimyndigheten.se
2199
+ sfv.se
2200
+ sfhm.se
2201
+ swedgeo.se
2202
+ havkom.se
2203
+ historiska.se
2204
+ siun.se
2205
+ stat-inst.se
2206
+ sjv.se
2207
+ statenskonstrad.se
2208
+ kulturradet.se
2209
+ maritima.se
2210
+ statensmedierad.se
2211
+ smvk.se
2212
+ smus.se
2213
+ statenssc.se
2214
+ skolinspektionen.se
2215
+ skolverket.se
2216
+ spv.se
2217
+ va-namnden.se
2218
+ sva.se
2219
+ vti.se
2220
+ scb.se
2221
+ statskontoret.se
2222
+ uniarts.se
2223
+ stralsakerhetsmyndigheten.se
2224
+ swedac.se
2225
+ esf.se
2226
+ si.se
2227
+ sieps.se
2228
+ svff.se
2229
+ sgu.se
2230
+ smhi.se
2231
+ sakint.se
2232
+ sakerhetspolisen.se
2233
+ tlv.se
2234
+ tillvaxtverket.se
2235
+ foi.se
2236
+ pliktverket.se
2237
+ trafa.se
2238
+ trafikverket.se
2239
+ transportstyrelsen.se
2240
+ tullverket.se
2241
+ val.se
2242
+ vinnova.se
2243
+ vr.se
2244
+ aklagare.se
2245
+ onh.se
2246
+ oks.se
2247
+
2080
2248
  // Swiss Cantons (Federal States)
2081
2249
  ag.ch
2082
2250
  ai.ch
@@ -2087,6 +2255,7 @@ bs.ch
2087
2255
  fr.ch
2088
2256
  ge.ch
2089
2257
  gl.ch
2258
+ gr.ch
2090
2259
  ju.ch
2091
2260
  lu.ch
2092
2261
  ne.ch
@@ -2987,7 +3156,6 @@ norfolkct.org
2987
3156
  norwalkct.org
2988
3157
  norwichct.org
2989
3158
  oldsaybrookct.org
2990
- oxford-ct.com
2991
3159
  plainfieldct.org
2992
3160
  plainvillect.com
2993
3161
  plymouthct.us
@@ -3492,7 +3660,6 @@ libertycountyga.com
3492
3660
  lowndescounty.com
3493
3661
  madisonco.us
3494
3662
  madisonga.com
3495
- manchester-ga.com
3496
3663
  metter-candler.com
3497
3664
  middlegacfc.com
3498
3665
  milledgevillega.us
@@ -4558,7 +4725,6 @@ townofberwick.org
4558
4725
  townofblanchard.us
4559
4726
  townofchatham.org
4560
4727
  townoffranklinton.com
4561
- townofhornbeck.com
4562
4728
  townoflivingston.com
4563
4729
  townoflockport.com
4564
4730
  townofwelsh.com
@@ -5119,10 +5285,8 @@ harrison-township.org
5119
5285
  hartlandtwp.com
5120
5286
  hazelpark.org
5121
5287
  hollytownship.org
5122
- homermich.org
5123
5288
  homertownship.org
5124
5289
  houghtoncounty.net
5125
- howardtownship.net
5126
5290
  howardtwp.org
5127
5291
  hsofmich.org
5128
5292
  hudsonville.org
@@ -5593,7 +5757,6 @@ boonslick.org
5593
5757
  boonville-mo.org
5594
5758
  brentwoodmo.org
5595
5759
  bridgetonmo.com
5596
- buffalomissouri.us
5597
5760
  byrnesmill.org
5598
5761
  cabool.org
5599
5762
  camdentoncity.com
@@ -6284,7 +6447,6 @@ ncsecc.org
6284
6447
  ncsicklecellprogram.org
6285
6448
  ncsip.org
6286
6449
  ncsitesearch.com
6287
- ncstars.org
6288
6450
  ncstatefair.org
6289
6451
  ncstatesurplus.com
6290
6452
  ncstormwater.org
@@ -6494,7 +6656,6 @@ lidgerwoodnd.com
6494
6656
  lintonnd.org
6495
6657
  lisbonnd.com
6496
6658
  maddocknd.com
6497
- makotind.com
6498
6659
  mapletonnd.com
6499
6660
  marmarth.org
6500
6661
  maxnd.com
@@ -6680,7 +6841,6 @@ hillsboroughcountynh.org
6680
6841
  hinsdale.govoffice.com
6681
6842
  hollis.nh.us
6682
6843
  hooksett.org
6683
- jacksonvillage.net
6684
6844
  kingstonnh.org
6685
6845
  lancasternh.org
6686
6846
  landaffnh.org
@@ -7233,7 +7393,6 @@ wanaqueborough.com
7233
7393
  wantagetwp.com
7234
7394
  warrennj.org
7235
7395
  washington-twp-warren.org
