population_externallinks
table for W and WP:M pages# basic defaults, including study dates, common SQL exclusions and parquet files for anonymized data
%run -i 'data-defaults.py'
# show lots of data
pd.options.display.max_rows=1000
# parse hostnames from links
# includes extraction for web.archive.org links
parse_host = """
PARSE_URL(REGEXP_REPLACE(LOWER({}),'^https?://web.archive.org/web/[^/]+/',''),'HOST')
"""
parse_host_from_el_to = parse_host.format('el_to')
parse_host_from_link_url = parse_host.format('link_url')
# Summary counts of top level domains
# limited to W pages with external links
# limited to 10000 or more links
w_tld_query = """
SELECT
REGEXP_EXTRACT({},'(\.[^\.]+)$',1) AS tld,
COUNT(distinct el_from, el_to) AS num_links
FROM ryanmax.population_externallinks
WHERE
el_from IN (SELECT page_id FROM ryanmax.population_w_pages_with_extlinks)
GROUP BY tld
ORDER BY num_links DESC
"""
w_tld = spark.sql(w_tld_query.format(parse_host_from_el_to))
w_tld_pda = w_tld.toPandas()
df_filtered = w_tld_pda.query('num_links>10000').copy()
df_filtered
tld | num_links | |
---|---|---|
0 | .com | 23883415 |
1 | .org | 14362804 |
2 | .gov | 4242619 |
3 | .uk | 3379001 |
4 | .net | 1749237 |
5 | .edu | 1544413 |
6 | .au | 1235596 |
7 | .fr | 996717 |
8 | .ca | 725635 |
9 | .de | 568513 |
10 | .info | 498609 |
11 | .jp | 454646 |
12 | .in | 328948 |
13 | .us | 289545 |
14 | .nz | 282507 |
15 | .it | 278292 |
16 | .ru | 263225 |
17 | .is | 243465 |
18 | .cz | 239175 |
19 | .nl | 230645 |
20 | .ch | 220589 |
21 | .no | 215629 |
22 | .es | 203148 |
23 | .ie | 201124 |
24 | .se | 187715 |
25 | .mil | 183311 |
26 | .pl | 174611 |
27 | .eu | 165142 |
28 | .ir | 158233 |
29 | .br | 131192 |
30 | .cn | 111787 |
31 | .be | 111576 |
32 | .kr | 108656 |
33 | .za | 106296 |
34 | .fi | 99709 |
35 | .dk | 96898 |
36 | .tv | 92665 |
37 | .ph | 85902 |
38 | .mx | 83582 |
39 | .ro | 82169 |
40 | .at | 78247 |
41 | .gr | 76477 |
42 | .int | 75565 |
43 | .pk | 71331 |
44 | .il | 69635 |
45 | .my | 66949 |
46 | .pt | 66362 |
47 | .tr | 65519 |
48 | .hu | 61909 |
49 | .ua | 61464 |
50 | .scot | 58618 |
51 | .ar | 55854 |
52 | .hr | 50064 |
53 | .lk | 49648 |
54 | .sg | 47578 |
55 | .si | 44939 |
56 | .tw | 44324 |
57 | .rs | 44288 |
58 | .hk | 40987 |
59 | None | 34587 |
60 | .co | 32542 |
61 | .cl | 28117 |
62 | .ee | 28045 |
63 | .lv | 26734 |
64 | .id | 25775 |
65 | .sk | 25763 |
66 | .today | 25157 |
67 | .biz | 22921 |
68 | .bg | 22367 |
69 | .th | 20284 |
70 | .lt | 19658 |
71 | .az | 19451 |
72 | .cat | 17723 |
73 | .pe | 17312 |
74 | .lu | 17160 |
75 | .am | 16234 |
76 | .io | 16231 |
77 | .ng | 15892 |
78 | .me | 15535 |
79 | .vn | 15368 |
80 | .fm | 14571 |
81 | .ae | 14262 |
82 | .ke | 14118 |
83 | .ug | 13832 |
84 | .va | 13721 |
85 | .bd | 13281 |
86 | .ba | 12749 |
87 | .al | 12602 |
88 | .np | 12420 |
89 | .uy | 11014 |
90 | .md | 10260 |
91 | .by | 10128 |
# Summary counts of top level domains
# limited to WP:M pages with external links
wpm_tld_query = """
SELECT
REGEXP_EXTRACT({},'(\.[^\.]+)$',1) as tld,
COUNT(distinct el_from, el_to) AS num_links
FROM ryanmax.population_externallinks
WHERE
el_from IN (SELECT page_id FROM ryanmax.population_wpm_pages_with_extlinks)
GROUP BY tld
ORDER BY num_links DESC
"""
wpm_tld = spark.sql(wpm_tld_query.format(parse_host_from_el_to))
wpm_tld.toPandas()
tld | num_links | |
---|---|---|
0 | .org | 331874 |
1 | .gov | 286912 |
2 | .com | 177458 |
3 | .uk | 28999 |
4 | .edu | 27992 |
5 | .int | 19854 |
6 | .ca | 9430 |
7 | .au | 7407 |
8 | .net | 7302 |
9 | .fr | 5201 |
10 | .info | 3788 |
11 | .jp | 3310 |
12 | .eu | 3209 |
13 | .de | 2958 |
14 | .no | 2568 |
15 | .nz | 1467 |
16 | .is | 1448 |
17 | .cz | 1308 |
18 | .in | 1195 |
19 | .ch | 1127 |
20 | .se | 1052 |
21 | .us | 1005 |
22 | .ie | 989 |
23 | .nl | 925 |
24 | .it | 901 |
25 | .today | 882 |
26 | .es | 784 |
27 | .ru | 763 |
28 | .br | 714 |
29 | .mil | 694 |
30 | .za | 670 |
31 | .cn | 619 |
32 | .io | 574 |
33 | .be | 404 |
34 | .pl | 395 |
35 | .sg | 352 |
36 | .pk | 335 |
37 | .dk | 334 |
38 | .il | 325 |
39 | .tw | 322 |
40 | .fi | 308 |
41 | .my | 292 |
42 | .hk | 285 |
43 | .ar | 278 |
44 | .at | 248 |
45 | .ro | 235 |
46 | .mx | 219 |
47 | .pt | 201 |
48 | .tv | 199 |
49 | .co | 194 |
50 | .ph | 194 |
51 | .ug | 188 |
52 | .kr | 183 |
53 | .hu | 176 |
54 | .ir | 168 |
55 | .hr | 163 |
56 | .ua | 152 |
57 | .tr | 138 |
58 | None | 127 |
59 | .lv | 122 |
60 | .lk | 109 |
61 | .cl | 94 |
62 | .ae | 93 |
63 | .gr | 92 |
64 | .rs | 90 |
65 | .si | 88 |
66 | .am | 86 |
67 | .ke | 83 |
68 | .th | 76 |
69 | .vn | 64 |
70 | .sa | 64 |
71 | .bg | 63 |
72 | .ee | 60 |
73 | .mm | 60 |
74 | .cc | 57 |
75 | .cu | 57 |
76 | .ng | 56 |
77 | .ve | 56 |
78 | .mt | 54 |
79 | .az | 53 |
80 | .pe | 52 |
81 | .id | 50 |
82 | .np | 50 |
83 | .sk | 49 |
84 | .scot | 49 |
85 | .bd | 49 |
86 | .jo | 49 |
87 | .cat | 48 |
88 | .bt | 48 |
89 | .ws | 45 |
90 | .zm | 41 |
91 | .mp | 40 |
92 | .sl | 40 |
93 | .tz | 39 |
94 | .uy | 37 |
95 | .lt | 37 |
96 | .biz | 36 |
97 | .gh | 35 |
98 | .eg | 33 |
99 | .md | 32 |
100 | 29 | |
101 | .va | 29 |
102 | .bo | 27 |
103 | .lb | 25 |
104 | .cr | 25 |
105 | .me | 25 |
106 | .om | 24 |
107 | .wales | 24 |
108 | .tt | 21 |
109 | .pa | 21 |
110 | .nu | 20 |
111 | .ma | 19 |
112 | .al | 19 |
113 | .museum | 19 |
114 | .na | 18 |
115 | .uz | 18 |
116 | .ec | 18 |
117 | .kz | 18 |
118 | .lu | 18 |
119 | .mk | 17 |
120 | .news | 17 |
121 | .ge | 16 |
122 | .asia | 16 |
123 | .li | 14 |
124 | .tm | 14 |
125 | .bn | 14 |
126 | .4 | 14 |
127 | .cy | 13 |
128 | .mn | 13 |
129 | .lr | 13 |
130 | .qa | 13 |
131 | .ni | 13 |
132 | .pg | 12 |
133 | .ac | 12 |
134 | .tn | 12 |
135 | .lc | 11 |
136 | .rw | 11 |
137 | .ms | 11 |
138 | .et | 11 |
139 | .fm | 11 |
140 | .af | 10 |
141 | .gt | 10 |
142 | .kg | 10 |
143 | .vg | 10 |
144 | .ht | 10 |
145 | .fo | 10 |
146 | .kp | 10 |
147 | .bz | 9 |
148 | .by | 9 |
149 | .pro | 9 |
150 | .fj | 9 |
151 | .ba | 9 |
152 | .mo | 9 |
153 | .py | 9 |
154 | .bw | 9 |
155 | .mv | 8 |
156 | .zw | 8 |
157 | .gi | 8 |
158 | .hn | 8 |
159 | .ly | 8 |
160 | .pr | 7 |
161 | .jm | 7 |
162 | .tj | 7 |
163 | www | 7 |
164 | .do | 7 |
165 | .html | 7 |
166 | .bm | 7 |
167 | .mw | 7 |
168 | .kw | 7 |
169 | .132 | 6 |
170 | .gg | 6 |
171 | .im | 6 |
172 | .sv | 6 |
173 | .vu | 6 |
174 | .bf | 6 |
175 | .ps | 6 |
176 | .sd | 6 |
177 | .kn | 6 |
178 | .173 | 6 |
179 | .to | 6 |
180 | .ag | 5 |
181 | .kh | 5 |
182 | .68 | 5 |
183 | .bb | 5 |
184 | .65 | 5 |
185 | .la | 5 |
186 | .dm | 5 |
187 | .gy | 5 |
188 | .26 | 4 |
189 | .codes | 4 |
190 | .ml | 4 |
191 | .press | 4 |
192 | .51 | 4 |
193 | .coop | 4 |
194 | .102 | 4 |
195 | .guide | 4 |
196 | .103 | 4 |
197 | .ky | 4 |
198 | .online | 4 |
199 | .foundation | 4 |
200 | .9 | 4 |
201 | .sz | 4 |
202 | .87 | 4 |
203 | .aero | 4 |
204 | .cymru | 4 |
205 | .review | 4 |
206 | .bs | 4 |
207 | .5 | 4 |
208 | .43 | 3 |
209 | .150 | 3 |
210 | .mobi | 3 |
211 | .135 | 3 |
212 | .report | 3 |
213 | .su | 3 |
214 | .ai | 3 |
215 | .144 | 3 |
216 | .nyc | 3 |
217 | .global | 3 |
218 | .29 | 3 |
219 | .bh | 3 |
220 | .206 | 3 |
221 | .166 | 3 |
222 | .life | 3 |
223 | .237 | 3 |
224 | .name | 3 |
225 | .academy | 3 |
226 | .198 | 3 |
227 | .world | 3 |
228 | .cdc | 2 |
229 | .media | 2 |
230 | .legendsofamerica | 2 |
231 | .216 | 2 |
232 | .dz | 2 |
233 | .33 | 2 |
234 | .13 | 2 |
235 | peterson | 2 |
236 | .clinic | 2 |
237 | .sc | 2 |
238 | .xyz | 2 |
239 | .224 | 2 |
240 | .pf | 2 |
241 | carl | 2 |
242 | .176 | 2 |
243 | .vi | 2 |
244 | .live | 2 |
245 | .sm | 2 |
246 | .mu | 2 |
247 | .220 | 2 |
248 | .mr | 2 |
249 | .12 | 2 |
250 | .60 | 2 |
251 | .blog | 2 |
252 | .183 | 2 |
253 | .gm | 2 |
254 | .je | 2 |
255 | .195 | 2 |
256 | .99 | 2 |
257 | .2 | 2 |
258 | .131 | 2 |
259 | .31 | 2 |
260 | .mc | 2 |
261 | .91 | 2 |
262 | .52 | 2 |
263 | .171 | 2 |
264 | .care | 2 |
265 | .154 | 2 |
266 | .nrw | 2 |
267 | .cancerresearch | 2 |
268 | .45 | 2 |
269 | .75 | 2 |
270 | .10 | 2 |
271 | https | 2 |
272 | .194 | 2 |
273 | .ad | 2 |
274 | .247 | 2 |
275 | .130 | 2 |
276 | .167 | 2 |
277 | .107 | 2 |
278 | .tk | 2 |
279 | .ao | 2 |
280 | .vc | 2 |
281 | .58 | 2 |
282 | .18 | 2 |
283 | .149 | 1 |
284 | pn | 1 |
285 | .86 | 1 |
286 | .211 | 1 |
287 | .nihgov | 1 |
288 | http | 1 |
289 | .205 | 1 |
290 | .zone | 1 |
291 | .23 | 1 |
292 | .surgery | 1 |
293 | .bi | 1 |
294 | .36 | 1 |
295 | .mdanderson | 1 |
296 | .93 | 1 |
297 | .ga | 1 |
298 | .63 | 1 |
299 | .233 | 1 |
300 | .gd | 1 |
301 | .bid | 1 |
302 | .88 | 1 |
303 | .202 | 1 |
304 | .jobs | 1 |
305 | .cv | 1 |
306 | .231 | 1 |
307 | .ye | 1 |
308 | .https | 1 |
309 | .bio | 1 |
310 | .cin | 1 |
311 | brescianogibraltarmysteries | 1 |
312 | .8 | 1 |
313 | .ooo | 1 |
314 | .cd | 1 |
315 | www-uptodate-com | 1 |
316 | .sn | 1 |
317 | .104 | 1 |
318 | .178 | 1 |
319 | web | 1 |
320 | .219 | 1 |
321 | .246 | 1 |
322 | .100 | 1 |
323 | .157 | 1 |
324 | .eus | 1 |
325 | .wiki | 1 |
326 | .50 | 1 |
327 | .ucr | 1 |
328 | .xn--p1ai | 1 |
329 | .pub | 1 |
330 | .png | 1 |
331 | ec | 1 |
332 | .ltd | 1 |
333 | .site | 1 |
334 | .cx | 1 |
335 | .uic | 1 |
336 | .14 | 1 |
337 | pages | 1 |
338 | .libinst | 1 |
339 | .77 | 1 |
340 | .ucfhttps | 1 |
341 | .190 | 1 |
342 | .229 | 1 |
343 | .133 | 1 |
344 | .252 | 1 |
345 | .70 | 1 |
346 | .buzz | 1 |
347 | www-ncbi-nlm-nih-gov | 1 |
348 | .http | 1 |
349 | .238 | 1 |
350 | .aarpinternational | 1 |
351 | .39 | 1 |
352 | .sh | 1 |
353 | .radio | 1 |
354 | .support | 1 |
355 | .nip | 1 |
356 | .234 | 1 |
357 | www-clinicalkey-com | 1 |
358 | .comu | 1 |
359 | .90 | 1 |
360 | suite | 1 |
361 | .223 | 1 |
362 | .ngo | 1 |
363 | .win | 1 |
364 | .83 | 1 |
365 | .72 | 1 |
366 | .comhttps | 1 |
367 | .pharmacy | 1 |
368 | .emerck | 1 |
369 | .200 | 1 |
370 | .186 | 1 |
371 | .78 | 1 |
372 | .fund | 1 |
373 | .education | 1 |
374 | .gop | 1 |
375 | .iq | 1 |
376 | .40 | 1 |
377 | .84 | 1 |
378 | .241 | 1 |
379 | med | 1 |
380 | .ajc | 1 |
381 | .tips | 1 |
382 | .archives | 1 |
383 | .group | 1 |
384 | .sy | 1 |
385 | .tl | 1 |
386 | monitoring | 1 |
387 | .expert | 1 |
388 | winslow-webpage | 1 |
389 | books | 1 |
390 | .center | 1 |
391 | .ci | 1 |
392 | pritzker | 1 |
393 | .189 | 1 |
394 | .108 | 1 |
395 | .222 | 1 |
396 | .study | 1 |
397 | .80 | 1 |
398 | .180 | 1 |
399 | .xn--congosynthse-6db | 1 |
400 | .tg | 1 |
401 | .212 | 1 |
# Summary counts of top level domains
# limited to W pages with external links
w_gov_query = """
SELECT
REGEXP_EXTRACT({},'(\.[^\.]+\.[^\.]+)$',1) as domain,
COUNT(distinct el_from, el_to) AS num_links
FROM ryanmax.population_externallinks
WHERE
el_from IN (SELECT page_id FROM ryanmax.population_w_pages_with_extlinks)
AND {} LIKE '%.gov'
GROUP BY domain
ORDER BY num_links DESC
"""
w_gov = spark.sql(w_gov_query.format(parse_host_from_el_to,parse_host_from_el_to))
w_gov.toPandas()
domain | num_links | |
---|---|---|
0 | .nih.gov | 1203974 |
1 | .nasa.gov | 665995 |
2 | .loc.gov | 529931 |
3 | .nps.gov | 330918 |
4 | .census.gov | 265741 |
5 | .usgs.gov | 185509 |
6 | .itis.gov | 147485 |
7 | .noaa.gov | 70033 |
8 | .fcc.gov | 57186 |
9 | .ars-grin.gov | 37804 |
10 | .ca.gov | 37723 |
11 | .usda.gov | 37254 |
12 | .congress.gov | 37007 |
13 | .state.gov | 23578 |
14 | .ed.gov | 22937 |
15 | .archives.gov | 21956 |
16 | .house.gov | 19395 |
17 | .faa.gov | 16235 |
18 | .virginia.gov | 14903 |
19 | .cia.gov | 13015 |
20 | .senate.gov | 12410 |
21 | .ny.gov | 11422 |
22 | .epa.gov | 11062 |
23 | .gpo.gov | 10206 |
24 | .wa.gov | 9909 |
25 | .whitehouse.gov | 9604 |
26 | .in.gov | 9584 |
27 | .nyc.gov | 9504 |
28 | .maryland.gov | 9079 |
29 | .sec.gov | 8793 |
30 | .fws.gov | 8387 |
31 | .defense.gov | 8287 |
32 | .dot.gov | 8223 |
33 | loc.gov | 7547 |
34 | .fjc.gov | 6758 |
35 | .mo.gov | 6484 |
36 | .utah.gov | 6317 |
37 | .cdc.gov | 6248 |
38 | .ga.gov | 5436 |
39 | .uspto.gov | 5376 |
40 | .ohio.gov | 5239 |
41 | .ky.gov | 5140 |
42 | .nist.gov | 5099 |
43 | .justice.gov | 5046 |
44 | .fbi.gov | 4939 |
45 | .uscourts.gov | 4705 |
46 | .oregon.gov | 4675 |
47 | .idaho.gov | 4528 |
48 | .fda.gov | 4481 |
49 | .usembassy.gov | 4382 |
50 | .supremecourt.gov | 4164 |
51 | .ct.gov | 3996 |
52 | .sc.gov | 3756 |
53 | .nationalmap.gov | 3703 |
54 | .la.gov | 3593 |
55 | .pa.gov | 3582 |
56 | .ncdcr.gov | 3344 |
57 | .michigan.gov | 3124 |
58 | .mass.gov | 3068 |
59 | .fec.gov | 3058 |
60 | .blm.gov | 3048 |
61 | .doe.gov | 2966 |
62 | .iowa.gov | 2880 |
63 | .usdoj.gov | 2775 |
64 | .federalregister.gov | 2718 |
65 | .mt.gov | 2649 |
66 | .ntsb.gov | 2599 |
67 | .energy.gov | 2515 |
68 | .wisconsin.gov | 2492 |
69 | .weather.gov | 2454 |
70 | .ri.gov | 2403 |
71 | .nj.gov | 2403 |
72 | .texas.gov | 2381 |
73 | .nsf.gov | 2276 |
74 | .irs.gov | 2236 |
75 | nj.gov | 2214 |
76 | .ilga.gov | 2110 |
77 | .maine.gov | 2081 |
78 | .delaware.gov | 2043 |
79 | .bop.gov | 1913 |
80 | .hawaii.gov | 1902 |
81 | .louisiana.gov | 1888 |
82 | .usbr.gov | 1876 |
83 | .bls.gov | 1809 |
84 | .usaid.gov | 1737 |
85 | .ok.gov | 1733 |
86 | .wi.gov | 1731 |
87 | .treasury.gov | 1687 |
88 | .nysed.gov | 1678 |
89 | .va.gov | 1669 |
90 | .gao.gov | 1664 |
91 | .nga.gov | 1655 |
92 | .eia.gov | 1642 |
93 | .seattle.gov | 1640 |
94 | .fema.gov | 1639 |
95 | .alaska.gov | 1638 |
96 | .dhs.gov | 1636 |
97 | .tn.gov | 1621 |
98 | .lbl.gov | 1620 |
