changeset 335:d083d089f55e trim

sic
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Mon, 02 Mar 2026 13:32:18 +0000
parents 252cf1263ad0
children a2918f19d9ed
files results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1994 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1995 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1996 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1997 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1998 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1999 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2000 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2001 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2002 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2003 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2004 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2005 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2006 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2007 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2008 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2009 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2010 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2011 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2012 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2013 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2014 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2015 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2016 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2017 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2018 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2019 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2020 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2021 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2022 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2023 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2024 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2025 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2026 results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/no_LM results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/oob
diffstat 35 files changed, 662 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1994	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,16 @@
+ 2483573	200
+   41161	302
+   20220	404
+   17692	304
+    5589	301
+    2576	403
+    1984	500
+     964	406
+     788	503
+     112	401
+      55	410
+      55	307
+      48	303
+       2	400
+       1	502
+       1	999
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1995	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,3 @@
+ 2070	200
+   32	304
+    3	404
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1996	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,3 @@
+ 7333	200
+   95	304
+   15	404
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1997	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,8 @@
+ 48012	200
+   825	302
+   437	304
+    36	404
+    13	500
+    10	301
+     2	406
+     1	202
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1998	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,6 @@
+ 12210	200
+   264	304
+   186	302
+     4	404
+     1	301
+     1	403
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/1999	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,7 @@
+ 21980	200
+  1323	404
+   751	304
+    75	302
+    22	401
+     5	301
+     3	500
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2000	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,7 @@
+ 56000	200
+  1517	301
+   801	304
+   349	403
+    89	404
+    69	302
+     1	500
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2001	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,8 @@
+ 74657	200
+  2603	304
+   994	301
+   748	404
+   570	500
+    77	403
+    76	302
+    10	401
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2002	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,8 @@
+ 73273	200
+  5089	304
+   930	404
+   117	403
+    89	500
+    13	302
+    11	401
+    11	301
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2003	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,8 @@
+ 115926	200
+  10042	304
+   1941	403
+    921	404
+     38	500
+     25	301
+     16	401
+      5	302
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2004	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,9 @@
+ 138295	200
+  11505	304
+   1056	403
+    959	404
+    922	500
+    670	302
+    182	401
+     42	301
+      2	204
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2005	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,12 @@
+ 567693	200
+  10993	304
+   5596	404
+   1868	403
+    163	301
+    150	500
+     84	302
+     60	401
+     17	406
+     13	503
+      2	300
+      1	410
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2006	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,10 @@
+ 272565	200
+  11630	304
+  10093	404
+   1760	403
+    294	500
+    184	406
+     89	301
+     73	302
+     65	401
+      3	503
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2007	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,12 @@
+ 351429	200
+  15655	304
+   6241	404
+   5066	403
+   1213	302
+   1206	401
+   1057	406
+    281	500
+     90	301
+     17	503
+      2	410
+      1	307
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2008	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,13 @@
+ 511292	200
+  20106	304
+  11814	404
+   6800	403
+   1394	406
+    341	500
+    278	302
+    114	401
+    109	301
+      9	503
+      3	410
+      3	502
+      2	307
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2009	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,13 @@
+ 783747	200
+  26153	304
+  18990	404
+  10146	403
+   4294	301
+   3045	406
+    694	302
+    447	500
+    166	401
+     59	503
+      8	307
+      5	410
+      1	205
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2010	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,15 @@
+ 974148	200
+  42786	304
+  16226	404
+   7036	403
+   2872	301
+   2090	406
+   1415	302
+    873	500
+    429	401
+    381	503
+    160	502
+    126	303
+     12	410
+      5	307
+      1	300
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2011	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,16 @@
+ 1221745	200
+   46703	304
+   46265	404
+   13473	302
+    6877	403
+    3799	406
+    2017	503
+    1012	500
+     989	301
+     362	401
+      24	303
+      13	410
+      13	400
+       8	307
+       4	206
+       1	502