7236
- washington-twp.org
7237
7396
  washingtonboro-nj.org
7238
7397
  washtwpmorris.org
7239
7398
  watchungnj.com
@@ -7398,7 +7557,6 @@ keetoowahcherokee.org
7398
7557
  kictribe.org
7399
7558
  klamathtribes.org
7400
7559
  kniktribalcouncil.org
7401
- koasekabenaki.org
7402
7560
  kootenai.org
7403
7561
  kotzebueira.org
7404
7562
  kumeyaay.info
@@ -7433,7 +7591,6 @@ nc-cherokee.com
7433
7591
  nezperce.org
7434
7592
  nihb.org
7435
7593
  nooksackindiantribe.org
7436
- northernarapaho.com
7437
7594
  northforkrancheria.com
7438
7595
  npaihb.org
7439
7596
  nveyak.com
@@ -7461,7 +7618,6 @@ quileutenation.org
7461
7618
  quinaultindiannation.com
7462
7619
  redding-rancheria.com
7463
7620
  robinsonrancheria.org
7464
- rumseyrancheria.org
7465
7621
  sagchip.org
7466
7622
  santaynezchumash.org
7467
7623
  santeedakota.org
@@ -7607,7 +7763,6 @@ cattco.org
7607
7763
  cayuga-heights.ny.us
7608
7764
  cayugacounty.us
7609
7765
  cdrpc.org
7610
- cfc-nyc.org
7611
7766
  chathamnewyork.us
7612
7767
  chautauqua-ny.com
7613
7768
  chemungcounty.com
@@ -8155,7 +8310,6 @@ victorny.org
8155
8310
  village.boonville.ny.us
8156
8311
  village.clinton.ny.us
8157
8312
  village.croton-on-hudson.ny.us
8158
- village.fairport.ny.us
8159
8313
  village.herkimer.ny.us
8160
8314
  village.holland-patent.ny.us
8161
8315
  village.mamaroneck.ny.us
@@ -8532,7 +8686,6 @@ vanwert.org
8532
8686
  vanwertcounty.org
8533
8687
  versaillesohio.cc
8534
8688
  villageofcoldwater.com
8535
- villageofjohnstown.org
8536
8689
  villageofnewalbany.org
8537
8690
  villageofottoville.org
8538
8691
  villageofseville.org
@@ -9320,7 +9473,6 @@ cfcofthecsra.org
9320
9473
  chapinsc.com
9321
9474
  charlestoncounty.org
9322
9475
  cheraw.com
9323
- chesnee.net
9324
9476
  chesterfield-sc.com
9325
9477
  chestersc.org
9326
9478
  cityofandersonsc.com
@@ -10326,7 +10478,6 @@ lincolnvermont.org
10326
10478
  londonderryvt.org
10327
10479
  ludlow.vt.us
10328
10480
  lyndonvt.org
10329
- marlboro.vt.us
10330
10481
  mendonvt.org
10331
10482
  middlesexvermont.org
10332
10483
  milton.govoffice2.com
@@ -10564,7 +10715,6 @@ republicwa.org
10564
10715
  royalcitywa.org
10565
10716
  rustonwa.org
10566
10717
  sanjuanco.com
10567
- sirti.org
10568
10718
  skagitcounty.net
10569
10719
  skamaniacounty.org
10570
10720
  skokomish.org
@@ -10858,7 +11008,6 @@ townofmerton.com
10858
11008
  townofminong.us
10859
11009
  townofmorrison.org
10860
11010
  townofmtpleasantwi.com
10861
- townofmukwonago.com
10862
11011
  townofmukwonago.us
10863
11012
  townofnavarino.com
10864
11013
  townofnorway.org
@@ -10926,7 +11075,6 @@ villageofmazomanie.com
10926
11075
  villageofmerton.com
10927
11076
  villageofmukwonago.com
10928
11077
  villageofneosho.org
10929
- villageofpewaukeewi.cbo2.com
10930
11078
  villageofpewaukeewi.us
10931
11079
  villageofpulaski.org
10932
11080
  villageofsharon.com
data/gman.gemspec CHANGED
@@ -2,7 +2,7 @@ Gem::Specification.new do |s|
2
2
  s.name = "gman"
3
3
  s.summary = "Check if a given domain or email address belong to a governemnt entity"
4
4
  s.description = "A ruby gem to check if the owner of a given email address is working for THE MAN."