99 | .regulations.gov | 1608 |
100 | .sd.gov | 1568 |
101 | .ftc.gov | 1546 |
102 | .gpoaccess.gov | 1532 |
103 | .ms.gov | 1513 |
104 | .usps.gov | 1508 |
105 | .nationalatlas.gov | 1492 |
106 | .dc.gov | 1485 |
107 | .txdot.gov | 1482 |
108 | .nd.gov | 1467 |
109 | .nh.gov | 1425 |
110 | .deldot.gov | 1424 |
111 | .houstontx.gov | 1378 |
112 | .kingcounty.gov | 1348 |
113 | .osti.gov | 1332 |
114 | .colorado.gov | 1309 |
115 | .ncdot.gov | 1305 |
116 | .dol.gov | 1289 |
117 | .md.gov | 1284 |
118 | .federalreserve.gov | 1266 |
119 | .hhs.gov | 1171 |
120 | .nwcg.gov | 1152 |
121 | .nrc.gov | 1136 |
122 | .newjersey.gov | 1135 |
123 | .cbo.gov | 1128 |
124 | .ornl.gov | 1122 |
125 | .arkansas.gov | 1115 |
126 | .mn.gov | 1088 |
127 | .illinois.gov | 1071 |
128 | .vermont.gov | 1057 |
129 | .nv.gov | 1049 |
130 | .ne.gov | 1044 |
131 | .mi.gov | 1034 |
132 | hawaii.gov | 1031 |
133 | .azsos.gov | 1020 |
134 | .bts.gov | 1005 |
135 | .wv.gov | 1005 |
136 | .doi.gov | 939 |
137 | .nysenate.gov | 932 |
138 | .lanl.gov | 927 |
139 | clinicaltrials.gov | 909 |
140 | .neh.gov | 898 |
141 | .uscis.gov | 894 |
142 | .nsa.gov | 891 |
143 | .gsa.gov | 876 |
144 | .nrel.gov | 871 |
145 | .anl.gov | 867 |
146 | .sandiego.gov | 863 |
147 | .ssa.gov | 842 |
148 | .osha.gov | 836 |
149 | pa.gov | 831 |
150 | .iowadot.gov | 815 |
151 | .myfloridahouse.gov | 812 |
152 | .cancer.gov | 808 |
153 | .cityofboston.gov | 786 |
154 | .ecfr.gov | 778 |
155 | .panynj.gov | 761 |
156 | .ncjrs.gov | 755 |
157 | .lacounty.gov | 744 |
158 | .cbp.gov | 740 |
159 | .bldrdoc.gov | 729 |
160 | .alabama.gov | 713 |
161 | .bnl.gov | 708 |
162 | .llnl.gov | 695 |
163 | .usmint.gov | 667 |
164 | .fdic.gov | 661 |
165 | .hud.gov | 627 |
166 | .fnal.gov | 618 |
167 | .arts.gov | 612 |
168 | energy.gov | 611 |
169 | medlineplus.gov | 605 |
170 | .bart.gov | 604 |
171 | .nebraska.gov | 602 |
172 | .fueleconomy.gov | 600 |
173 | .nea.gov | 590 |
174 | .az.gov | 580 |
175 | .azleg.gov | 577 |
176 | .miamidade.gov | 562 |
177 | .phila.gov | 561 |
178 | .georgia.gov | 557 |
179 | .fdlp.gov | 548 |
180 | .uscg.gov | 545 |
181 | .azgfd.gov | 543 |
182 | .treas.gov | 529 |
183 | .il.gov | 523 |
184 | .portlandoregon.gov | 523 |
185 | .america.gov | 519 |
186 | .centennialofflight.gov | 516 |
187 | .azlibrary.gov | 496 |
188 | .copyright.gov | 491 |
189 | .aoc.gov | 489 |
190 | .nara.gov | 485 |
191 | .sandia.gov | 484 |
192 | .bea.gov | 476 |
193 | .tennessee.gov | 475 |
194 | sdsos.gov | 470 |
195 | .azdot.gov | 468 |
196 | .cpsc.gov | 459 |
197 | .nycourts.gov | 456 |
198 | .doc.gov | 439 |
199 | .govinfo.gov | 437 |
200 | .clinicaltrials.gov | 432 |
201 | educateiowa.gov | 431 |
202 | .fairfaxcounty.gov | 429 |
203 | .ohiodnr.gov | 427 |
204 | .scstatehouse.gov | 415 |
205 | .atlantaga.gov | 407 |
206 | .flsenate.gov | 399 |
207 | .dni.gov | 396 |
208 | .okhouse.gov | 394 |
209 | michigan.gov | 391 |
210 | mn.gov | 391 |
211 | .pr.gov | 388 |
212 | .cambridgema.gov | 370 |
213 | morriscountynj.gov | 367 |
214 | .usconsulate.gov | 367 |
215 | .arkansased.gov | 363 |
216 | .safercar.gov | 352 |
217 | nationalatlas.gov | 349 |
218 | .wvdnr.gov | 345 |
219 | .wicourts.gov | 343 |
220 | .nmlegis.gov | 343 |
221 | .nhtsa.gov | 343 |
222 | .minneapolismn.gov | 337 |
223 | malegislature.gov | 334 |
224 | .opm.gov | 330 |
225 | wisconsindot.gov | 328 |
226 | .inl.gov | 327 |
227 | .ncsbe.gov | 326 |
228 | .educateiowa.gov | 322 |
229 | .fbo.gov | 321 |
230 | .ice.gov | 321 |
231 | .montgomerycountymd.gov | 320 |
232 | .ncparks.gov | 317 |
233 | .atf.gov | 316 |
234 | ilga.gov | 315 |
235 | .abmc.gov | 313 |
236 | .eeoc.gov | 310 |
237 | .recreation.gov | 303 |
238 | .baltimorecity.gov | 303 |
239 | .louisvilleky.gov | 298 |
240 | .sba.gov | 288 |
241 | .nashville.gov | 286 |
242 | .usmission.gov | 283 |
243 | nebraskalegislature.gov | 280 |
244 | .bjs.gov | 277 |
245 | .usa.gov | 277 |
246 | .ustreas.gov | 274 |
247 | .ferc.gov | 270 |
248 | census.gov | 268 |
249 | .ks.gov | 266 |
250 | .9-11commission.gov | 266 |
251 | .cabq.gov | 265 |
252 | .paauditor.gov | 263 |
253 | .rivers.gov | 262 |
254 | .iowacourts.gov | 260 |
255 | .stlouis-mo.gov | 259 |
256 | .supremecourtus.gov | 252 |
257 | .roanokeva.gov | 251 |
258 | .energystar.gov | 251 |
259 | .usap.gov | 248 |
260 | .tsa.gov | 247 |
261 | .usmarshals.gov | 247 |
262 | .akleg.gov | 247 |
263 | .cincinnati-oh.gov | 246 |
264 | .fordlibrarymuseum.gov | 241 |
265 | .ustr.gov | 240 |
266 | .samhsa.gov | 237 |
267 | .cftc.gov | 237 |
268 | .namus.gov | 236 |
269 | .oksenate.gov | 236 |
270 | .commerce.gov | 235 |
271 | .milwaukee.gov | 234 |
272 | .malegislature.gov | 233 |
273 | .tva.gov | 229 |
274 | .peacecorps.gov | 227 |
275 | .uscirf.gov | 223 |
276 | .ntdprogram.gov | 222 |
277 | .wichita.gov | 220 |
278 | .nvsos.gov | 220 |
279 | tennessee.gov | 219 |
280 | .bia.gov | 219 |
281 | .metrokc.gov | 218 |
282 | lacoast.gov | 216 |
283 | .ahrq.gov | 216 |
284 | .nystart.gov | 216 |
285 | arts.gov | 214 |
286 | .cap.gov | 214 |
287 | .sanjoseca.gov | 213 |
288 | .alexandriava.gov | 211 |
289 | epa.gov | 211 |
290 | .gop.gov | 206 |
291 | .oregonlegislature.gov | 205 |
292 | .pnl.gov | 203 |
293 | .ncua.gov | 202 |
294 | .pnnl.gov | 202 |
295 | .njsda.gov | 201 |
296 | .invasivespeciesinfo.gov | 200 |
297 | .princegeorgescountymd.gov | 195 |
298 | .guam.gov | 193 |
299 | .cecc.gov | 191 |
300 | .iowadnr.gov | 190 |
301 | phoenix.gov | 188 |
302 | .nifc.gov | 186 |
303 | .ffiec.gov | 184 |
304 | nvsos.gov | 181 |
305 | .indy.gov | 179 |
306 | .mms.gov | 179 |
307 | .imls.gov | 179 |
308 | majorityleader.gov | 176 |
309 | .bpa.gov | 175 |
310 | .austintexas.gov | 174 |
311 | .uscc.gov | 173 |
312 | .penndot.gov | 172 |
313 | .ussc.gov | 170 |
314 | .mncourts.gov | 169 |
315 | .globalchange.gov | 166 |
316 | americansamoa.gov | 166 |
317 | .nro.gov | 166 |
318 | .nlrb.gov | 165 |
319 | .mndnr.gov | 164 |
320 | .msha.gov | 164 |
321 | .hrsa.gov | 164 |
322 | .dea.gov | 164 |
323 | .maricopa.gov | 163 |
324 | .honolulu.gov | 163 |
325 | .clarkcountynv.gov | 163 |
326 | azsos.gov | 160 |
327 | .okc.gov | 160 |
328 | .erie.gov | 159 |
329 | .tempe.gov | 158 |
330 | .drugabuse.gov | 158 |
331 | .us-cert.gov | 158 |
332 | .genome.gov | 158 |
333 | .nixonlibrary.gov | 157 |
334 | .americaslibrary.gov | 157 |
335 | change.gov | 155 |
336 | .sdlegislature.gov | 154 |
337 | .ilsos.gov | 154 |
338 | .howardcountymd.gov | 153 |
339 | nsf.gov | 153 |
340 | ustr.gov | 152 |
341 | .transportation.gov | 152 |
342 | .ourdocuments.gov | 151 |
343 | .illinoiscourts.gov | 150 |
344 | .arc.gov | 150 |
345 | .consumerfinance.gov | 149 |
346 | .sanantonio.gov | 149 |
347 | .ohiohouse.gov | 149 |
348 | .nebraskalegislature.gov | 148 |
349 | .usaspending.gov | 148 |
350 | .detroitmi.gov | 146 |
351 | .digitalpreservation.gov | 145 |
352 | .doleta.gov | 145 |
353 | .kentucky.gov | 141 |
354 | .nc.gov | 141 |
355 | .nassaucountyny.gov | 138 |
356 | .phoenix.gov | 138 |
357 | .boston.gov | 137 |
358 | .sss.gov | 137 |
359 | .pppl.gov | 136 |
360 | .treasurydirect.gov | 134 |
361 | stlouis-mo.gov | 134 |
362 | .cms.gov | 131 |
363 | .salemcountynj.gov | 131 |
364 | .utcourts.gov | 131 |
365 | .longbeach.gov | 128 |
366 | .oregonmetro.gov | 128 |
367 | .hanford.gov | 128 |
368 | .export.gov | 128 |
369 | .somervillema.gov | 127 |
370 | .ttb.gov | 127 |
371 | .speaker.gov | 126 |
372 | .rrb.gov | 124 |
373 | .climatescience.gov | 124 |
374 | .pima.gov | 124 |
375 | .ohiosenate.gov | 123 |
376 | .capnhq.gov | 122 |
377 | .solardecathlon.gov | 121 |
378 | .ncpc.gov | 119 |
379 | .riversideca.gov | 119 |
380 | .eac.gov | 119 |
381 | .occ.gov | 119 |
382 | .nationalservice.gov | 118 |
383 | .fincen.gov | 117 |
384 | cbo.gov | 115 |
385 | .secretservice.gov | 115 |
386 | .osac.gov | 114 |
387 | .elpasotexas.gov | 113 |
388 | kingcounty.gov | 112 |
389 | .windpoweringamerica.gov | 112 |
390 | .txcourts.gov | 111 |
391 | .csb.gov | 111 |
392 | nyassembly.gov | 110 |
393 | .mcc.gov | 110 |
394 | nyc.gov | 110 |
395 | .fresno.gov | 107 |
396 | .childwelfare.gov | 107 |
397 | .lasvegasnevada.gov | 107 |
398 | azleg.gov | 106 |
399 | virginiageneralassembly.gov | 105 |
400 | .ar.gov | 105 |
401 | charlottenc.gov | 105 |
402 | maine.gov | 104 |
403 | capemaycountynj.gov | 104 |
404 | georgia.gov | 103 |
405 | .endow.gov | 103 |
406 | ntsb.gov | 103 |
407 | .usccr.gov | 103 |
408 | .raleighnc.gov | 102 |
409 | .suffolkcountyny.gov | 102 |
410 | .thomas.gov | 100 |
411 | .tfhrc.gov | 99 |
412 | .stpaul.gov | 99 |
413 | .socialsecurity.gov | 99 |
414 | .loudoun.gov | 98 |
415 | .surgeongeneral.gov | 98 |
416 | .usitc.gov | 98 |
417 | .santafenm.gov | 96 |
418 | .columbus.gov | 96 |
419 | .ofcm.gov | 95 |
420 | .hillsboro-oregon.gov | 95 |
421 | .moneyfactory.gov | 94 |
422 | .sfwmd.gov | 93 |
423 | .osmre.gov | 93 |
424 | .ustaxcourt.gov | 93 |
425 | mich.gov | 92 |
426 | .boem.gov | 92 |
427 | .baltimorecountymd.gov | 91 |
428 | .tucsonaz.gov | 91 |
429 | .csce.gov | 88 |
430 | tn.gov | 88 |
431 | .climate.gov | 88 |
432 | .huntsvilleal.gov | 87 |
433 | .buyusa.gov | 87 |
434 | .morriscountynj.gov | 86 |
435 | alexandriava.gov | 85 |
436 | .bbg.gov | 85 |
437 | .data.gov | 85 |
438 | .ada.gov | 85 |
439 | senate.gov | 84 |
440 | .missouri.gov | 83 |
441 | .dccourts.gov | 83 |
442 | .ndcourts.gov | 82 |
443 | .cityofrochester.gov | 82 |
444 | .seminolecountyfl.gov | 82 |
445 | .dod.gov | 82 |
446 | .scottsdaleaz.gov | 82 |
447 | .trade.gov | 81 |
448 | .ameslab.gov | 81 |
449 | .nctc.gov | 81 |
450 | iowadot.gov | 80 |
451 | .as.gov | 80 |
452 | .pittsburghpa.gov | 79 |
453 | .nola.gov | 79 |
454 | .duluthmn.gov | 79 |
455 | .wyo.gov | 78 |
456 | outdoornebraska.gov | 78 |
457 | .wvlegislature.gov | 77 |
458 | .gps.gov | 76 |
459 | .azcourts.gov | 75 |
460 | .miamibeachfl.gov | 75 |
461 | .eugene-or.gov | 75 |
462 | snohomishcountywa.gov | 74 |
463 | .manchesternh.gov | 73 |
464 | .norfolk.gov | 73 |
465 | .chulavistaca.gov | 73 |
466 | .jimmycarterlibrary.gov | 72 |
467 | .sbcounty.gov | 72 |
468 | abmc.gov | 71 |
469 | ipcc-wg2.gov | 70 |
470 | .reaganlibrary.gov | 70 |
471 | fortworthtexas.gov | 70 |
472 | .azcorrections.gov | 69 |
473 | .ntis.gov | 69 |
474 | .middlesexcountynj.gov | 69 |
475 | .attorneygeneral.gov | 69 |
476 | .goes-r.gov | 68 |
477 | .glin.gov | 68 |
478 | copyright.gov | 68 |
479 | .monroecounty.gov | 68 |
480 | .dol-esa.gov | 68 |
481 | deldot.gov | 68 |
482 | .azcc.gov | 67 |
483 | .wapa.gov | 67 |
484 | .fl.gov | 67 |
485 | myloc.gov | 66 |
486 | .kansas.gov | 66 |
487 | .lowellma.gov | 66 |
488 | .whitehousedrugpolicy.gov | 65 |
489 | .boemre.gov | 65 |
490 | .access-board.gov | 64 |
491 | .restorethegulf.gov | 64 |
492 | ftc.gov | 64 |
493 | .sbir.gov | 64 |
494 | columbus.gov | 64 |
495 | .ncdhhs.gov | 64 |
496 | detroitmi.gov | 64 |
497 | .ncdps.gov | 64 |
498 | .ready.gov | 64 |
499 | .santabarbaraca.gov | 63 |
... | ... | ... |
4289 | .tiffinohio.gov | 1 |
4290 | .cuyonoticias.gov | 1 |
4291 | .fallcreekwi.gov | 1 |
4292 | .oceangate-nj.gov | 1 |
4293 | villageofphoenix-ny.gov | 1 |
4294 | .dccode.gov | 1 |
4295 | pima.gov | 1 |
4296 | hopewellva.gov | 1 |
4297 | .leo.gov | 1 |
4298 | sussexcountyva.gov | 1 |
4299 | .floresvilletx.gov | 1 |
4300 | visitthecapitol.gov | 1 |
4301 | andersontx.gov | 1 |
4302 | raleighnc.gov | 1 |
4303 | indiana.gov | 1 |
4304 | broadband.gov | 1 |
4305 | .oakham-ma.gov | 1 |
4306 | cranberryisles-me.gov | 1 |
4307 | .alexandercountync.gov | 1 |
4308 | .washingtoncountyny.gov | 1 |
4309 | .waltoncountyga.gov | 1 |
4310 | rutherfordcountytn.gov | 1 |
4311 | manchesternh.gov | 1 |
4312 | .stmaryparishla.gov | 1 |
4313 | .elbertcounty-co.gov | 1 |
4314 | .fsam.gov | 1 |
4315 | .iowastem.gov | 1 |
4316 | pacificflyway.gov | 1 |
4317 | hillsboro-oregon.gov | 1 |
4318 | .brycecanyoncityut.gov | 1 |
4319 | .angelfirenm.gov | 1 |
4320 | .washingtoncountyks.gov | 1 |
4321 | .abingdon-va.gov | 1 |
4322 | .northhampton-nh.gov | 1 |
4323 | .hispanicheritagemonth.gov | 1 |
4324 | brownwoodtexas.gov | 1 |
4325 | buckeyeaz.gov | 1 |
4326 | newrussiatownship-oh.gov | 1 |
4327 | .lewisham.gov | 1 |
4328 | .supreme-court.gov | 1 |
4329 | beavercreekohio.gov | 1 |
4330 | .jerome-oh.gov | 1 |
4331 | easthamptonma.gov | 1 |
4332 | pmi.gov | 1 |
4333 | tusayan-az.gov | 1 |
4334 | .nz.gov | 1 |
4335 | .staffordnj.gov | 1 |
4336 | goes-r.gov | 1 |
4337 | .wallawallawa.gov | 1 |
4338 | cityofpattersonla.gov | 1 |
4339 | wheelingil.gov | 1 |
4340 | marlboro-nj.gov | 1 |
4341 | azdoa.gov | 1 |
4342 | .mendonma.gov | 1 |
4343 | alexandercountync.gov | 1 |
4344 | sullivancountytn.gov | 1 |
4345 | martinsville-va.gov | 1 |
4346 | .riversideoh.gov | 1 |
4347 | .azunclaimed.gov | 1 |
4348 | .starnc.gov | 1 |
4349 | .miamicountyohio.gov | 1 |
4350 | leaguecitytx.gov | 1 |
4351 | jamesmadison.gov | 1 |
4352 | townoftropicut.gov | 1 |
4353 | daytonohio.gov | 1 |
4354 | leoncountyfl.gov | 1 |
4355 | .gustavus-ak.gov | 1 |
4356 | .burnsharbor-in.gov | 1 |
4357 | mobilecountyal.gov | 1 |
4358 | .eagle-wi.gov | 1 |
4359 | .egrpra.gov | 1 |
4360 | spp.gov | 1 |
4361 | smart.gov | 1 |
4362 | .iowacollegeaid.gov | 1 |
4363 | .jaspercountyin.gov | 1 |
4364 | .brysoncitync.gov | 1 |
4365 | dontserveteens.gov | 1 |
4366 | .portagewi.gov | 1 |
4367 | .jewishheritagemonth.gov | 1 |
4368 | waukeshacounty.gov | 1 |
4369 | kechiks.gov | 1 |
4370 | indianaffairs.gov | 1 |
4371 | .huroncounty-oh.gov | 1 |
4372 | hraunfoss.gov | 1 |
4373 | southoldtownny.gov | 1 |
4374 | .dh.gov | 1 |
4375 | normanparkga.gov | 1 |
4376 | .hin.gov | 1 |
4377 | .junctioncity-ks.gov | 1 |
4378 | brookhaven-ms.gov | 1 |
4379 | .mnhousing.gov | 1 |
4380 | .medweek.gov | 1 |
4381 | .cottagecitymd.gov | 1 |
4382 | townofriverheadny.gov | 1 |
4383 | cstx.gov | 1 |
4384 | .marylandtaxes.gov | 1 |
4385 | lacounty.gov | 1 |
4386 | .arkansacs.gov | 1 |
4387 | .yanceycountync.gov | 1 |
4388 | maineservicecommission.gov | 1 |
4389 | .investamerica.gov | 1 |
4390 | .dalharttx.gov | 1 |
4391 | crossvilletn.gov | 1 |
4392 | .mckenzietn.gov | 1 |
4393 | .cbca.gov | 1 |
4394 | .seatacwa.gov | 1 |
4395 | .mountainairnm.gov | 1 |
4396 | .grandrapidsmi.gov | 1 |
4397 | .lakepark-fl.gov | 1 |
4398 | .jeffersoncountyga.gov | 1 |
4399 | .northprovidenceri.gov | 1 |
4400 | .eatonville-wa.gov | 1 |
4401 | .mitchell-in.gov | 1 |
4402 | .montague-ma.gov | 1 |
4403 | .washingtonville-ny.gov | 1 |
4404 | .suffolk-va.gov | 1 |
4405 | .fff.gov | 1 |
4406 | .mountkiscony.gov | 1 |
4407 | .washingtonisland-wi.gov | 1 |
4408 | dcradio.gov | 1 |
4409 | manchester-ga.gov | 1 |
4410 | .greenwoodcounty-sc.gov | 1 |
4411 | amherstma.gov | 1 |
4412 | .monckscornersc.gov | 1 |
4413 | .plainfieldnj.gov | 1 |
4414 | ready.gov | 1 |
4415 | .baldwincountyal.gov | 1 |
4416 | .cityofladue-mo.gov | 1 |
4417 | .gulfshoreal.gov | 1 |
4418 | newbritainct.gov | 1 |
4419 | .danvilleva.gov | 1 |
4420 | lsc.gov | 1 |
4421 | .lyndonks.gov | 1 |
4422 | .montgomeryma.gov | 1 |
4423 | .pittsfieldnh.gov | 1 |
4424 | americanlatinomuseum.gov | 1 |
4425 | .nilestwpmi.gov | 1 |
4426 | iarpa.gov | 1 |
4427 | dunmorepa.gov | 1 |
4428 | .foodsafetyworkinggroup.gov | 1 |
4429 | .westford-ma.gov | 1 |
4430 | spaceflorida.gov | 1 |
4431 | .harriscountyga.gov | 1 |
4432 | .cityofgroveok.gov | 1 |
4433 | ustaxcourt.gov | 1 |
4434 | greyforest-tx.gov | 1 |
4435 | .bellavistaar.gov | 1 |
4436 | .cityofweyauwega-wi.gov | 1 |
4437 | buenavistaco.gov | 1 |
4438 | orau.gov | 1 |
4439 | .carboncyclescience.gov | 1 |
4440 | mansfieldct.gov | 1 |
4441 | .adamn.gov | 1 |
4442 | gsaig.gov | 1 |
4443 | mtbs.gov | 1 |
4444 | ricocolorado.gov | 1 |
4445 | .cityofworthingtonhillsky.gov | 1 |
4446 | utcourts.gov | 1 |
4447 | manisteemi.gov | 1 |
4448 | .mrlc.gov | 1 |
4449 | .cityofgalenapark-tx.gov | 1 |
4450 | oshrc.gov | 1 |
4451 | nbm.gov | 1 |
4452 | miramarfl.gov | 1 |
4453 | kingsporttn.gov | 1 |
4454 | .tuskegeealabama.gov | 1 |
4455 | lakeforestca.gov | 1 |
4456 | fcda.gov | 1 |
4457 | rappahannockcountyva.gov | 1 |
4458 | mnrg.gov | 1 |
4459 | bulverdetx.gov | 1 |
4460 | .hoopeston-il.gov | 1 |
4461 | .frogweb.gov | 1 |
4462 | savanna-il.gov | 1 |
4463 | .atlanta.gov | 1 |
4464 | .starkcountynd.gov | 1 |
4465 | .haverhillma.gov | 1 |
4466 | sf.gov | 1 |
4467 | symbols.gov | 1 |
4468 | eloyaz.gov | 1 |
4469 | .normanok.gov | 1 |
4470 | .qld.gov | 1 |
4471 | .cityofkingsburg-ca.gov | 1 |
4472 | .coag.gov | 1 |
4473 | .aftonwyoming.gov | 1 |
4474 | .measuretn.gov | 1 |
4475 | .farmington-mo.gov | 1 |
4476 | .tuxedopark-ny.gov | 1 |
4477 | dcfra.gov | 1 |
4478 | .savanna-il.gov | 1 |
4479 | .calaisvermont.gov | 1 |
4480 | nccs.gov | 1 |
4481 | mcminncountytn.gov | 1 |
4482 | .bacacountyco.gov | 1 |
4483 | .yukonok.gov | 1 |
4484 | .4woman.gov | 1 |
4485 | .hampsteadmd.gov | 1 |
4486 | azag.gov | 1 |
4487 | hamptonnh.gov | 1 |
4488 | pawneerock-ks.gov | 1 |
4489 | dot.gov | 1 |
4490 | .heyworth-il.gov | 1 |
4491 | carthagemo.gov | 1 |
4492 | fema.gov | 1 |
4493 | cullmanal.gov | 1 |
4494 | .coopercountymo.gov | 1 |
4495 | .greenecountyga.gov | 1 |
4496 | .citizenservices.gov | 1 |
4497 | huntspoint-wa.gov | 1 |
4498 | .identitytheft.gov | 1 |
4499 | .northsiouxcity-sd.gov | 1 |
4500 | .trousdalecountytn.gov | 1 |
4501 | .bosquefarmsnm.gov | 1 |
4502 | trumbull-ct.gov | 1 |
4503 | .statehouse.gov | 1 |
4504 | .historicpreservation.gov | 1 |
4505 | .fairmountheightsmd.gov | 1 |
4506 | .sccwi.gov | 1 |
4507 | mymedicare.gov | 1 |
4508 | poquoson-va.gov | 1 |
4509 | .piercecountywa.gov | 1 |
4510 | .fitzwilliam-nh.gov | 1 |
4511 | .copperascovetx.gov | 1 |
4512 | virginia.gov | 1 |
4513 | .milan-ny.gov | 1 |
4514 | newarknj.gov | 1 |
4515 | .boiseidaho.gov | 1 |
4516 | .sanmiguelcountyco.gov | 1 |
4517 | mead-co.gov | 1 |
4518 | .morgancountywv.gov | 1 |
4519 | .middletonma.gov | 1 |
4520 | .rockyhillct.gov | 1 |
4521 | desmoineswa.gov | 1 |
4522 | .foxcrossingwi.gov | 1 |
4523 | exim.gov | 1 |
4524 | .middleburgva.gov | 1 |
4525 | .interlachen-fl.gov | 1 |
4526 | .watchungnj.gov | 1 |
4527 | .ktik-nsn.gov | 1 |
4528 | mca.gov | 1 |
4529 | piermont-ny.gov | 1 |
4530 | .stoneham-ma.gov | 1 |
4531 | gallatin-tn.gov | 1 |
4532 | yesican.gov | 1 |
4533 | digital.gov | 1 |
4534 | .legislation.gov | 1 |
4535 | fbo.gov | 1 |
4536 | blainecounty-mt.gov | 1 |
4537 | .colchestervt.gov | 1 |
4538 | .medlineplus.gov | 1 |
4539 | cityofsouthfultonga.gov | 1 |
4540 | .greenecountyms.gov | 1 |
4541 | .warrickcounty.gov | 1 |
4542 | .stanlycountync.gov | 1 |
4543 | .emmitsburgmd.gov | 1 |
4544 | .coronaca.gov | 1 |
4545 | fhfb.gov | 1 |
4546 | hendersoncountytn.gov | 1 |
4547 | .hooveralabama.gov | 1 |
4548 | hialeahfl.gov | 1 |
4549 | fdicig.gov | 1 |
4550 | .jfc.gov | 1 |
4551 | .summervillesc.gov | 1 |
4552 | .burkittsville-md.gov | 1 |
4553 | lexingtonky.gov | 1 |
4554 | .njccc.gov | 1 |
4555 | duluthmn.gov | 1 |
4556 | .villageofkensingtonny.gov | 1 |
4557 | .toolecountymt.gov | 1 |
4558 | salemva.gov | 1 |
4559 | .openinternet.gov | 1 |
4560 | ohiohouse.gov | 1 |
4561 | .tisburyma.gov | 1 |
4562 | .ndop.gov | 1 |
4563 | ankenyiowa.gov | 1 |
4564 | franklincountyga.gov | 1 |
4565 | .cityofsouthfultonga.gov | 1 |
4566 | lawrenceburgtn.gov | 1 |
4567 | rpvca.gov | 1 |
4568 | .hpca.gov | 1 |
4569 | columbianaohio.gov | 1 |
4570 | .nolaoig.gov | 1 |
4571 | bureaucounty-il.gov | 1 |
4572 | .bureaucounty-il.gov | 1 |
4573 | .azboec.gov | 1 |
4574 | .nclawspecialists.gov | 1 |
4575 | .clarioniowa.gov | 1 |
4576 | .bayside-wi.gov | 1 |
4577 | rosebudcountymt.gov | 1 |
4578 | ise.gov | 1 |
4579 | section508.gov | 1 |
4580 | .ncdor.gov | 1 |
4581 | .richlandsnc.gov | 1 |
4582 | wwwcia.gov | 1 |
4583 | mesagrandeband-nsn.gov | 1 |
4584 | .gadsdencountyfl.gov | 1 |
4585 | .nagsheadnc.gov | 1 |
4586 | .crimevictims.gov | 1 |
4587 | .northvernon-in.gov | 1 |
4588 | .pinevillenc.gov | 1 |
4589 | browncounty-in.gov | 1 |
4590 | buyaccessible.gov | 1 |
4591 | .syracuseks.gov | 1 |
4592 | boxborough-ma.gov | 1 |
4593 | .azusaca.gov | 1 |
4594 | .emanuelco-ga.gov | 1 |
4595 | .transparencyflorida.gov | 1 |
4596 | .harrisonohio.gov | 1 |
4597 | .lakemt.gov | 1 |
4598 | williamsoncounty-tn.gov | 1 |
4599 | .sugarcityidaho.gov | 1 |
4600 | cheathamcountytn.gov | 1 |
4601 | lakestevenswa.gov | 1 |
4602 | .claycountyin.gov | 1 |
4603 | .lackawannany.gov | 1 |
4604 | .mahouse.gov | 1 |
4605 | swaincountync.gov | 1 |
4606 | heyworth-il.gov | 1 |
4607 | .clearspringmd.gov | 1 |
4608 | .franklinpa.gov | 1 |
4609 | fgdc.gov | 1 |
4610 | .limerick-me.gov | 1 |
4611 | .craigcountyva.gov | 1 |
4612 | .cherokeecounty-al.gov | 1 |
4613 | crystalmn.gov | 1 |
4614 | bountifulutah.gov | 1 |
4615 | honolulu.gov | 1 |
4616 | .sunnyside-wa.gov | 1 |
4617 | .townofcallahan-fl.gov | 1 |
4618 | consumeraction.gov | 1 |
4619 | .bellairetx.gov | 1 |
4620 | cravencountync.gov | 1 |
4621 | crestoniowa.gov | 1 |
4622 | .scottcountymn.gov | 1 |
4623 | cityoftitusvillepa.gov | 1 |
4624 | .chatsworthga.gov | 1 |
4625 | .azcjc.gov | 1 |
4626 | txdmv.gov | 1 |
4627 | wellesleyma.gov | 1 |
4628 | pci-nsn.gov | 1 |
4629 | cityofirondaleal.gov | 1 |
4630 | williamstownma.gov | 1 |
4631 | .covingtoncountyms.gov | 1 |
4632 | indianpoint-mo.gov | 1 |
4633 | .ca10uscourts.gov | 1 |
4634 | .losranchosnm.gov | 1 |
4635 | .mineralwellstx.gov | 1 |
4636 | .dallascountyiowa.gov | 1 |
4637 | dotgov.gov | 1 |
4638 | .clubdrugs.gov | 1 |
4639 | .dcfra.gov | 1 |
4640 | .blainemn.gov | 1 |
4641 | .piercecountynd.gov | 1 |
4642 | westonwi.gov | 1 |
4643 | northvernon-in.gov | 1 |
4644 | ramona-nsn.gov | 1 |
4645 | annapolis.gov | 1 |
4646 | nepa.gov | 1 |
4647 | townofhurtva.gov | 1 |
4648 | .killinglyct.gov | 1 |
4649 | .mecklenburgcountync.gov | 1 |
4650 | endingthedocumentgame.gov | 1 |
4651 | .masticbeachvillageny.gov | 1 |
4652 | starkcountyohio.gov | 1 |
4653 | .nutrition.gov | 1 |
4654 | .jackson-sc.gov | 1 |
4655 | .dumfriesva.gov | 1 |
4656 | .warren-ma.gov | 1 |
4657 | .mshaa.gov | 1 |
4658 | sandyspringsga.gov | 1 |
4659 | .eisgatewaypacificwa.gov | 1 |
4660 | .ninilchiktribe-nsn.gov | 1 |
4661 | .azhousing.gov | 1 |
4662 | mountainairnm.gov | 1 |
4663 | .superioraz.gov | 1 |
4664 | digitalliteracy.gov | 1 |
4665 | hhs.gov | 1 |
4666 | .trinityal.gov | 1 |
4667 | .tnk12.gov | 1 |
4668 | .buildingamerica.gov | 1 |
4669 | .usgms.gov | 1 |
4670 | .lccountymt.gov | 1 |
4671 | ratonnm.gov | 1 |
4672 | lagrangeny.gov | 1 |
4673 | .cg.gov | 1 |
4674 | .justthinktwice.gov | 1 |
4675 | achp.gov | 1 |
4676 | .chukchansi-nsn.gov | 1 |
4677 | cityofchetek-wi.gov | 1 |
4678 | townofminervany.gov | 1 |
4679 | harrisburgsd.gov | 1 |
4680 | shrewsbury-ma.gov | 1 |
4681 | .careervoyages.gov | 1 |
4682 | .noa.gov | 1 |
4683 | .recalls.gov | 1 |
4684 | srmt-nsn.gov | 1 |
4685 | .tallulahfallsga.gov | 1 |
4686 | .showlowaz.gov | 1 |
4687 | fortsmithar.gov | 1 |
4688 | .forestheightsmd.gov | 1 |
4689 | townofmoriahny.gov | 1 |
4690 | .federalreserveconsumerhelp.gov | 1 |
4691 | montana.gov | 1 |
4692 | .jacksoncounty-il.gov | 1 |
4693 | lovington-il.gov | 1 |
4694 | courtswv.gov | 1 |
4695 | usatradeonline.gov | 1 |
4696 | nysdhcr.gov | 1 |
4697 | .cityofbowmanga.gov | 1 |
4698 | registertovoteflorida.gov | 1 |
4699 | cns.gov | 1 |
4700 | metrokc.gov | 1 |
4701 | .lavernia-tx.gov | 1 |
4702 | colrain-ma.gov | 1 |
4703 | wmatc.gov | 1 |
4704 | .flleg.gov | 1 |
4705 | .warrencountyky.gov | 1 |
4706 | lasalle-il.gov | 1 |
4707 | mtshastaca.gov | 1 |
4708 | .ghana.gov | 1 |
4709 | .npas.gov | 1 |
4710 | .veterans.gov | 1 |
4711 | lantabus-pa.gov | 1 |
4712 | dhs.gov | 1 |
4713 | .walkercountyga.gov | 1 |
4714 | .westjeffersonohio.gov | 1 |
4715 | mypyramid.gov | 1 |
4716 | .donaldoregon.gov | 1 |
4717 | .hendersoncountytn.gov | 1 |
4718 | .eklutna-nsn.gov | 1 |
4719 | cantontwp-oh.gov | 1 |
4720 | bendoregon.gov | 1 |
4721 | .daniabeachfl.gov | 1 |
4722 | .evergladesrestoration.gov | 1 |
4723 | .nationalinstituteofcorrections.gov | 1 |
4724 | .wyomingofficeoftourism.gov | 1 |
4725 | .aztecnm.gov | 1 |
4726 | .knoxvilleia.gov | 1 |
4727 | .italladdsup.gov | 1 |
4728 | rochestermn.gov | 1 |
4729 | .chulavistca.gov | 1 |
4730 | borgertx.gov | 1 |
4731 | .wspmn.gov | 1 |
4732 | .nnlm.gov | 1 |
4733 | .federalreporting.gov | 1 |
4734 | .usaseanconnect.gov | 1 |
4735 | .cpars.gov | 1 |
4736 | .glennheightstx.gov | 1 |
4737 | ecorsemi.gov | 1 |
4738 | .dcsc.gov | 1 |
4739 | tupeloms.gov | 1 |
4740 | iowacore.gov | 1 |
4741 | .mcrmc.gov | 1 |
4742 | usap.gov | 1 |
4743 | newjersey.gov | 1 |
4744 | nhl.gov | 1 |
4745 | .scribner-ne.gov | 1 |
4746 | .townofpenningtonva.gov | 1 |
4747 | bacacountyco.gov | 1 |
4748 | oakhillwv.gov | 1 |
4749 | needhamma.gov | 1 |
4750 | .woodville-tx.gov | 1 |
4751 | .breckenridgetx.gov | 1 |
4752 | fredericksburgva.gov | 1 |
4753 | naplescityut.gov | 1 |
4754 | .ma.gov | 1 |
4755 | freeportflorida.gov | 1 |
4756 | .oklatourism.gov | 1 |
4757 | .atpa.gov | 1 |
4758 | .plymouthcountyma.gov | 1 |
4759 | .mansfieldga.gov | 1 |
4760 | .healthyforests.gov | 1 |
4761 | .blissfieldmichigan.gov | 1 |
4762 | rockwellnc.gov | 1 |
4763 | aikencountysc.gov | 1 |
4764 | gulfport-ms.gov | 1 |
4765 | .newtownohio.gov | 1 |
4766 | azcleanelections.gov | 1 |
4767 | bnl.gov | 1 |
4768 | .vernontx.gov | 1 |
4769 | .cityofhubbard-oh.gov | 1 |
4770 | .pleasantvalley-ny.gov | 1 |
4771 | .beckemeyeril.gov | 1 |
4772 | gardencity-ga.gov | 1 |
4773 | .stmaryspa.gov | 1 |
4774 | tuckerga.gov | 1 |
4775 | .townofnortheastny.gov | 1 |
4776 | .sunlandpark-nm.gov | 1 |
4777 | computersforlearning.gov | 1 |
4778 | fremontne.gov | 1 |
4779 | .toombscountyga.gov | 1 |
4780 | .wcnyh.gov | 1 |
4781 | morehead-ky.gov | 1 |
4782 | .marshfieldmo.gov | 1 |
4783 | .rockdalecountyga.gov | 1 |
4784 | .cityofpataskalaohio.gov | 1 |
4785 | .aftac.gov | 1 |
4786 | kannapolisnc.gov | 1 |
4787 | .njmvc.gov | 1 |
4788 | northforkrancheria-nsn.gov | 1 |
4789 rows × 2 columns
# Summary counts of top level domains
# limited to WP:M pages with external links
wpm_gov_query = """
SELECT
REGEXP_EXTRACT({},'(\.[^\.]+\.[^\.]+)$',1) as domain,
COUNT(distinct el_from, el_to) AS num_links
FROM ryanmax.population_externallinks
WHERE
el_from IN (SELECT page_id FROM ryanmax.population_wpm_pages_with_extlinks)
AND {} LIKE '%.gov'
GROUP BY domain
ORDER BY num_links DESC
"""
wpm_gov = spark.sql(wpm_gov_query.format(parse_host_from_el_to,parse_host_from_el_to))
wpm_gov.toPandas()
domain | num_links | |
---|---|---|
0 | .nih.gov | 257219 |
1 | .cdc.gov | 7040 |
2 | .fda.gov | 4336 |
3 | .loc.gov | 3671 |
4 | .cancer.gov | 1569 |
5 | medlineplus.gov | 1072 |
6 | .epa.gov | 747 |
7 | .hhs.gov | 577 |
8 | clinicaltrials.gov | 466 |
9 | .ahrq.gov | 441 |
10 | .usda.gov | 376 |
11 | .ca.gov | 293 |
12 | .gpo.gov | 287 |
13 | .medicaid.gov | 270 |
14 | .va.gov | 246 |