5
- s.version = '4.5.0'
5
+ s.version = '4.5.1'
6
6
  s.authors = ["Ben Balter"]
7
7
  s.email = "ben.balter@github.com"
8
8
  s.homepage = "https://github.com/benbalter/gman"
@@ -25,5 +25,6 @@ Gem::Specification.new do |s|
25
25
  s.add_development_dependency( "bundler" )
26
26
  s.add_development_dependency( "pry" )
27
27
  s.add_development_dependency( "parallel" )
28
+ s.add_development_dependency( "mechanize" )
28
29
 
29
30
  end
data/script/vendor-se ADDED
@@ -0,0 +1,54 @@
1
+ #! /usr/bin/env ruby
2
+
3
+ require 'mechanize'
4
+ require 'csv'
5
+ require 'gman'
6
+ require 'swot'
7
+ require './lib/gman'
8
+ require './lib/gman/parser'
9
+
10
+ url = "http://www.myndighetsregistret.scb.se/Myndighet.aspx"
11
+ agent = Mechanize.new
12
+ page = agent.get(url)
13
+ form = page.form("form1")
14
+ form.radiobuttons.find { |r| r.value = "Textfil" }.check
15
+ submit_button = form.buttons.find { |b| b.type == "submit" }
16
+ response = agent.submit(form, submit_button)
17
+
18
+ domains = []
19
+ rows = CSV.parse(response.content, :headers => true, :col_sep => "\t")
20
+
21
+ puts "Starting with #{rows.count} domains..."
22
+
23
+ rows.each do |row|
24
+ next if Swot.valid?(row["Webbadress"]) # Filter out Swot'd domains
25
+ next if row["Namn"] =~ /UNIVERSITET/ # Filter out domains that are clearly edu
26
+ domains.push Gman.new(row["Webbadress"]).domain.to_s.gsub(/^www\./,"")
27
+ end
28
+
29
+ domains.reject! { |domain| domain.empty? }
30
+ domains.compact!
31
+ domains.uniq!
32
+ domains.select! { |domain| PublicSuffix.valid?(".#{domain}") }
33
+
34
+ puts "Ended up with #{domains.count} domains."
35
+
36
+ current = Gman::Parser.file_to_array( Gman::list_path )
37
+ current_hash = Gman::Parser.array_to_hash(current)
38
+
39
+ current_hash["Swedish Administrative Authorities"] = domains
40
+ current_hash = current_hash.sort_by { |group, domains| group.downcase }
41
+
42
+ # PublicSuffix Formatted Output
43
+ current_group = ""
44
+ output = ""
45
+ current_hash.each do |group, domains|
46
+ if group != current_group
47
+ output << "\n\n" unless current_group.empty? # first entry
48
+ output << "// #{group}\n"
49
+ current_group = group
50
+ end
51
+ output << domains.join("\n")
52
+ end
53
+
54
+ File.open(Gman.list_path, "w") { |file| file.write output }
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: gman
3
3
  version: !ruby/object:Gem::Version
4
- version: 4.5.0
4
+ version: 4.5.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ben Balter
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2015-01-30 00:00:00.000000000 Z
11
+ date: 2015-03-10 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: swot
@@ -150,6 +150,20 @@ dependencies:
150
150
  - - ">="
151
151
  - !ruby/object:Gem::Version
152
152
  version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: mechanize
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - ">="
158
+ - !ruby/object:Gem::Version
159
+ version: '0'
160
+ type: :development
161
+ prerelease: false
162
+ version_requirements: !ruby/object:Gem::Requirement
163
+ requirements:
164
+ - - ">="
165
+ - !ruby/object:Gem::Version
166
+ version: '0'
153
167
  description: A ruby gem to check if the owner of a given email address is working
154
168
  for THE MAN.
155
169
  email: ben.balter@github.com
@@ -187,6 +201,7 @@ files:
187
201
  - script/state-domains
188
202
  - script/vendor-de
189
203
  - script/vendor-gov-list
204
+ - script/vendor-se
190
205
  - script/vendor-us
191
206
  - test/helper.rb
192
207
  - test/obama.txt