15 | .cms.gov | 244 |
16 | .congress.gov | 237 |
17 | .nasa.gov | 227 |
18 | .house.gov | 203 |
19 | .archives.gov | 192 |
20 | .clinicaltrials.gov | 192 |
21 | .drugabuse.gov | 183 |
22 | .usdoj.gov | 179 |
23 | .whitehouse.gov | 177 |
24 | .uspto.gov | 157 |
25 | .itis.gov | 150 |
26 | .hrsa.gov | 146 |
27 | .cia.gov | 132 |
28 | .osha.gov | 131 |
29 | .senate.gov | 130 |
30 | .samhsa.gov | 126 |
31 | .sec.gov | 126 |
32 | .womenshealth.gov | 120 |
33 | .cbo.gov | 119 |
34 | .justice.gov | 114 |
35 | .wa.gov | 109 |
36 | .bls.gov | 105 |
37 | .surgeongeneral.gov | 101 |
38 | .federalregister.gov | 101 |
39 | .genome.gov | 99 |
40 | .usaid.gov | 97 |
41 | .census.gov | 91 |
42 | .guideline.gov | 91 |
43 | .ny.gov | 86 |
44 | .ed.gov | 85 |
45 | .ncjrs.gov | 84 |
46 | .healthcare.gov | 79 |
47 | .gao.gov | 78 |
48 | .irs.gov | 74 |
49 | .usgs.gov | 73 |
50 | .oregon.gov | 71 |
51 | .nyc.gov | 71 |
52 | .fema.gov | 71 |
53 | cdc.gov | 68 |
54 | .uscourts.gov | 67 |
55 | .nps.gov | 62 |
56 | .state.gov | 61 |
57 | .nist.gov | 59 |
58 | .fbi.gov | 56 |
59 | .dot.gov | 56 |
60 | .ihs.gov | 55 |
61 | .faa.gov | 54 |
62 | .dc.gov | 53 |
63 | .ftc.gov | 51 |
64 | .medicare.gov | 50 |
65 | .healthit.gov | 50 |
66 | .nsf.gov | 49 |
67 | .ssa.gov | 45 |
68 | .mo.gov | 42 |
69 | .noaa.gov | 41 |
70 | .ornl.gov | 41 |
71 | .healthypeople.gov | 41 |
72 | .michigan.gov | 38 |
73 | .virginia.gov | 37 |
74 | .nrc.gov | 36 |
75 | .fcc.gov | 35 |
76 | .dea.gov | 34 |
77 | .osti.gov | 34 |
78 | .ars-grin.gov | 33 |
79 | .mass.gov | 32 |
80 | .health.gov | 30 |
81 | health.gov | 30 |
82 | .ct.gov | 30 |
83 | .utah.gov | 29 |
84 | .supremecourt.gov | 28 |
85 | .pepfar.gov | 27 |
86 | .lbl.gov | 26 |
87 | .wisconsin.gov | 26 |
88 | .maryland.gov | 26 |
89 | .ohio.gov | 25 |
90 | .lacounty.gov | 24 |
91 | .ems.gov | 24 |
92 | .usembassy.gov | 24 |
93 | .ky.gov | 23 |
94 | .in.gov | 23 |
95 | .bnl.gov | 22 |
96 | .pandemicflu.gov | 22 |
97 | .fdlp.gov | 21 |
98 | .childwelfare.gov | 21 |
99 | .regulations.gov | 20 |
100 | .dol.gov | 20 |
101 | .ntsb.gov | 19 |
102 | womenshealth.gov | 19 |
103 | .nhtsa.gov | 19 |
104 | .kingcounty.gov | 19 |
105 | .eeoc.gov | 19 |
106 | .azdhs.gov | 19 |
107 | .aids.gov | 18 |
108 | .ri.gov | 18 |
109 | .flu.gov | 18 |
110 | .energy.gov | 18 |
111 | .doe.gov | 18 |
112 | .medpac.gov | 18 |
113 | .choosemyplate.gov | 18 |
114 | .scdhec.gov | 17 |
115 | .govinfo.gov | 17 |
116 | .bjs.gov | 17 |
117 | .usphs.gov | 17 |
118 | .gpoaccess.gov | 16 |
119 | .maine.gov | 16 |
120 | .mentalhealthcommission.gov | 15 |
121 | .vermont.gov | 15 |
122 | .nysed.gov | 15 |
123 | .alaska.gov | 15 |
124 | .anl.gov | 15 |
125 | .delaware.gov | 14 |
126 | .treasury.gov | 14 |
127 | healthypeople.gov | 13 |
128 | .phe.gov | 13 |
129 | .nj.gov | 13 |
130 | .hiv.gov | 13 |
131 | .lanl.gov | 13 |
132 | locatorplus.gov | 13 |
133 | .sandiego.gov | 13 |
134 | .guidelines.gov | 12 |
135 | healthfinder.gov | 12 |
136 | .azsos.gov | 12 |
137 | .cpsc.gov | 12 |
138 | .psc.gov | 12 |
139 | .mn.gov | 12 |
140 | .wi.gov | 12 |
141 | .idaho.gov | 11 |
142 | .dhhs.gov | 11 |
143 | .hawaii.gov | 11 |
144 | .colorado.gov | 11 |
145 | .dhs.gov | 11 |
146 | .illinois.gov | 11 |
147 | .selectagents.gov | 11 |
148 | .phila.gov | 10 |
149 | .pa.gov | 10 |
150 | .vaccines.gov | 10 |
151 | .ready.gov | 9 |
152 | .georgia.gov | 9 |
153 | .mt.gov | 9 |
154 | .fws.gov | 9 |
155 | .defense.gov | 9 |
156 | .nlm.gov | 9 |
157 | .louisvilleky.gov | 9 |
158 | drugabuse.gov | 9 |
159 | .ecfr.gov | 9 |
160 | .4woman.gov | 9 |
161 | .mi.gov | 9 |
162 | .ok.gov | 9 |
163 | .ncdhhs.gov | 9 |
164 | .nh.gov | 8 |
165 | guideline.gov | 8 |
166 | bestbonesforever.gov | 8 |
167 | .louisiana.gov | 8 |
168 | .metrokc.gov | 8 |
169 | loc.gov | 8 |
170 | .opm.gov | 8 |
171 | .pmi.gov | 8 |
172 | healthvermont.gov | 8 |
173 | .whitehousedrugpolicy.gov | 8 |
174 | .kdheks.gov | 7 |
175 | epa.gov | 7 |
176 | cbo.gov | 7 |
177 | .csb.gov | 7 |
178 | cancer.gov | 7 |
179 | .gsa.gov | 7 |
180 | .tn.gov | 7 |
181 | .nara.gov | 7 |
182 | .treas.gov | 7 |
183 | .traviscountytx.gov | 7 |
184 | .organdonor.gov | 7 |
185 | .ne.gov | 6 |
186 | .mypyramid.gov | 6 |
187 | .arkansas.gov | 6 |
188 | .healthfinder.gov | 6 |
189 | .newjersey.gov | 6 |
190 | .miamidade.gov | 6 |
191 | .usa.gov | 6 |
192 | hawaii.gov | 6 |
193 | .sd.gov | 6 |
194 | .ks.gov | 6 |
195 | .ada.gov | 6 |
196 | .america.gov | 6 |
197 | .uscis.gov | 6 |
198 | .fbo.gov | 6 |
199 | .pubmedcentral.gov | 6 |
200 | .osac.gov | 6 |
201 | .msha.gov | 6 |
202 | .texas.gov | 5 |
203 | .newportbeachca.gov | 5 |
204 | .iowa.gov | 5 |
205 | organdonor.gov | 5 |
206 | .peacecorps.gov | 5 |
207 | aids.gov | 5 |
208 | .dni.gov | 5 |
209 | .milwaukee.gov | 5 |
210 | .aoa.gov | 5 |
211 | .ms.gov | 5 |
212 | .riversideca.gov | 5 |
213 | .seattle.gov | 5 |
214 | .neh.gov | 5 |
215 | .fjc.gov | 5 |
216 | .mentalhealth.gov | 4 |
217 | .nbii.gov | 4 |
218 | .nij.gov | 4 |
219 | .socialsecurity.gov | 4 |
220 | .la.gov | 4 |
221 | .ncd.gov | 4 |
222 | .hanford.gov | 4 |
223 | isotopes.gov | 4 |
224 | .tsa.gov | 4 |
225 | .arsusda.gov | 4 |
226 | .bop.gov | 4 |
227 | majorityleader.gov | 4 |
228 | .flsenate.gov | 4 |
229 | nihseniorhealth.gov | 4 |
230 | .nc.gov | 4 |
231 | .wv.gov | 4 |
232 | nj.gov | 4 |
233 | .nv.gov | 4 |
234 | .clinicaltrial.gov | 4 |
235 | hhs.gov | 4 |
236 | ttb.gov | 4 |
237 | senate.gov | 3 |
238 | .myfloridahouse.gov | 3 |
239 | .foodsafety.gov | 3 |
240 | .healthvermont.gov | 3 |
241 | .nationalchildrensstudy.gov | 3 |
242 | .usbr.gov | 3 |
243 | .malegislature.gov | 3 |
244 | .ttb.gov | 3 |
245 | .doleta.gov | 3 |
246 | .healthdata.gov | 3 |
247 | .commerce.gov | 3 |
248 | .transportation.gov | 3 |
249 | .wyo.gov | 3 |
250 | .fitness.gov | 3 |
251 | .floridahealth.gov | 3 |
252 | smokefree.gov | 3 |
253 | bioethics.gov | 3 |
254 | .eia.gov | 3 |
255 | surgeongeneral.gov | 3 |
256 | guidelines.gov | 3 |
257 | .ga.gov | 3 |
258 | .azleg.gov | 3 |
259 | .fec.gov | 3 |
260 | 4women.gov | 3 |
261 | riversideca.gov | 3 |
262 | .az.gov | 3 |
263 | .uscirf.gov | 3 |
264 | austintexas.gov | 3 |
265 | healthit.gov | 3 |
266 | .oksenate.gov | 3 |
267 | .ilga.gov | 3 |
268 | .nysenate.gov | 3 |
269 | costamesaca.gov | 3 |
270 | malegislature.gov | 3 |
271 | nsf.gov | 3 |
272 | .llnl.gov | 3 |
273 | .hud.gov | 3 |
274 | .cecc.gov | 3 |
275 | .nitrd.gov | 3 |
276 | .arc.gov | 2 |
277 | .4women.gov | 2 |
278 | .montgomerycountymd.gov | 2 |
279 | .nsa.gov | 2 |
280 | .federalreserve.gov | 2 |
281 | .fordlibrarymuseum.gov | 2 |
282 | .usconsulate.gov | 2 |
283 | .wvlegislature.gov | 2 |
284 | .data.gov | 2 |
285 | .md.gov | 2 |
286 | .girlshealth.gov | 2 |
287 | .attorneygeneral.gov | 2 |
288 | .jct.gov | 2 |
289 | .ustr.gov | 2 |
290 | .citizencorps.gov | 2 |
291 | .nutrition.gov | 2 |
292 | .glin.gov | 2 |
293 | .fnal.gov | 2 |
294 | .ice.gov | 2 |
295 | genome.gov | 2 |
296 | .collegedrinkingprevention.gov | 2 |
297 | .tennessee.gov | 2 |
298 | nnlm.gov | 2 |
299 | .baltimorecity.gov | 2 |
300 | .usap.gov | 2 |
301 | .ncifcrf.gov | 2 |
302 | .azcc.gov | 2 |
303 | .baltimorecountymd.gov | 2 |
304 | .ar.gov | 2 |
305 | .marylandhealthconnection.gov | 2 |
306 | .oregonlegislature.gov | 2 |
307 | .nyhealth.gov | 2 |
308 | ngc.gov | 2 |
309 | .usmission.gov | 2 |
310 | .invasivespeciesinfo.gov | 2 |
311 | .ncdcr.gov | 2 |
312 | .acus.gov | 2 |
313 | .cwc.gov | 2 |
314 | nih.gov | 2 |
315 | usphs.gov | 2 |
316 | .sbir.gov | 2 |
317 | .usitc.gov | 2 |
318 | .omhrc.gov | 2 |
319 | .bioethics.gov | 2 |
320 | .cityofboston.gov | 2 |
321 | flu.gov | 2 |
322 | .orau.gov | 2 |
323 | .nola.gov | 2 |
324 | mn.gov | 2 |
325 | .healthindicators.gov | 2 |
326 | .safercar.gov | 2 |
327 | maine.gov | 2 |
328 | .stopmedicarefraud.gov | 2 |
329 | .bestbonesforever.gov | 2 |
330 | .gop.gov | 2 |
331 | gao.gov | 2 |
332 | .agingstats.gov | 2 |
333 | .nmlegis.gov | 2 |
334 | .oilspillcommission.gov | 2 |
335 | .ncagr.gov | 2 |
336 | .chemsafety.gov | 2 |
337 | vetsuccess.gov | 2 |
338 | .fiscalcommission.gov | 2 |
339 | sierranevadawild.gov | 2 |
340 | .vt.gov | 2 |
341 | .hayward-ca.gov | 2 |
342 | .sc.gov | 2 |
343 | healthcare.gov | 2 |
344 | .psn.gov | 2 |
345 | illinoisattorneygeneral.gov | 1 |
346 | usich.gov | 1 |
347 | .copyright.gov | 1 |
348 | .pubmed.gov | 1 |
349 | .boem.gov | 1 |
350 | .hcfa.gov | 1 |
351 | .pr.gov | 1 |
352 | .floridahealthfinder.gov | 1 |
353 | .distraction.gov | 1 |
354 | .recoverymonth.gov | 1 |
355 | .consumer.gov | 1 |
356 | .nrd.gov | 1 |
357 | .cap.gov | 1 |
358 | .nea.gov | 1 |
359 | flsenate.gov | 1 |
360 | .fedcenter.gov | 1 |
361 | .nebraska.gov | 1 |
362 | dni.gov | 1 |
363 | njconsumeraffairs.gov | 1 |
364 | .letsmove.gov | 1 |
365 | .morgantownwv.gov | 1 |
366 | clermontcountyohio.gov | 1 |
367 | michigan.gov | 1 |
368 | .ohioattorneygeneral.gov | 1 |
369 | .sandiegocounty.gov | 1 |
370 | .change.gov | 1 |
371 | .costamesaca.gov | 1 |
372 | .azmd.gov | 1 |
373 | .wvdnr.gov | 1 |
374 | .williamsoncountyil.gov | 1 |
375 | .neglecteddiseases.gov | 1 |
376 | .jimmycarterlibrary.gov | 1 |
377 | .cavc.gov | 1 |
378 | .nro.gov | 1 |
379 | .juvenilecouncil.gov | 1 |
380 | .pnl.gov | 1 |
381 | .fido.gov | 1 |
382 | cityofboston.gov | 1 |
383 | .eldercare.gov | 1 |
384 | ojp.gov | 1 |
385 | .ojjdp.gov | 1 |
386 | change.gov | 1 |
387 | .nationalservice.gov | 1 |
388 | .houstontx.gov | 1 |
389 | osha.gov | 1 |
390 | .recovery.gov | 1 |
391 | .plainlanguage.gov | 1 |
392 | .challenge.gov | 1 |
393 | .scstatehouse.gov | 1 |
394 | energy.gov | 1 |
395 | .austintexas.gov | 1 |
396 | .crimesolutions.gov | 1 |
397 | .ohioagriculture.gov | 1 |
398 | nist.gov | 1 |
399 | .boston.gov | 1 |
400 | crimesolutions.gov | 1 |
401 | .burlingtonvt.gov | 1 |
402 | .ghi.gov | 1 |
403 | .somervillema.gov | 1 |
404 | .alabama.gov | 1 |
405 | .ovc.gov | 1 |
406 | .illinoisattorneygeneral.gov | 1 |
407 | .us-cert.gov | 1 |
408 | hrsa.gov | 1 |
409 | .ohioresponds.gov | 1 |
410 | .access-board.gov | 1 |
411 | .ncdps.gov | 1 |
412 | .ilsos.gov | 1 |
413 | .roanokeva.gov | 1 |
414 | .benefits.gov | 1 |
415 | pubmed.gov | 1 |
416 | outdoornebraska.gov | 1 |
417 | .hcqualitycommission.gov | 1 |
418 | .ngc.gov | 1 |
419 | .ussc.gov | 1 |
420 | .doc.gov | 1 |
421 | .visitthecapitol.gov | 1 |
422 | .srpmic-nsn.gov | 1 |
423 | .dna.gov | 1 |
424 | .lymenh.gov | 1 |
425 | .cabq.gov | 1 |
426 | .atf.gov | 1 |
427 | .usaspending.gov | 1 |
428 | .pcip.gov | 1 |
429 | .dconc.gov | 1 |
430 | .adf.gov | 1 |
431 | .jccbi.gov | 1 |
432 | kentucky.gov | 1 |
433 | azdhs.gov | 1 |
434 | phila.gov | 1 |
435 | .samsha.gov | 1 |
436 | .usccr.gov | 1 |
437 | azleg.gov | 1 |
438 | .sba.gov | 1 |
439 | .insurekidsnow.gov | 1 |
440 | .stpaul.gov | 1 |
441 | .pnnl.gov | 1 |
442 | census.gov | 1 |
443 | .globalhealth.gov | 1 |
444 | udall.gov | 1 |
445 | .pearlandtx.gov | 1 |
446 | .bja.gov | 1 |
447 | .alpinecountyca.gov | 1 |
448 | .alabamapublichealth.gov | 1 |
449 | .greenvillenc.gov | 1 |
450 | ems.gov | 1 |
451 | .cahwnet.gov | 1 |
452 | medpac.gov | 1 |
453 | .who.gov | 1 |
454 | .cstx.gov | 1 |
455 | .ntis.gov | 1 |
456 | azsos.gov | 1 |
457 | .staffordtx.gov | 1 |
458 | .section508.gov | 1 |
459 | childwelfare.gov | 1 |
460 | .medlineplus.gov | 1 |
461 | pandemicflu.gov | 1 |
462 | .ohiopmp.gov | 1 |
463 | mdcourts.gov | 1 |
464 | .scdhhs.gov | 1 |
465 | biometrics.gov | 1 |
466 | .quic.gov | 1 |
467 | .stopfraudcolorado.gov | 1 |
468 | federalregister.gov | 1 |
469 | .usps.gov | 1 |
470 | .howardcountymd.gov | 1 |
471 | section508.gov | 1 |
472 | .hearttruth.gov | 1 |
473 | .sno-nsn.gov | 1 |
474 | .txcourts.gov | 1 |
475 | .usich.gov | 1 |
476 | .expectmore.gov | 1 |
477 | .usdol.gov | 1 |
478 | myloc.gov | 1 |
479 | .longbeach.gov | 1 |
480 | .azauditor.gov | 1 |
481 | .inl.gov | 1 |
482 | .sanantonio.gov | 1 |
483 | .nebraskalegislature.gov | 1 |
484 | oregon.gov | 1 |
# Event counts for top level domains by event type
# limited to W pages with external links
w_tld_query = """
SELECT REGEXP_EXTRACT({},'(\.[^\.]+)$',1) as tld, action, COUNT(*) AS count
FROM citationusage
WHERE wiki = 'enwiki'
AND page_id IN
(SELECT page_id FROM ryanmax.population_w_pages_with_extlinks)
{}
AND to_date(event_time) >= '{}'
AND to_date(event_time) <= '{}'
AND useragent_is_bot = FALSE
GROUP BY tld, action
ORDER BY COUNT(*) DESC
"""
w_tld_events = spark.sql(
w_tld_query.format(
parse_host_from_link_url,
event_exclusion_sql, start_date_string, end_date_string
))
w_tld_events_rdd = w_tld_events.rdd
w_tld_events_df = sqlContext.createDataFrame(w_tld_events_rdd)
w_tld_events_pandas = w_tld_events_df.toPandas()
tld_pda = w_tld_events_pandas.copy()
parsing_errors = tld_pda.loc[(tld_pda['tld'] == '') | (tld_pda['tld'].isnull())]
count_parsing_errors = parsing_errors['count'].sum()
total = tld_pda['count'].sum()
display(Markdown("Could not parse hostname/domain from {0} link_urls (first two rows) which represents {1:.2%} of all values.".format(count_parsing_errors,count_parsing_errors/total)))
# limit to counts of 1K or more
df_filtered = tld_pda.query('count>1000').copy()
# set precision before pivot
df_filtered['count'] = df_filtered['count'].map(lambda x: '{0:.0f}'.format(x))
df_filtered.pivot(index='tld', columns='action', values='count')
Could not parse hostname/domain from 74917 link_urls (first two rows) which represents 0.07% of all values.
action | extClick | fnClick | fnHover | upClick |
---|---|---|---|---|
tld | ||||
NaN | 21792 | 22848 | 27224 | None |
2074 | None | None | None | |
.122 | 4480 | None | None | None |
.132 | 3450 | None | None | None |
.173 | 3321 | None | None | None |
.194 | 2610 | None | None | None |
.208 | 2602 | None | None | None |
.27 | 4104 | None | None | None |
.5 | 1071 | None | None | None |
.ac | 2047 | None | None | None |
.ad | 1456 | None | None | None |
.ae | 30891 | None | None | None |
.aero | 20623 | None | None | None |
.af | 3455 | None | None | None |
.ai | 5139 | None | None | None |
.al | 7450 | None | None | None |
.am | 7781 | None | None | None |
.ao | 1434 | None | None | None |
.app | 1718 | None | None | None |
.ar | 24965 | None | None | None |
.asia | 3249 | None | None | None |
.at | 49233 | None | None | None |
.au | 639031 | None | None | None |
.az | 7928 | None | None | None |
.ba | 6667 | None | None | None |
.band | 1485 | None | None | None |
.basketball | 6781 | None | None | None |
.bd | 30033 | None | None | None |
.be | 55951 | None | None | None |
.bg | 11467 | None | None | None |
.bh | 2812 | None | None | None |
.biz | 16942 | None | None | None |
.blog | 1236 | None | None | None |
.bm | 1202 | None | None | None |
.bn | 4731 | None | None | None |
.bo | 1658 | None | None | None |
.br | 56845 | None | None | None |
.bt | 2847 | None | None | None |
.bw | 2187 | None | None | None |
.by | 7683 | None | None | None |
.bz | 1744 | None | None | None |
.ca | 531791 | None | None | None |
.canon | 1149 | None | None | None |
.cat | 12627 | None | None | None |
.cc | 14172 | None | None | None |
.cd | 1050 | None | None | None |
.ch | 103424 | None | None | None |
.church | 1577 | None | None | None |
.cl | 12667 | None | None | None |
.club | 5516 | None | None | None |
.cn | 134545 | None | None | None |
.co | 58620 | None | None | None |
.com | 28766412 | 48469 | 72195 | 1064 |
.company | 1133 | None | None | None |
.coop | 3443 | None | None | None |
.cr | 1782 | None | None | None |
.cu | 4020 | None | None | None |
.cx | 2777 | None | None | None |
.cy | 5950 | None | None | None |
.cymru | 1173 | None | None | None |
.cz | 43883 | None | None | None |
.de | 363660 | None | None | None |
.design | 2637 | None | None | None |
.dev | 8484 | None | None | None |
.dk | 56814 | None | None | None |
.do | 2772 | None | None | None |
.dz | 3559 | None | None | None |
.earth | 1381 | None | None | None |
.ec | 103453 | None | None | None |
.edu | 1467353 | None | None | None |
.ee | 13676 | None | None | None |
.eg | 10372 | None | None | None |
.es | 70851 | None | None | None |
.et | 6480 | None | None | None |
.eu | 143356 | None | None | None |
.eus | 2350 | None | None | None |
.fi | 45985 | None | None | None |
.fj | 1652 | None | None | None |
.fm | 11396 | None | None | None |
.fo | 3466 | None | None | None |
.foundation | 1078 | None | None | None |
.fr | 220212 | None | None | None |
.ga | 5764 | None | None | None |
.ge | 7977 | None | None | None |
.gg | 3122 | None | None | None |
.gh | 7884 | None | None | None |
.gi | 1286 | None | None | None |
.gl | 4818 | None | None | None |
.global | 2440 | None | None | None |
1884 | None | None | None | |
.gov | 1247591 | None | None | None |
.gr | 44695 | None | None | None |
.group | 7938 | None | None | None |
.gt | 1447 | None | None | None |
.hk | 39828 | None | None | None |
.hn | 1205 | None | None | None |
.hockey | 4308 | None | None | None |
.hr | 18834 | None | None | None |
.hu | 30829 | None | None | None |
.id | 24768 | None | None | None |
.ie | 114385 | None | None | None |
.il | 63303 | None | None | None |
.im | 3749 | None | None | None |
.in | 999248 | None | None | None |
.info | 158173 | None | None | None |
.int | 57368 | None | None | None |
.io | 89879 | None | None | None |
.iq | 3358 | None | None | None |
.ir | 18890 | None | None | None |
.is | 113277 | None | None | None |
.it | 184562 | None | None | None |
.jm | 2092 | None | None | None |
.jo | 4386 | None | None | None |
.jp | 284947 | None | None | None |
.ke | 12322 | None | None | None |
.kg | 1665 | None | None | None |
.kh | 2911 | None | None | None |
.kp | 2543 | None | None | None |
.kpmg | 1021 | None | None | None |
.kr | 82184 | None | None | None |
.kw | 3983 | None | None | None |
.ky | 1382 | None | None | None |
.kz | 8188 | None | None | None |
.la | 2325 | None | None | None |
.lb | 5291 | None | None | None |
.li | 4106 | None | None | None |
.life | 1950 | None | None | None |
.live | 1607 | None | None | None |
.lk | 29139 | None | None | None |
.london | 1609 | None | None | None |
.lt | 11414 | None | None | None |
.lu | 8334 | None | None | None |
.lv | 8623 | None | None | None |
.ly | 5341 | None | None | None |
.ma | 6002 | None | None | None |
.mc | 1237 | None | None | None |
.md | 4370 | None | None | None |
.me | 25845 | None | None | None |
.media | 2526 | None | None | None |
.mil | 139913 | None | None | None |
.mk | 7439 | None | None | None |
.mm | 4225 | None | None | None |
.mn | 3974 | None | None | None |
.mo | 2118 | None | None | None |
.movie | 5304 | None | None | None |
.ms | 1601 | None | None | None |
.mt | 5360 | None | None | None |
.mu | 3165 | None | None | None |
.museum | 2881 | None | None | None |
.mv | 2097 | None | None | None |
.mx | 43933 | None | None | None |
.my | 72376 | None | None | None |
.mz | 1217 | None | None | None |
.na | 3026 | None | None | None |
.name | 4507 | None | None | None |
.net | 1069963 | None | 1578 | None |
.news | 3673 | None | None | None |
.ng | 22097 | None | None | None |
.ni | 1124 | None | None | None |
.nl | 118028 | None | None | None |
.no | 63161 | None | None | None |
.np | 21760 | None | None | None |
.nu | 4502 | None | None | None |
.nyc | 2235 | None | None | None |
.nz | 126910 | None | None | None |
.om | 6502 | None | None | None |
.online | 2552 | None | None | None |
.org | 6708760 | 23036327 | 35825166 | 1109571 |
.pa | 1665 | None | None | None |
.party | 1252 | None | None | None |
.pe | 8242 | None | None | None |
.pg | 1549 | None | None | None |
.ph | 82864 | None | None | None |
.pk | 86222 | None | None | None |
.pl | 72733 | None | None | None |
.pr | 1387 | None | None | None |
.pro | 1002 | None | None | None |
.ps | 2258 | None | None | None |
.pt | 106694 | None | None | None |
.pw | 14387 | None | None | None |
.py | 1781 | None | None | None |
.qa | 6712 | None | None | None |
.report | 4014 | None | None | None |
.ro | 32895 | None | None | None |
.rs | 21969 | None | None | None |
.ru | 146320 | None | None | None |
.rw | 2501 | None | None | None |
.sa | 18170 | None | None | None |
.scot | 7222 | None | None | None |
.sd | 1945 | None | None | None |
.se | 99000 | None | None | None |
.sg | 59667 | None | None | None |
.sh | 4732 | None | None | None |
.si | 15588 | None | None | None |
.sk | 17903 | None | None | None |
.sm | 1026 | None | None | None |
.space | 2111 | None | None | None |
.sport | 1078 | None | None | None |
.su | 2733 | None | None | None |
.sv | 1011 | None | None | None |
.sy | 1809 | None | None | None |
.technology | 1085 | None | None | None |
.th | 21965 | None | None | None |
.tj | 1135 | None | None | None |
.tk | 1568 | None | None | None |
.tl | 1828 | None | None | None |
.tm | 1628 | None | None | None |
.tn | 2573 | None | None | None |
.to | 73995 | None | None | None |
.today | 10079 | None | None | None |
.tr | 48292 | None | None | None |
.travel | 2258 | None | None | None |
.tt | 2153 | None | None | None |
.tv | 108570 | None | None | None |
.tw | 63867 | None | None | None |
.tz | 9041 | None | None | None |
.ua | 35800 | None | None | None |
.ug | 7801 | None | None | None |
.uk | 2553969 | None | None | None |
.us | 224854 | None | None | None |
.uy | 3587 | None | None | None |
.uz | 3264 | None | None | None |
.va | 13992 | None | None | None |
.ve | 5778 | None | None | None |
.vn | 18353 | None | None | None |
.wales | 3228 | None | None | None |
.website | 2200 | None | None | None |
.world | 2962 | None | None | None |
.ws | 15411 | None | None | None |
.xxx | 5503 | None | None | None |
.xyz | 5895 | None | None | None |
.za | 86343 | None | None | None |
.zm | 1636 | None | None | None |
.zw | 4103 | None | None | None |
# Event counts for top level domains by event type
# limited to WP:M pages with external links
wpm_tld_query = """
SELECT REGEXP_EXTRACT({},'(\.[^\.]+)$',1) as tld, action, COUNT(*) AS count
FROM citationusage
WHERE wiki = 'enwiki'
AND page_id IN
(SELECT page_id FROM ryanmax.population_wpm_pages_with_extlinks)
{}
AND to_date(event_time) >= '{}'
AND to_date(event_time) <= '{}'
AND useragent_is_bot = FALSE
GROUP BY tld, action
ORDER BY COUNT(*) DESC
"""
wpm_tld_events = spark.sql(
wpm_tld_query.format(
parse_host_from_link_url,
event_exclusion_sql, start_date_string, end_date_string
))
wpm_tld_events_rdd = wpm_tld_events.rdd
wpm_tld_events_df = sqlContext.createDataFrame(wpm_tld_events_rdd)
wpm_tld_events_pandas = wpm_tld_events_df.toPandas()
tld_pda = wpm_tld_events_pandas.copy()
parsing_errors = tld_pda.loc[(tld_pda['tld'] == '') | (tld_pda['tld'].isnull())]
count_parsing_errors = parsing_errors['count'].sum()
total = tld_pda['count'].sum()
display(Markdown("Could not parse hostname/domain from {0} link_urls (first row) which represents {1:.2%} of all values.".format(count_parsing_errors,count_parsing_errors/total)))
# limit to counts of 100 or more
df_filtered = tld_pda.query('count>100').copy()
# set precision before pivot
df_filtered['count'] = df_filtered['count'].map(lambda x: '{0:.0f}'.format(x))
df_filtered.pivot(index='tld', columns='action', values='count')
Could not parse hostname/domain from 1372 link_urls (first row) which represents 0.04% of all values.
action | extClick | fnClick | fnHover | upClick |
---|---|---|---|---|
tld | ||||
NaN | 168 | 412 | 698 | None |
.ag | 120 | None | None | None |
.al | 170 | None | None | None |
.am | 139 | None | None | None |
.at | 263 | None | None | None |
.au | 7959 | None | None | None |
.be | 532 | None | None | None |
.br | 460 | None | None | None |
.ca | 14045 | None | None | None |
.ch | 2739 | None | None | None |
.cn | 1212 | None | None | None |
.co | 334 | None | None | None |
.com | 267229 | 3213 | 4246 | None |
.cz | 223 | None | None | None |
.de | 2849 | None | None | None |
.dk | 387 | None | None | None |
.edu | 41718 | None | None | None |
.es | 315 | None | None | None |
.eu | 3792 | None | None | None |
.fi | 232 | None | None | None |
.fr | 1850 | None | None | None |
.gov | 165336 | None | None | None |
.hk | 240 | None | None | None |
.hr | 139 | None | None | None |
.hu | 202 | None | None | None |
.ie | 992 | None | None | None |
.il | 286 | None | None | None |
.in | 3641 | None | None | None |
.info | 2811 | None | None | None |
.int | 24312 | None | None | None |
.io | 350 | None | None | None |
.ir | 251 | None | None | None |
.is | 1471 | None | None | None |
.it | 1947 | None | None | None |
.jp | 1875 | None | None | None |
.kr | 196 | None | None | None |
.kz | 103 | None | None | None |
.mil | 1133 | None | None | None |
.mp | 308 | None | None | None |
.mx | 166 | None | None | None |
.my | 219 | None | None | None |
.net | 8439 | None | 120 | None |
.nl | 934 | None | None | None |
.no | 2100 | None | None | None |
.nz | 992 | None | None | None |
.org | 212378 | 883997 | 1554886 | 49116 |
.ph | 228 | None | None | None |
.pk | 344 | None | None | None |
.pl | 1223 | None | None | None |
.pt | 149 | None | None | None |
.ro | 232 | None | None | None |
.ru | 741 | None | None | None |
.se | 906 | None | None | None |
.sg | 509 | None | None | None |
.today | 528 | None | None | None |
.tw | 282 | None | None | None |
.ua | 307 | None | None | None |
.ug | 111 | None | None | None |
.uk | 37474 | None | None | None |
.us | 1420 | None | None | None |
.za | 507 | None | None | None |
# Event counts for .gov top level domain by event type
# limited to W pages with external links
w_gov_query = """
SELECT REGEXP_EXTRACT({},'(\.[^\.]+\.[^\.]+)$',1) as domain, action, COUNT(*) AS count
FROM citationusage
WHERE wiki = 'enwiki'
AND page_id IN
(SELECT page_id FROM ryanmax.population_w_pages_with_extlinks)
{}
AND to_date(event_time) >= '{}'
AND to_date(event_time) <= '{}'
AND useragent_is_bot = FALSE
AND REGEXP_EXTRACT({},'(\.[^\.]+)$',1) = '.gov'
GROUP BY domain, action
ORDER BY COUNT(*) DESC
"""
w_gov_events = spark.sql(
w_gov_query.format(
parse_host_from_link_url,
event_exclusion_sql, start_date_string, end_date_string,
parse_host_from_link_url
))
w_gov_events_rdd = w_gov_events.rdd
w_gov_events_df = sqlContext.createDataFrame(w_gov_events_rdd)
w_gov_events_pandas = w_gov_events_df.toPandas()
tld_pda = w_gov_events_pandas.copy()
tld_pda.sort_values(by=['count'],ascending=False)[['domain','count']]
domain | count | |
---|---|---|
0 | .nih.gov | 187352 |
1 | .nps.gov | 71874 |
2 | .nasa.gov | 61757 |
3 | .loc.gov | 46585 |
4 | .census.gov | 36855 |
5 | .usgs.gov | 34132 |
6 | .ca.gov | 30849 |
7 | .house.gov | 29518 |
8 | .congress.gov | 23638 |
9 | .usda.gov | 23079 |
10 | .cia.gov | 19587 |
11 | .noaa.gov | 19268 |
12 | .state.gov | 19064 |
13 | .nist.gov | 18483 |
14 | .sec.gov | 16488 |
15 | .senate.gov | 16228 |
16 | .ed.gov | 15778 |
17 | .gpo.gov | 14966 |
18 | .epa.gov | 13277 |
19 | .archives.gov | 12975 |
20 | .fbi.gov | 12918 |
21 | .faa.gov | 12781 |
22 | .fcc.gov | 12495 |
23 | .fda.gov | 10912 |
24 | .irs.gov | 10733 |
25 | .whitehouse.gov | 9971 |
26 | .nyc.gov | 9763 |
27 | .justice.gov | 9561 |
28 | .cdc.gov | 8898 |
29 | .ny.gov | 8116 |
30 | .bop.gov | 7238 |
31 | .fws.gov | 6558 |
32 | .maryland.gov | 6364 |
33 | .dot.gov | 6112 |
34 | .wa.gov | 5630 |
35 | .virginia.gov | 5475 |
36 | .uscourts.gov | 5282 |
37 | .in.gov | 4941 |
38 | .ecfr.gov | 4923 |
39 | .supremecourt.gov | 4800 |
40 | .defense.gov | 4731 |
41 | .uspto.gov | 4586 |
42 | .ntsb.gov | 4556 |
43 | .dhs.gov | 4473 |
44 | .fjc.gov | 4460 |
45 | .ars-grin.gov | 4333 |
46 | .mass.gov | 4167 |
47 | .namus.gov | 3930 |
48 | .ky.gov | 3850 |
49 | .eia.gov | 3840 |
50 | .itis.gov | 3745 |
51 | .blm.gov | 3739 |
52 | .bls.gov | 3736 |
53 | loc.gov | 3715 |
54 | .texas.gov | 3629 |
55 | .ohio.gov | 3593 |
56 | .lbl.gov | 3313 |
57 | .energy.gov | 3307 |
58 | .usembassy.gov | 3285 |
59 | .lacounty.gov | 3087 |
60 | .ct.gov | 3067 |
61 | .cbp.gov | 3066 |
62 | .mo.gov | 3065 |
63 | .va.gov | 3019 |
64 | .usdoj.gov | 3017 |
65 | .utah.gov | 2926 |
66 | .doe.gov | 2905 |
67 | .sc.gov | 2758 |
68 | .federalreserve.gov | 2650 |
69 | .ssa.gov | 2627 |
70 | .nga.gov | 2523 |
71 | .dol.gov | 2425 |
72 | .fec.gov | 2399 |
73 | .treasury.gov | 2387 |
74 | .oregon.gov | 2361 |
75 | .uscis.gov | 2306 |
76 | .osha.gov | 2301 |
77 | .ftc.gov | 2192 |
78 | .wi.gov | 2190 |
79 | .michigan.gov | 2185 |
80 | .illinois.gov | 2135 |
81 | southbendin.gov | 1955 |
82 | .gao.gov | 1947 |
83 | .nsf.gov | 1935 |
84 | .federalregister.gov | 1789 |
85 | .ornl.gov | 1783 |
86 | .pa.gov | 1690 |
87 | .weather.gov | 1652 |
88 | .tn.gov | 1638 |
89 | .nv.gov | 1630 |
90 | .bea.gov | 1619 |
91 | .maine.gov | 1609 |
92 | .hud.gov | 1524 |
93 | .usbr.gov | 1510 |
94 | .nsa.gov | 1491 |
95 | .nrel.gov | 1477 |
96 | .hhs.gov | 1473 |
97 | .idaho.gov | 1468 |
98 | .mt.gov | 1461 |
99 | .ok.gov | 1452 |
100 | .colorado.gov | 1435 |
101 | .ncdcr.gov | 1404 |
102 | .ilga.gov | 1380 |
103 | .opm.gov | 1380 |
104 | .govinfo.gov | 1380 |
105 | .fema.gov | 1337 |
106 | .delaware.gov | 1328 |
107 | .lanl.gov | 1297 |
108 | .nj.gov | 1285 |
109 | .ohiodnr.gov | 1282 |
110 | .osti.gov | 1269 |
111 | .cancer.gov | 1253 |
112 | .anl.gov | 1252 |
113 | .usaid.gov | 1234 |
114 | .ncjrs.gov | 1213 |
115 | .wicourts.gov | 1210 |
116 | .seattle.gov | 1197 |
117 | energy.gov | 1194 |
118 | .hawaii.gov | 1173 |
119 | .sss.gov | 1166 |
120 | .arkansas.gov | 1159 |
121 | justice.gov | 1121 |
122 | .sandia.gov | 1114 |
123 | .nhtsa.gov | 1109 |
124 | .nysenate.gov | 1109 |
125 | .ga.gov | 1108 |
126 | .wisconsin.gov | 1102 |
127 | .eeoc.gov | 1090 |
128 | .miamidade.gov | 1088 |
129 | .nrc.gov | 1082 |
130 | .nd.gov | 1081 |
131 | whitehouse.gov | 1067 |
132 | .cbo.gov | 1046 |
133 | .gpoaccess.gov | 1033 |
134 | .nixonlibrary.gov | 1031 |
135 | .bts.gov | 1030 |
136 | .dc.gov | 1025 |
137 | .sba.gov | 1004 |
138 | .doc.gov | 993 |
139 | clinicaltrials.gov | 980 |
140 | .gsa.gov | 980 |
141 | .fdic.gov | 974 |
142 | .usa.gov | 972 |
143 | .ncparks.gov | 954 |
144 | .neh.gov | 934 |
145 | .bjs.gov | 931 |
146 | .az.gov | 920 |
147 | .panynj.gov | 914 |
148 | .usmint.gov | 909 |
149 | .llnl.gov | 886 |
150 | .sandiego.gov | 877 |
151 | .ice.gov | 865 |
152 | .alaska.gov | 826 |
153 | hawaii.gov | 816 |
154 | .nh.gov | 809 |
155 | .azgfd.gov | 796 |
156 | .ms.gov | 777 |
157 | .alabama.gov | 777 |
158 | .sd.gov | 763 |
159 | .fnal.gov | 754 |
160 | .ourdocuments.gov | 750 |
161 | .atf.gov | 742 |
162 | .nysed.gov | 742 |
163 | .kingcounty.gov | 726 |
164 | .dni.gov | 718 |
165 | .austintexas.gov | 717 |
166 | .iowa.gov | 706 |
167 | .georgia.gov | 700 |
168 | .ri.gov | 691 |
169 | .peacecorps.gov | 685 |
170 | .bldrdoc.gov | 681 |
171 | .tva.gov | 680 |
172 | .fdlp.gov | 669 |
173 | .secretservice.gov | 666 |
174 | .usmarshals.gov | 662 |
175 | .bnl.gov | 661 |
176 | .doi.gov | 657 |
177 | .vermont.gov | 653 |
178 | .louisiana.gov | 648 |
179 | .ffiec.gov | 622 |
180 | .cityofboston.gov | 622 |
181 | .fairfaxcounty.gov | 620 |
182 | .azleg.gov | 613 |
183 | .nwcg.gov | 605 |
184 | .mn.gov | 603 |
185 | .mi.gov | 597 |
186 | fbi.gov | 597 |
187 | .consumerfinance.gov | 584 |
188 | .pr.gov | 570 |
189 | .iowadnr.gov | 568 |
191 | .treas.gov | 566 |
190 | .myfloridahouse.gov | 566 |
192 | .nationalservice.gov | 564 |
193 | .ne.gov | 560 |
194 | .fueleconomy.gov | 560 |
195 | .md.gov | 556 |
196 | .cpsc.gov | 556 |
197 | .txcourts.gov | 535 |
198 | .dea.gov | 534 |
199 | .ntis.gov | 532 |
200 | .tennessee.gov | 526 |
201 | dhs.gov | 524 |
202 | .copyright.gov | 520 |
203 | .aoc.gov | 518 |
204 | medlineplus.gov | 517 |
205 | .houstontx.gov | 516 |
206 | .phila.gov | 511 |
207 | .nycourts.gov | 497 |
208 | census.gov | 495 |
209 | michigan.gov | 485 |
210 | .nc.gov | 476 |
211 | .gps.gov | 473 |
212 | .baltimorecity.gov | 466 |
213 | .fincen.gov | 461 |
214 | wisconsindot.gov | 459 |
215 | federalreserve.gov | 458 |
216 | .nationalmap.gov | 457 |
217 | .clarkcountynv.gov | 452 |
218 | .uscg.gov | 442 |
219 | .nashville.gov | 439 |
220 | .inl.gov | 435 |
221 | .treasurydirect.gov | 431 |
222 | .cms.gov | 430 |
223 | .nifc.gov | 428 |
224 | .abmc.gov | 428 |
225 | miramarfl.gov | 426 |
226 | .us-cert.gov | 425 |
227 | .samhsa.gov | 423 |
228 | .la.gov | 422 |
229 | texas.gov | 413 |
230 | .azdot.gov | 401 |
231 | .wv.gov | 400 |
232 | outdoornebraska.gov | 395 |
233 | .donotcall.gov | 383 |
234 | .bia.gov | 380 |
235 | .phoenix.gov | 380 |
236 | .nebraska.gov | 380 |
237 | malegislature.gov | 380 |
238 | .cabq.gov | 379 |
239 | .honolulu.gov | 378 |
240 | .transportation.gov | 366 |
241 | .ks.gov | 364 |
242 | .nola.gov | 359 |
243 | flsenate.gov | 359 |
244 | ustr.gov | 356 |
245 | .commerce.gov | 350 |
246 | .nara.gov | 349 |
247 | .detroitmi.gov | 344 |
248 | .ncdot.gov | 343 |
249 | .doleta.gov | 340 |
250 | .export.gov | 340 |
251 | .clinicaltrials.gov | 339 |
252 | ilga.gov | 337 |
253 | .scstatehouse.gov | 337 |
254 | .centennialofflight.gov | 336 |
255 | .malegislature.gov | 333 |
256 | .occ.gov | 331 |
257 | .indy.gov | 330 |
258 | .sanantonio.gov | 329 |
259 | .ferc.gov | 328 |
260 | .invasivespeciesinfo.gov | 322 |
261 | .flsenate.gov | 318 |
262 | .bart.gov | 313 |
263 | .usps.gov | 308 |
264 | .9-11commission.gov | 306 |
265 | .recreation.gov | 306 |
266 | .milwaukee.gov | 306 |
267 | .cftc.gov | 306 |
268 | .portlandoregon.gov | 300 |
269 | .tsa.gov | 296 |
270 | .usitc.gov | 293 |
271 | .txdot.gov | 292 |
272 | .genome.gov | 289 |
273 | .childwelfare.gov | 288 |
274 | .raleighnc.gov | 285 |
275 | .ussc.gov | 285 |
276 | .pnnl.gov | 284 |
277 | charlottenc.gov | 284 |
278 | mn.gov | 280 |
279 | .energystar.gov | 272 |
280 | .nmlegis.gov | 272 |
281 | .navajo-nsn.gov | 271 |
282 | georgia.gov | 269 |
283 | .guam.gov | 266 |
284 | .sanjoseca.gov | 264 |
285 | nj.gov | 262 |
288 | nasa.gov | 261 |
286 | speaker.gov | 261 |
287 | .moneyfactory.gov | 261 |
289 | sanantonio.gov | 260 |
290 | .fbo.gov | 254 |
291 | .oregonlegislature.gov | 252 |
292 | .sam.gov | 251 |
293 | moneyfactory.gov | 249 |
294 | epa.gov | 248 |
295 | .regulations.gov | 245 |
296 | nyc.gov | 243 |
297 | .southbendin.gov | 242 |
298 | .csb.gov | 241 |
299 | .hrsa.gov | 239 |
300 | .cincinnati-oh.gov | 237 |
301 | .atlantaga.gov | 237 |
302 | .america.gov | 235 |
303 | .digitalpreservation.gov | 233 |
304 | .speaker.gov | 230 |
305 | .globalchange.gov | 228 |
306 | .erie.gov | 227 |
307 | .plano.gov | 224 |
308 | usaid.gov | 224 |
309 | copyright.gov | 223 |
310 | .data.gov | 221 |
311 | .reaganlibrary.gov | 220 |
312 | .nro.gov | 220 |
313 | .safercar.gov | 218 |
314 | .monroecounty.gov | 217 |
315 | .pima.gov | 217 |
316 | .ustr.gov | 213 |
318 | stlouis-mo.gov | 210 |
317 | dc.gov | 210 |
319 | supremecourt.gov | 209 |
320 | .usap.gov | 208 |
321 | .uspis.gov | 207 |
322 | .longbeach.gov | 205 |
323 | .ncdps.gov | 203 |
324 | .prescott-az.gov | 203 |
325 | .traviscountytx.gov | 202 |
326 | .msha.gov | 201 |
327 | .ncua.gov | 201 |
328 | phoenix.gov | 201 |
329 | .deldot.gov | 198 |
330 | .fresno.gov | 197 |
331 | .azcorrections.gov | 196 |
332 | .pppl.gov | 195 |
333 | nhtsa.gov | 194 |
334 | .fletc.gov | 193 |
335 | .louisvilleky.gov | 193 |
336 | .bpa.gov | 192 |
337 | .cnss.gov | 191 |
338 | coloradosprings.gov | 191 |
339 | kcmo.gov | 191 |
340 | .loudoun.gov | 190 |
341 | .sbcounty.gov | 190 |
342 | .stlouis-mo.gov | 188 |
343 | .jobcorps.gov | 188 |
344 | .socialsecurity.gov | 186 |
345 | .osc.gov | 186 |
346 | .americaslibrary.gov | 186 |
347 | .usmission.gov | 184 |
348 | .montgomerycountymd.gov | 184 |
350 | .trade.gov | 183 |
349 | .elpasotexas.gov | 183 |
351 | .arts.gov | 181 |
352 | .nationalatlas.gov | 180 |
353 | .intelink.gov | 180 |
354 | .columbus.gov | 179 |
355 | .ehawaii.gov | 177 |
356 | .ttb.gov | 174 |
357 | .usajobs.gov | 174 |
358 | ntsb.gov | 173 |
359 | .roundrocktexas.gov | 173 |
360 | .augustaga.gov | 172 |
361 | .pnl.gov | 171 |
362 | .usconsulate.gov | 170 |
363 | .newmexico.gov | 168 |
364 | .howardcountymd.gov | 168 |
365 | .capitol.gov | 167 |
366 | .jimmycarterlibrary.gov | 166 |
367 | .uscc.gov | 164 |
368 | .wvdnr.gov | 164 |
369 | .ohioattorneygeneral.gov | 159 |
370 | .kansas.gov | 158 |
371 | .clarkstonga.gov | 158 |
372 | .cambridgema.gov | 157 |
373 | .nassaucountyny.gov | 155 |
374 | arts.gov | 155 |
375 | .ada.gov | 155 |
376 | .tsp.gov | 154 |
377 | .okc.gov | 153 |
378 | .iowadot.gov | 152 |
379 | .fordlibrarymuseum.gov | 151 |
380 | .charleston-sc.gov | 149 |
381 | .maricopa.gov | 149 |
382 | .boston.gov | 148 |
383 | .suffolkcountyny.gov | 147 |
384 | archives.gov | 147 |
385 | .eugene-or.gov | 146 |
386 | .ameslab.gov | 145 |
387 | usmint.gov | 143 |
388 | cdc.gov | 143 |
389 | .sedonaaz.gov | 143 |
390 | .ins.gov | 142 |
391 | .brevardfl.gov | 142 |
392 | .baltimorecountymd.gov | 142 |
393 | .minneapolismn.gov | 140 |
394 | nationalmap.gov | 139 |
395 | pittsburghpa.gov | 139 |
396 | .ncifcrf.gov | 139 |
397 | .tucsonaz.gov | 138 |
399 | .rrb.gov | 137 |
398 | .lasvegasnevada.gov | 137 |
400 | .flhsmv.gov | 136 |
401 | lasvegasnevada.gov | 136 |
402 | .nlrb.gov | 136 |
403 | .palmspringsca.gov | 133 |
404 | .santafenm.gov | 132 |
405 | .alexandriava.gov | 131 |
406 | .dccourts.gov | 130 |
407 | .cap.gov | 129 |
408 | .missouri.gov | 129 |
409 | .pbgc.gov | 128 |
410 | .vi.gov | 128 |
411 | .fdot.gov | 128 |
414 | opm.gov | 127 |
415 | .fpds.gov | 127 |
413 | virginiageneralassembly.gov | 127 |
412 | federalregister.gov | 127 |
416 | .stpaul.gov | 125 |
417 | tsa.gov | 124 |
418 | .mms.gov | 124 |
419 | .il.gov | 123 |
420 | .ashevillenc.gov | 123 |
423 | .iad.gov | 122 |
424 | .memphistn.gov | 122 |
422 | .harriscountytx.gov | 122 |
421 | .birminghamal.gov | 122 |
425 | .fishwatch.gov | 121 |
426 | alaska.gov | 121 |
427 | .id.gov | 120 |
428 | .wichita.gov | 120 |
429 | louisvilleky.gov | 119 |
430 | nist.gov | 119 |
431 | .gsaadvantage.gov | 118 |
432 | .ohiohouse.gov | 117 |
433 | .nij.gov | 117 |
434 | .nypa.gov | 117 |
435 | lanl.gov | 117 |
436 | .tncourts.gov | 117 |
437 | wyoming.gov | 116 |
438 | .santabarbaraca.gov | 116 |
439 | .roanokeva.gov | 115 |
440 | .choosemyplate.gov | 115 |
441 | .azsos.gov | 115 |
442 | fincen.gov | 114 |
443 | .cityofkeywest-fl.gov | 114 |
444 | .climate.gov | 114 |
450 | .airnow.gov | 113 |
448 | nyassembly.gov | 113 |
449 | .opic.gov | 113 |
446 | .acquisition.gov | 113 |
447 | .americansamoa.gov | 113 |
445 | .flhealth.gov | 113 |
451 | .tempe.gov | 112 |
452 | .ready.gov | 112 |
453 | atlantaga.gov | 111 |
454 | .fhfa.gov | 110 |
455 | .iowacourts.gov | 110 |
456 | .drugabuse.gov | 110 |
460 | .time.gov | 109 |
461 | ftc.gov | 109 |
458 | .coloradosprings.gov | 109 |
459 | acquisition.gov | 109 |
457 | .nsopr.gov | 109 |
462 | .chattanooga.gov | 108 |
463 | maine.gov | 108 |
464 | .ic3.gov | 108 |
467 | bea.gov | 107 |
468 | .norfolk.gov | 107 |
465 | ipcc-wg2.gov | 107 |
466 | kingcounty.gov | 107 |
469 | .mcc.gov | 106 |
470 | .americorps.gov | 106 |
471 | colorado.gov | 105 |
472 | .pittsburghpa.gov | 105 |
473 | aviationweather.gov | 105 |
474 | .uscirf.gov | 105 |
475 | .cookcountyil.gov | 105 |
476 | .usccr.gov | 105 |
477 | .ustreas.gov | 104 |
478 | .codot.gov | 104 |
482 | .usagm.gov | 103 |
483 | .miamibeachfl.gov | 103 |
479 | .goes-r.gov | 103 |
481 | .osac.gov | 103 |
480 | .cdfifund.gov | 103 |
484 | .exim.gov | 102 |
485 | .schohariecounty-ny.gov | 102 |
486 | .unicor.gov | 102 |
487 | .usability.gov | 102 |
488 | .medicare.gov | 101 |
489 | .savannahga.gov | 101 |
490 | .aqmd.gov | 100 |
491 | .nea.gov | 100 |
492 | .springfieldmo.gov | 100 |
493 | .scottsdaleaz.gov | 100 |
496 | .acl.gov | 99 |
495 | .aoa.gov | 99 |
494 | gatlinburgtn.gov | 99 |
497 | .attorneygeneral.gov | 98 |
498 | .sandiegocounty.gov | 98 |
499 | .greenvillenc.gov | 97 |
... | ... | ... |
3566 | usembassy-mexico.gov | 2 |
3564 | .lavernia-tx.gov | 2 |
3533 | .fairviewnc.gov | 2 |
3563 | .buffalony.gov | 2 |
3534 | .galvestontx.gov | 2 |
3535 | cantonohio.gov | 2 |
3536 | manchesternh.gov | 2 |
3537 | .westamptonnj.gov | 2 |
3538 | andoverma.gov | 2 |
3539 | .gocc.gov | 2 |
3540 | .sunnyside-wa.gov | 2 |
3541 | cranberryisles-me.gov | 2 |
3542 | pcah.gov | 2 |
3543 | .middletonnh.gov | 2 |
3544 | .padillabay.gov | 2 |
3545 | flauditor.gov | 2 |
3546 | .sialkot.gov | 2 |
3547 | .buildingamerica.gov | 2 |
3548 | .twpoceannj.gov | 2 |
3549 | .takepride.gov | 2 |
3550 | .webstercountymo.gov | 2 |
3551 | .morningsidemd.gov | 2 |
3552 | iowaculture.gov | 2 |
3553 | redcliff-nsn.gov | 2 |
3554 | .northsiouxcity-sd.gov | 2 |
3555 | globalchange.gov | 2 |
3556 | pompanobeachfl.gov | 2 |
3557 | .rosebudcountymt.gov | 2 |
3558 | remember.gov | 2 |
3559 | .nuclear.gov | 2 |
3560 | .ridgefieldnj.gov | 2 |
3561 | .smartcheck.gov | 2 |
3562 | presidentialinnovationfellows.gov | 2 |
3467 | .esc.gov | 2 |
3484 | .milanohio.gov | 2 |
3465 | .townofvassnc.gov | 2 |
3368 | .consumer.gov | 2 |
3370 | .nhl.gov | 2 |
3371 | gpo.gov | 2 |
3372 | .app.gov | 2 |
3373 | oceancommission.gov | 2 |
3374 | .florence-nj.gov | 2 |
3375 | .newjersey.gov | 2 |
3376 | dublinohiousa.gov | 2 |
3377 | .azland.gov | 2 |
3378 | montgomerycountyga.gov | 2 |
3379 | franklincountyga.gov | 2 |
3380 | nepa.gov | 2 |
3381 | .highlandil.gov | 2 |
3382 | columbianaohio.gov | 2 |
3383 | .greencastlepa.gov | 2 |
3384 | .upto.gov | 2 |
3385 | woodlandhills-ut.gov | 2 |
3386 | .lakesitetn.gov | 2 |
3387 | feedthefuture.gov | 2 |
3388 | .apec2011.gov | 2 |
3389 | invasivespeciesinfo.gov | 2 |
3390 | .battlefieldmo.gov | 2 |
3391 | .lanesborough-ma.gov | 2 |
3392 | realestatesales.gov | 2 |
3393 | customs.gov | 2 |
3394 | .ohiocourtofclaims.gov | 2 |
3395 | .ceciltonmd.gov | 2 |
3396 | normanparkga.gov | 2 |
3397 | .smartcard.gov | 2 |
3398 | okhouse.gov | 2 |
3369 | .wartimecontracting.gov | 2 |
3367 | .warrencountyky.gov | 2 |
3400 | portvincent-la.gov | 2 |
3366 | makinghomeaffordable.gov | 2 |
3464 | beachhaven-nj.gov | 2 |
3337 | .nagb.gov | 2 |
3338 | .pentagon.gov | 2 |
3339 | supremecourtus.gov | 2 |
3340 | .fortluptonco.gov | 2 |
3341 | .azhousing.gov | 2 |
3342 | .murrietaca.gov | 2 |
3343 | bioethics.gov | 2 |
3344 | bellevuewa.gov | 2 |
3345 | medicare.gov | 2 |
3346 | .californiadesert.gov | 2 |
3347 | .yarrowpointwa.gov | 2 |
3348 | .daughertytownship-pa.gov | 2 |
3349 | merchantvillenj.gov | 2 |
3350 | .dayton-me.gov | 2 |
3351 | .townofnortheastny.gov | 2 |
3352 | rosebudcountymt.gov | 2 |
3353 | cupcao.gov | 2 |
3354 | nea.gov | 2 |
3355 | .oceancommission.gov | 2 |
3356 | .bixbyok.gov | 2 |
3357 | .noscamnc.gov | 2 |
3358 | brooklynwi.gov | 2 |
3359 | .usis.gov | 2 |
3361 | savanna-il.gov | 2 |
3362 | .dalton-ma.gov | 2 |
3363 | .chathamtownship-nj.gov | 2 |
3364 | .beaumonttexas.gov | 2 |
3365 | nantucket-ma.gov | 2 |
3399 | crystalmn.gov | 2 |
3360 | 5aday.gov | 2 |
3401 | .clintontownship-mi.gov | 2 |
3433 | .arnet.gov | 2 |
3435 | .govloans.gov | 2 |
3436 | .mrgo.gov | 2 |
3437 | .sturtevant-wi.gov | 2 |
3438 | .ngi.gov | 2 |
3439 | .williamsoncounty-tn.gov | 2 |
3440 | acwi.gov | 2 |
3441 | sacandfoxnation-nsn.gov | 2 |
3442 | .cmts.gov | 2 |
3443 | .greenwoodcounty-sc.gov | 2 |
3444 | bja.gov | 2 |
3445 | .fff.gov | 2 |
3446 | .dsac.gov | 2 |
3447 | newarkde.gov | 2 |
3448 | daniabeachfl.gov | 2 |
3449 | .amtrakoig.gov | 2 |
3450 | paristn.gov | 2 |
3452 | .ich.gov | 2 |
3453 | lowerpaxton-pa.gov | 2 |
3454 | roswell-nm.gov | 2 |
3455 | .lyndonks.gov | 2 |
3456 | shivelyky.gov | 2 |
3457 | .ashvilleohio.gov | 2 |
3458 | .villageofkensingtonny.gov | 2 |
3459 | iowa.gov | 2 |
3460 | .nortonva.gov | 2 |
3461 | ise.gov | 2 |
3462 | miamibeachfl.gov | 2 |
3402 | .claycountymn.gov | 2 |
3463 | .shakopeemn.gov | 2 |
3434 | consumeraction.gov | 2 |
3451 | strategicsourcing.gov | 2 |
3432 | .de.gov | 2 |
3417 | .ttbonline.gov | 2 |
3404 | .tallapoosaga.gov | 2 |
3431 | ustraderep.gov | 2 |
3405 | .wilmingtonma.gov | 2 |
3406 | marysvillewa.gov | 2 |
3407 | .innocencecommission-nc.gov | 2 |
3408 | sc.gov | 2 |
3409 | .telework.gov | 2 |
3411 | .cityofhouston.gov | 2 |
3412 | .citizenservices.gov | 2 |
3413 | .goshen-ohio.gov | 2 |
3414 | .orangecountync.gov | 2 |
3415 | .westminstermd.gov | 2 |
3416 | .sustainability.gov | 2 |
3410 | pflugervilletx.gov | 2 |
3418 | azlibrary.gov | 2 |
3425 | .protectyourmove.gov | 2 |
3430 | .performance.gov | 2 |
3429 | .ndop.gov | 2 |
3419 | vetsuccess.gov | 2 |
3428 | .identitytheft.gov | 2 |
3427 | .azdfi.gov | 2 |
3426 | maroaillinois.gov | 2 |
3403 | .chowancounty-nc.gov | 2 |
3423 | usgeo.gov | 2 |
3422 | cooperativeconservation.gov | 2 |
3421 | .ohioagriculture.gov | 2 |
3420 | townofwillsborony.gov | 2 |
3424 | wethersfieldct.gov | 2 |
3826 | amberalert.gov | 1 |
3818 | .christiancountymo.gov | 1 |
3825 | .bureaucounty-il.gov | 1 |
3824 | .biosecurityboard.gov | 1 |
3823 | .cantontwp-oh.gov | 1 |
3822 | taylortx.gov | 1 |
3821 | .tomballtx.gov | 1 |
3820 | .baycounty-mi.gov | 1 |
3819 | .nibin.gov | 1 |
3816 | .coast2050.gov | 1 |
3809 | .estrategy.gov | 1 |
3817 | .trinityal.gov | 1 |
3815 | .bunkerhilltx.gov | 1 |
3814 | .mrlc.gov | 1 |
3813 | greenvillenc.gov | 1 |
3811 | waverlyhallga.gov | 1 |
3810 | .defendamerica.gov | 1 |
3808 | virginiacapitol.gov | 1 |
3812 | .harpercountyks.gov | 1 |
3839 | .nalusda.gov | 1 |
3827 | .saddlerockny.gov | 1 |
3828 | lakegroveny.gov | 1 |
3845 | .taxreformpanel.gov | 1 |
3806 | dedham-ma.gov | 1 |
3844 | .watertown-ma.gov | 1 |
3843 | .fireplan.gov | 1 |
3842 | broadbandmap.gov | 1 |
3841 | imls.gov | 1 |
3840 | .brookhavenny.gov | 1 |
3838 | drought.gov | 1 |
3837 | .fitchburgwi.gov | 1 |
3836 | ourdocuments.gov | 1 |
3835 | .georgewbushlibrary.gov | 1 |
3834 | web-services.gov | 1 |
3833 | .pelhamalabama.gov | 1 |
3832 | morriscountynj.gov | 1 |
3831 | .nyassembly.gov | 1 |
3830 | .goshen-oh.gov | 1 |
3829 | ncjrs.gov | 1 |
3807 | hilliardohio.gov | 1 |
3775 | .stat-usa.gov | 1 |
3805 | fgdc.gov | 1 |
3784 | .winneconnewi.gov | 1 |
3782 | azot.gov | 1 |
3781 | socialcirclega.gov | 1 |
3780 | .challenge.gov | 1 |
3779 | .jacksonwy.gov | 1 |
3778 | usaspending.gov | 1 |
3777 | cityofhaywardwi.gov | 1 |
3776 | .chcoc.gov | 1 |
3774 | frtr.gov | 1 |
3773 | sullivancountynh.gov | 1 |
3772 | hempsteadny.gov | 1 |
3771 | .noa.gov | 1 |
3770 | .aftac.gov | 1 |
3769 | ridgecrest-ca.gov | 1 |
3768 | .stocktonca.gov | 1 |
3767 | .vetbiz.gov | 1 |
3766 | hialeahfl.gov | 1 |
3847 | clermontcountyohio.gov | 1 |
3783 | .lyman-me.gov | 1 |
3785 | .oceangate-nj.gov | 1 |
3804 | .azinvestor.gov | 1 |
3786 | .washingtonnc.gov | 1 |
3803 | .azclimatechange.gov | 1 |
3802 | .daniabeachfl.gov | 1 |
3801 | .kentcountymi.gov | 1 |
3800 | nh.gov | 1 |
3799 | .micmac-nsn.gov | 1 |
3798 | .getyouhome.gov | 1 |
3797 | fdlp.gov | 1 |
3796 | usptocareers.gov | 1 |
3795 | .americanlatinomuseum.gov | 1 |
3794 | .tsunami.gov | 1 |
3793 | mesaaz.gov | 1 |
3792 | sedonaaz.gov | 1 |
3791 | climatetechnology.gov | 1 |
3790 | yonkersny.gov | 1 |
3789 | ucrdatatool.gov | 1 |
3788 | heritageabroad.gov | 1 |
3787 | .stopfraud.gov | 1 |
3846 | .iedison.gov | 1 |
3911 | .miamicountyin.gov | 1 |
3848 | tnpromise.gov | 1 |
3901 | hooveralabama.gov | 1 |
3909 | .woodburymn.gov | 1 |
3908 | .psob.gov | 1 |
3907 | wheelingil.gov | 1 |
3906 | .acqnet.gov | 1 |
3905 | .medlineplus.gov | 1 |
3904 | yelmwa.gov | 1 |
3903 | .wcnyh.gov | 1 |
3902 | salisburync.gov | 1 |
3900 | .firescience.gov | 1 |
3849 | athol-ma.gov | 1 |
3899 | .basslakewi.gov | 1 |
3898 | .ems.gov | 1 |
3897 | buenavistaco.gov | 1 |
3896 | scsenate.gov | 1 |
3895 | uspto.gov | 1 |
3894 | .nwbc.gov | 1 |
3893 | .dh.gov | 1 |
3892 | .wsdot.gov | 1 |
3910 | start2farm.gov | 1 |
3764 | cendi.gov | 1 |
3912 | hud.gov | 1 |
3913 | .surfcitync.gov | 1 |
3930 | .heritageny.gov | 1 |
3929 | ctoc.gov | 1 |
3928 | mesagrandeband-nsn.gov | 1 |
3927 | .housedemocrats.gov | 1 |
3926 | indianaffairs.gov | 1 |
3925 | arlingtonma.gov | 1 |
3924 | fedcir.gov | 1 |
3923 | tetoncountyidaho.gov | 1 |
3922 | .mcminncountytn.gov | 1 |
3921 | .science360.gov | 1 |
3920 | .sourcewell-mn.gov | 1 |
3919 | .mndnr.gov | 1 |
3918 | ncs.gov | 1 |
3917 | marlborough-ma.gov | 1 |
3916 | .bremertonwa.gov | 1 |
3915 | swinomish-nsn.gov | 1 |
3914 | .cityofwestonlakes-tx.gov | 1 |
3891 | azdoa.gov | 1 |
3890 | .gsaig.gov | 1 |
3889 | mtbs.gov | 1 |
3868 | .washingtoncountyks.gov | 1 |
3866 | .daviecountync.gov | 1 |
3865 | .ppirs.gov | 1 |
3864 | westonwi.gov | 1 |
3863 | boemre.gov | 1 |
3862 | .scconsumer.gov | 1 |
3861 | .fredenbergtwp-mn.gov | 1 |
3860 | culpepercounty.gov | 1 |
3859 | monroewa.gov | 1 |
3858 | .manitousprings-co.gov | 1 |
3857 | .ardot.gov | 1 |
3856 | .virginiageneralassembly.gov | 1 |
3855 | .eastborough-ks.gov | 1 |
3854 | .putnamcountytn.gov | 1 |
3853 | .heyworth-il.gov | 1 |
3852 | .unioncountyil.gov | 1 |
3851 | oceangate-nj.gov | 1 |
3850 | .crimevictims.gov | 1 |
3867 | .lakevillemn.gov | 1 |
3869 | fhfa.gov | 1 |
3888 | .greenecountyms.gov | 1 |
3870 | blainecounty-mt.gov | 1 |
3887 | .sdi.gov | 1 |
3886 | .flcrc.gov | 1 |
3885 | tsunami.gov | 1 |
3884 | roanecountytn.gov | 1 |
3883 | simontontexas.gov | 1 |
3882 | .healthierus.gov | 1 |
3881 | .lincolnbicentennial.gov | 1 |
3880 | troyny.gov | 1 |
3879 | .morrillcountyne.gov | 1 |
3878 | .capitolflags.gov | 1 |
3877 | onrr.gov | 1 |
3876 | peacecorps.gov | 1 |
3875 | .willingboronj.gov | 1 |
3874 | ohiocourtofclaims.gov | 1 |
3873 | mitigationcommission.gov | 1 |
3872 | .results.gov | 1 |
3871 | roundrocktexas.gov | 1 |
3765 | .azftf.gov | 1 |
3699 | lansingmi.gov | 1 |
3763 | .fsam.gov | 1 |
3647 | .crt2014-2024review.gov | 1 |
3655 | harrisburgsd.gov | 1 |
3654 | thayercountyne.gov | 1 |
3653 | .thehistoryofareacodes.gov | 1 |
3652 | .disabilityinfo.gov | 1 |
3651 | .girardkansas.gov | 1 |
3650 | springfieldohio.gov | 1 |
3649 | .middletownrancheria-nsn.gov | 1 |
3648 | .frogweb.gov | 1 |
3646 | .americusga.gov | 1 |
3762 | salemva.gov | 1 |
3645 | .yadkincounty.gov | 1 |
3644 | .civilianresponsecorps.gov | 1 |
3643 | americorps.gov | 1 |
3642 | .jwod.gov | 1 |
3641 | illinoisattorneygeneral.gov | 1 |
3640 | .richlandsnc.gov | 1 |
3639 | .delawaretownshippa.gov | 1 |
3638 | ottawaks.gov | 1 |
3656 | .brunswickcountync.gov | 1 |
3657 | fnal.gov | 1 |
3658 | .floresvilletx.gov | 1 |
3659 | .artreasury.gov | 1 |
3676 | .ohiojudicialcenter.gov | 1 |
3675 | champaignil.gov | 1 |
3674 | .greenwichct.gov | 1 |
3673 | .ellijay-ga.gov | 1 |
3672 | .cityoflincoln-il.gov | 1 |
3671 | fargond.gov | 1 |
3670 | .ashgrovemo.gov | 1 |
3669 | wyomingmi.gov | 1 |
3668 | .asc.gov | 1 |
3667 | .mandauecity.gov | 1 |
3666 | restorethegulf.gov | 1 |
3665 | starkcountyohio.gov | 1 |
3664 | lymansc.gov | 1 |
3663 | .hanovercounty.gov | 1 |
3662 | dallasga.gov | 1 |
3661 | stpaul.gov | 1 |
3660 | fueleconomy.gov | 1 |
3637 | thomas.gov | 1 |
3636 | viennava.gov | 1 |
3635 | manufacturing.gov | 1 |
3614 | losgatosca.gov | 1 |
3612 | .waveland-ms.gov | 1 |
3611 | longhillnj.gov | 1 |
3610 | johnscreekga.gov | 1 |
3609 | .pauma-nsn.gov | 1 |
3608 | .belleriveacresmo.gov | 1 |
3607 | nashville.gov | 1 |
3606 | aqmd.gov | 1 |
3605 | .financialresearch.gov | 1 |
3604 | bpa.gov | 1 |
3603 | wheelingwv.gov | 1 |
3602 | .goddardks.gov | 1 |
3601 | childstats.gov | 1 |
3600 | anl.gov | 1 |
3599 | .arklegaudit.gov | 1 |
3598 | braintreema.gov | 1 |
3597 | .azarts.gov | 1 |
3596 | .marine.gov | 1 |
3613 | .disasterhelp.gov | 1 |
3615 | takomaparkmd.gov | 1 |
3634 | virginia.gov | 1 |
3616 | .supreme-court.gov | 1 |
3633 | .oregonvotes.gov | 1 |
3632 | .presidiotrust.gov | 1 |
3631 | .scribner-ne.gov | 1 |
3630 | ucore.gov | 1 |
3629 | columbiasc.gov | 1 |
3628 | .limerick-me.gov | 1 |
3627 | .jaspercountyin.gov | 1 |
3626 | .eastfishkillny.gov | 1 |
3625 | .omhrc.gov | 1 |
3624 | .durban.gov | 1 |
3623 | .abilityone.gov | 1 |
3622 | .cfoc.gov | 1 |
3621 | roanokeva.gov | 1 |
3620 | .flu.gov | 1 |
3619 | tennesseepromise.gov | 1 |
3618 | bethlehem-pa.gov | 1 |
3617 | .ma.gov | 1 |
3677 | auburnmaine.gov | 1 |
3678 | collegenavigator.gov | 1 |
3679 | needhamma.gov | 1 |
3742 | .stpauls.gov | 1 |
3740 | louisianaentertainment.gov | 1 |
3739 | knoxvilletn.gov | 1 |
3738 | .otaywater.gov | 1 |
3737 | .measuretn.gov | 1 |
3736 | .ninilchiktribe-nsn.gov | 1 |
3735 | .egrpra.gov | 1 |
3734 | dcfra.gov | 1 |
3733 | .manisteecountymi.gov | 1 |
3732 | chilmarkma.gov | 1 |
3731 | .maplegrovemn.gov | 1 |
3730 | sdsos.gov | 1 |
3729 | .mnhousing.gov | 1 |
3728 | surgeongeneral.gov | 1 |
3727 | .ihaveaplaniowa.gov | 1 |
3726 | .njmvc.gov | 1 |
3725 | pa.gov | 1 |
3724 | .maharashtra.gov | 1 |
3741 | mlkday.gov | 1 |
3743 | whitehousedrugpolicy.gov | 1 |
3722 | .sequatchiecounty-tn.gov | 1 |
3744 | .byesvilleoh.gov | 1 |
3761 | .beecavetexas.gov | 1 |
3760 | .azbn.gov | 1 |
3759 | .mich.gov | 1 |
3758 | pawneerock-ks.gov | 1 |
3757 | csosa.gov | 1 |
3756 | truman.gov | 1 |
3755 | galenaks.gov | 1 |
3754 | .blainecounty-mt.gov | 1 |
3753 | greenecountymo.gov | 1 |
3752 | .swinomish-nsn.gov | 1 |
3751 | sbcounty.gov | 1 |
3750 | .plandomeheights-ny.gov | 1 |
3749 | nativeamericanheritagemonth.gov | 1 |
3748 | azliquor.gov | 1 |
3747 | .edgarcounty-il.gov | 1 |
3746 | cindy.gov | 1 |
3745 | .supremecourtofohio.gov | 1 |
3723 | .frelinghuysentwp-nj.gov | 1 |
3721 | jamesmadison.gov | 1 |
3680 | ouraycountyco.gov | 1 |
3700 | .deserttortoise.gov | 1 |
3697 | .icbemp.gov | 1 |
3696 | .galvestoncountytx.gov | 1 |
3695 | cityoftitusvillepa.gov | 1 |
3694 | .azgohs.gov | 1 |
3693 | .capitolheightsmd.gov | 1 |
3692 | .belaireks.gov | 1 |
3691 | tukwilawa.gov | 1 |
3690 | .eastcoventry-pa.gov | 1 |
3689 | .childcare.gov | 1 |
3688 | .mundytwp-mi.gov | 1 |
3687 | .encinitasca.gov | 1 |
3686 | njsda.gov | 1 |
3685 | .druidhillsky.gov | 1 |
3684 | symbols.gov | 1 |
3683 | .juvenilecouncil.gov | 1 |
3682 | .ypt-nsn.gov | 1 |
3681 | .summervillesc.gov | 1 |
3698 | .whitehouseoh.gov | 1 |
3701 | .fnc.gov | 1 |
3720 | uscirf.gov | 1 |
3702 | .kingsburyny.gov | 1 |
3719 | .westlinnoregon.gov | 1 |
3718 | .pnt.gov | 1 |
3717 | rowe-ma.gov | 1 |
3716 | maricopa.gov | 1 |
3715 | .townshipoftabernacle-nj.gov | 1 |
3714 | .911commission.gov | 1 |
3713 | .conshohockenpa.gov | 1 |
3712 | .sausalito.gov | 1 |
3711 | .projectsafechildhood.gov | 1 |
3710 | .cityofhokah-mn.gov | 1 |
3709 | chandleraz.gov | 1 |
3708 | cityofcanalfulton-oh.gov | 1 |
3707 | .alabamapublichealth.gov | 1 |
3706 | .whcoa.gov | 1 |
3705 | cliftonaz.gov | 1 |
3704 | scijinks.gov | 1 |
3703 | .okgeosurvey1.gov | 1 |
3931 | sno-nsn.gov | 1 |
3932 rows × 2 columns
# Event counts for .gov top level domain by event type
# limited to WP:M pages with external links
wpm_gov_query = """
SELECT REGEXP_EXTRACT({},'(\.[^\.]+\.[^\.]+)$',1) as domain, action, COUNT(*) AS count
FROM citationusage
WHERE wiki = 'enwiki'
AND page_id IN
(SELECT page_id FROM ryanmax.population_wpm_pages_with_extlinks)
{}
AND to_date(event_time) >= '{}'
AND to_date(event_time) <= '{}'
AND useragent_is_bot = FALSE
AND REGEXP_EXTRACT({},'(\.[^\.]+)$',1) = '.gov'
GROUP BY domain, action
ORDER BY COUNT(*) DESC
"""
wpm_gov_events = spark.sql(
wpm_gov_query.format(
parse_host_from_link_url,
event_exclusion_sql, start_date_string, end_date_string,
parse_host_from_link_url
))
wpm_gov_events_rdd = wpm_gov_events.rdd
wpm_gov_events_df = sqlContext.createDataFrame(wpm_gov_events_rdd)
wpm_gov_events_pandas = wpm_gov_events_df.toPandas()
wpm_gov_events_pandas.sort_values(by=['count'],ascending=False)[['domain','count']]
domain | count | |
---|---|---|
0 | .nih.gov | 117605 |
1 | .cdc.gov | 11238 |
2 | .fda.gov | 9536 |
3 | .cancer.gov | 3703 |
4 | medlineplus.gov | 2302 |
5 | .hhs.gov | 1601 |
6 | .cms.gov | 1228 |
7 | .epa.gov | 1157 |
8 | .gpo.gov | 793 |
9 | .va.gov | 621 |
10 | .usda.gov | 600 |
11 | .ahrq.gov | 566 |
12 | .house.gov | 522 |
13 | .drugabuse.gov | 506 |
14 | .samhsa.gov | 468 |
15 | .congress.gov | 442 |
16 | .cia.gov | 432 |
17 | .senate.gov | 410 |
18 | .womenshealth.gov | 394 |
19 | clinicaltrials.gov | 390 |
20 | .ohio.gov | 382 |
21 | .fema.gov | 362 |
22 | .ca.gov | 333 |
23 | .hrsa.gov | 326 |
24 | .loc.gov | 318 |
25 | .genome.gov | 274 |
26 | .sec.gov | 252 |
27 | .nasa.gov | 245 |
28 | .medicaid.gov | 245 |
29 | .osha.gov | 231 |
30 | .healthcare.gov | 225 |
31 | .irs.gov | 218 |
32 | .usdoj.gov | 211 |
33 | .fbi.gov | 203 |
34 | .ny.gov | 193 |
35 | .census.gov | 190 |
36 | .clinicaltrials.gov | 190 |
37 | .govinfo.gov | 189 |
38 | .medicare.gov | 165 |
39 | .bls.gov | 160 |
41 | .cbo.gov | 142 |
40 | .guideline.gov | 142 |
42 | .in.gov | 141 |
43 | .federalregister.gov | 139 |
44 | .justice.gov | 137 |
45 | .ed.gov | 131 |
46 | .wa.gov | 127 |
47 | .surgeongeneral.gov | 111 |
48 | .dc.gov | 108 |
49 | .nist.gov | 104 |
50 | .gao.gov | 92 |
51 | .whitehouse.gov | 90 |
52 | .dot.gov | 89 |
53 | .uspto.gov | 88 |
54 | .fcc.gov | 80 |
55 | .ornl.gov | 77 |
56 | .usaid.gov | 76 |
57 | .dol.gov | 75 |
58 | .usphs.gov | 74 |
59 | health.gov | 74 |
60 | .archives.gov | 72 |
62 | .ada.gov | 70 |
61 | .ncjrs.gov | 70 |
63 | .oregon.gov | 69 |
64 | .usgs.gov | 69 |
65 | cdc.gov | 67 |
66 | .noaa.gov | 66 |
67 | .medlineplus.gov | 64 |
68 | .ihs.gov | 63 |
69 | .healthit.gov | 63 |
70 | .hiv.gov | 62 |
72 | .vermont.gov | 60 |
71 | .faa.gov | 60 |
73 | .bnl.gov | 59 |
74 | .lacounty.gov | 56 |
75 | .eeoc.gov | 54 |
76 | .vaccines.gov | 54 |
77 | .mass.gov | 54 |
78 | .nola.gov | 52 |
79 | .ftc.gov | 50 |
80 | .nsf.gov | 50 |
81 | .doe.gov | 49 |
83 | .ssa.gov | 48 |
82 | .miamidade.gov | 48 |
84 | .idaho.gov | 47 |
85 | .ars-grin.gov | 46 |
86 | .uscourts.gov | 43 |
87 | .juvenilecouncil.gov | 43 |
88 | .childwelfare.gov | 42 |
89 | .nhtsa.gov | 41 |
90 | .dea.gov | 40 |
91 | .ems.gov | 40 |
92 | .lanl.gov | 39 |
93 | .osti.gov | 39 |
94 | .bjs.gov | 38 |
95 | .michigan.gov | 37 |
96 | .nlm.gov | 37 |
97 | .virginia.gov | 37 |
98 | .health.gov | 36 |
99 | .utah.gov | 35 |
100 | .dhhs.gov | 34 |
101 | .doleta.gov | 33 |
102 | .nyc.gov | 31 |
103 | .sandiego.gov | 30 |
104 | .state.gov | 29 |
105 | .phila.gov | 27 |
107 | mn.gov | 27 |
108 | .nrc.gov | 27 |
106 | .healthypeople.gov | 27 |
109 | .safercar.gov | 26 |
110 | healthypeople.gov | 26 |
111 | .anl.gov | 26 |
112 | .aids.gov | 25 |
113 | .lbl.gov | 25 |
116 | .energy.gov | 24 |
117 | .supremecourt.gov | 24 |
114 | .nps.gov | 24 |
115 | .treasury.gov | 24 |
118 | .ne.gov | 23 |
119 | .wisconsin.gov | 23 |
120 | womenshealth.gov | 20 |
121 | .milwaukee.gov | 20 |
122 | .riversideca.gov | 20 |
125 | nj.gov | 19 |
124 | .usembassy.gov | 19 |
123 | .tennessee.gov | 19 |
127 | .illinois.gov | 18 |
128 | .fdlp.gov | 18 |
126 | .ky.gov | 18 |
129 | .choosemyplate.gov | 17 |
130 | .usa.gov | 17 |
131 | cityofboston.gov | 17 |
132 | .fitness.gov | 17 |
136 | .nara.gov | 16 |
137 | .flu.gov | 16 |
135 | .csb.gov | 16 |
134 | healthvermont.gov | 16 |
133 | .regulations.gov | 16 |
138 | .tsa.gov | 15 |
139 | .cpsc.gov | 14 |
140 | bioethics.gov | 14 |
141 | .nv.gov | 14 |
142 | .pandemicflu.gov | 14 |
143 | .maryland.gov | 14 |
147 | .ntsb.gov | 13 |
148 | .metrokc.gov | 13 |
144 | .marylandhealthconnection.gov | 13 |
146 | .organdonor.gov | 13 |
145 | .phe.gov | 13 |
149 | .whitehousedrugpolicy.gov | 12 |
150 | .colorado.gov | 12 |
151 | .delaware.gov | 12 |
152 | .mn.gov | 12 |
157 | .kingcounty.gov | 11 |
160 | .nh.gov | 11 |
159 | .mentalhealth.gov | 11 |
158 | .gpoaccess.gov | 11 |
155 | .nysed.gov | 11 |
156 | .fws.gov | 11 |
154 | organdonor.gov | 11 |
153 | guideline.gov | 11 |
167 | .hud.gov | 10 |
166 | cancer.gov | 10 |
165 | .medpac.gov | 10 |
164 | .stopfraudcolorado.gov | 10 |
163 | .louisvilleky.gov | 10 |
161 | .fedcenter.gov | 10 |
162 | michigan.gov | 10 |
168 | .ncdhhs.gov | 9 |
169 | healthit.gov | 9 |
170 | .msha.gov | 9 |
175 | .foodsafety.gov | 8 |
178 | .wi.gov | 8 |
177 | section508.gov | 8 |
176 | healthfinder.gov | 8 |
173 | .psc.gov | 8 |
174 | .opm.gov | 8 |
172 | .consumer.gov | 8 |
171 | .ct.gov | 8 |
183 | .4woman.gov | 7 |
186 | .pa.gov | 7 |
184 | .visitthecapitol.gov | 7 |
185 | .treas.gov | 7 |
182 | .ecfr.gov | 7 |
179 | .defense.gov | 7 |
180 | smokefree.gov | 7 |
181 | .ready.gov | 7 |
192 | .azdhs.gov | 6 |
197 | .mypyramid.gov | 6 |
196 | .maine.gov | 6 |
195 | .ncd.gov | 6 |
193 | .insurekidsnow.gov | 6 |
194 | .mo.gov | 6 |
191 | biometrics.gov | 6 |
190 | .ga.gov | 6 |
189 | .cavc.gov | 6 |
188 | drugabuse.gov | 6 |
187 | .nj.gov | 6 |
205 | .iowa.gov | 5 |
211 | guidelines.gov | 5 |
210 | .seattle.gov | 5 |
209 | .hawaii.gov | 5 |
208 | .bop.gov | 5 |
207 | .pepfar.gov | 5 |
206 | healthcare.gov | 5 |
203 | .dni.gov | 5 |
204 | .nitrd.gov | 5 |
202 | .cityofboston.gov | 5 |
201 | .healthindicators.gov | 5 |
200 | .scstatehouse.gov | 5 |
199 | .sc.gov | 5 |
198 | .mi.gov | 5 |
221 | .sandiegocounty.gov | 4 |
229 | .newportbeachca.gov | 4 |
228 | .transportation.gov | 4 |
227 | .healthfinder.gov | 4 |
226 | .neh.gov | 4 |
225 | .hanford.gov | 4 |
224 | surgeongeneral.gov | 4 |
222 | .ri.gov | 4 |
223 | .ohiopmp.gov | 4 |
220 | .scdhhs.gov | 4 |
218 | .arc.gov | 4 |
217 | nih.gov | 4 |
216 | .commerce.gov | 4 |
215 | .pmi.gov | 4 |
214 | .ks.gov | 4 |
213 | maine.gov | 4 |
219 | .pcip.gov | 4 |
212 | genome.gov | 4 |
248 | phila.gov | 3 |
244 | .usap.gov | 3 |
245 | .ilsos.gov | 3 |
246 | .nij.gov | 3 |
252 | .globalhealth.gov | 3 |
249 | aids.gov | 3 |
250 | .nbii.gov | 3 |
251 | usphs.gov | 3 |
253 | .lymenh.gov | 3 |
242 | .nyhealth.gov | 3 |
243 | azdhs.gov | 3 |
247 | .scdhec.gov | 3 |
241 | locatorplus.gov | 3 |
234 | .osac.gov | 3 |
240 | .bja.gov | 3 |
230 | .traviscountytx.gov | 3 |
231 | .baltimorecountymd.gov | 3 |
233 | usich.gov | 3 |
232 | .fido.gov | 3 |
235 | .mentalhealthcommission.gov | 3 |
236 | .uscis.gov | 3 |
237 | .gsa.gov | 3 |
238 | loc.gov | 3 |
239 | .tn.gov | 3 |
278 | .ok.gov | 2 |
272 | .mt.gov | 2 |
273 | mdcourts.gov | 2 |
274 | .jccbi.gov | 2 |
275 | .fjc.gov | 2 |
276 | azleg.gov | 2 |
277 | .sbir.gov | 2 |
284 | .az.gov | 2 |
279 | costamesaca.gov | 2 |
280 | .uscirf.gov | 2 |
281 | senate.gov | 2 |
282 | .invasivespeciesinfo.gov | 2 |
283 | .dhs.gov | 2 |
270 | .texas.gov | 2 |
271 | .fnal.gov | 2 |
285 | .wv.gov | 2 |
269 | .nutrition.gov | 2 |
260 | .myfloridahouse.gov | 2 |
268 | .itis.gov | 2 |
254 | .jct.gov | 2 |
255 | .aoa.gov | 2 |
256 | .llnl.gov | 2 |
258 | .challenge.gov | 2 |
259 | .section508.gov | 2 |
257 | .nc.gov | 2 |
261 | .alabamapublichealth.gov | 2 |
262 | .fec.gov | 2 |
263 | federalregister.gov | 2 |
264 | isotopes.gov | 2 |
265 | cbo.gov | 2 |
266 | .wvlegislature.gov | 2 |
267 | epa.gov | 2 |
317 | .ojjdp.gov | 1 |
309 | .ngc.gov | 1 |
310 | .usbr.gov | 1 |
311 | .kdheks.gov | 1 |
312 | .azleg.gov | 1 |
313 | .usmission.gov | 1 |
314 | .us-cert.gov | 1 |
315 | .america.gov | 1 |
316 | .samsha.gov | 1 |
325 | .omhrc.gov | 1 |
318 | .guidelines.gov | 1 |
319 | .usps.gov | 1 |
320 | riversideca.gov | 1 |
321 | .arkansas.gov | 1 |
322 | .federalreserve.gov | 1 |
323 | .acus.gov | 1 |
324 | .howardcountymd.gov | 1 |
307 | .la.gov | 1 |
326 | .newjersey.gov | 1 |
327 | .nebraskalegislature.gov | 1 |
308 | flsenate.gov | 1 |
299 | .selectagents.gov | 1 |
306 | .fbo.gov | 1 |
294 | .costamesaca.gov | 1 |
286 | energy.gov | 1 |
287 | .recovery.gov | 1 |
288 | .nationalservice.gov | 1 |
289 | .healthdata.gov | 1 |
290 | .inl.gov | 1 |
291 | childwelfare.gov | 1 |
292 | 4women.gov | 1 |
293 | .sno-nsn.gov | 1 |
295 | .dna.gov | 1 |
305 | .alabama.gov | 1 |
296 | gao.gov | 1 |
297 | .wvdnr.gov | 1 |
298 | .cstx.gov | 1 |
300 | .neglecteddiseases.gov | 1 |
301 | .vt.gov | 1 |
302 | .usccr.gov | 1 |
303 | .hearttruth.gov | 1 |
304 | .nationalchildrensstudy.gov | 1 |
328 | .copyright.gov | 1 |