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2012	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,18 @@
+ 1508212	200
+   76575	304
+   21560	404
+   19040	403
+    9193	503
+    4953	500
+    3572	401
+    2379	301
+    2360	406
+    1830	302
+     270	502
+      37	410
+      37	303
+      19	400
+       5	511
+       5	504
+       3	307
+       1	300
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2013	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,16 @@
+ 2079425	200
+  102132	304
+   26935	404
+   15392	403
+    9154	503
+    2613	301
+    2451	500
+    1868	406
+    1611	302
+     709	401
+     198	509
+     104	303
+      22	410
+      11	502
+       7	307
+       3	400
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2014	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,19 @@
+ 2314259	200
+  111795	304
+   62249	404
+   49394	403
+   13209	503
+    5375	301
+    3411	500
+    2959	302
+    2452	406
+    1510	401
+      99	410
+      67	307
+      60	303
+      34	400
+      17	508
+      14	502
+       7	504
+       1	522
+       1	509
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2015	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,19 @@
+ 3196726	200
+  129075	304
+   57032	404
+   23513	403
+   14827	503
+   11412	302
+    5638	301
+    3645	406
+    2852	500
+    1033	401
+     425	502
+     283	410
+      91	400
+      23	307
+      19	303
+       3	405
+       2	504
+       1	508
+       1	300
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2016	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,20 @@
+ 4064426	200
+  315860	304
+   94003	404
+   36968	503
+   34392	403
+   16559	302
+   11765	500
+    5895	301
+    4755	406
+    2269	502
+    1284	410
+    1227	401
+     292	400
+      41	303
+      39	424
+      29	307
+       3	300
+       2	501
+       1	504
+       1	509
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2017	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,25 @@
+ 6150778	200
+  291050	304
+  138445	404
+   70456	403
+   47254	503
+   12893	500
+   11914	301
+    8545	302
+    6230	406
+    3700	410
+    2643	401
+    1546	400
+    1266	307
+     790	502
+     358	504
+     272	303
+      31	412
+       3	402
+       3	542
+       3	509
+       2	508
+       2	520
+       1	206
+       1	415
+       1	501
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2018	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,28 @@
+ 22491410	200
+   689541	304
+   384163	404
+   156317	403
+    81277	503
+    25072	301
+    17550	500
+    15831	302
+     6294	401
+     5635	406
+     3763	405
+     2421	423
+     2216	410
+     1304	504
+      973	502
+      233	400
+      187	307
+      145	507
+       84	402
+       47	303
+       46	501
+       11	509
+        7	409
+        3	300
+        3	508
+        2	426
+        1	544
+        1	422
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2019	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,67 @@
+ 474315629	200
+   4392345	304
+   4348541	301
+   4190587	404
+   1823136	302
+   1111292	403
+   1008572	500
+    971736	503
+    685443	303
+    259805	410
+     66753	406
+     27275	401
+     23015	307
+     14921	429
+      8881	502
+      4413	400
+      3796	451
+      2118	504
+      2035	409
+      1680	405
+      1634	509
+      1331	202
+       956	423
+       942	300
+       726	413
+       410	418
+       313	534
+       193	206
+       143	538
+       117	555
+       117	550
+       111	505
+       101	501
+        78	422
+        49	520
+        49	402
+        41	532
+        29	533
+        25	464
+        25	508
+        24	602
+        21	510
+        20	522
+        14	530
+        12	308
+        11	660
+         7	411
+         4	512
+         4	201
+         3	521
+         3	529
+         2	204
+         2	455
+         2	478
+         2	205
+         2	888
+         1	511
+         1	416
+         1	564
+         1	700
+         1	560
+         1	218
+         1	226
+         1	670
+         1	412
+         1	203
+         1	408
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2020	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,7 @@
+ 8044	200
+  247	301
+   99	404
+   81	302
+    1	409
+    1	403
+    1	503
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2021	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,4 @@
+ 113	200
+  12	301
+  10	404
+   1	302
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2022	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,1 @@
+ 77	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2023	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,1 @@
+ 14	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2024	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,1 @@
+ 5	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2025	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,1 @@
+ 11	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/2026	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,1 @@
+ 4	200
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/no_LM	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,254 @@
+ 2504850205	200
+  204447701	301
+  128848288	302
+  109284298	404
+   29604478	430
+   24187736	403
+   15640195	304
+   13555836	500
+    9258409	503
+    6468728	406
+    4761306	522
+    3373877	303
+    2522109	429
+    2494746	307
+    2407501	410
+    1953953	502
+    1520096	400
+    1418161	521
+     851278	401
+     652982	520
+     538942	308
+     447916	405
+     372617	402
+     262847	504
+     245976	523
+     184869	203
+     182571	999
+     138976	408
+     125253	530
+     118608	526
+      98632	416
+      79594	508
+      72451	448
+      49130	451
+      43331	204
+      41680	202
+      40000	525
+      39801	418
+      37217	423
+      35767	409
+      31947	509
+      30553	300
+      26541	424
+      24797	511
+      22223	206
+      14113	412
+      14090	501
+      13458	507
+      11634	444
+       9004	422
+       8183	479
+       8161	414
+       7972	421
+       6366	524
+       6204	201
+       6132	555
+       5823	312
+       5096	456
+       4850	244
+       3344	773
+       3093	533
+       2719	415
+       2444	505
+       2216	512
+       2078	564
+       2025	420
+       1920	419
+       1335	653
+       1158	477
+       1027	599
+        821	600
+        558	0
+        550	760
+        523	550
+        473	417
+        407	510
+        371	205
+        360	256
+        326	499
+        324	220
+        320	426
+        318	462
+        317	463
+        301	445
+        298	490
+        258	280
+        251	496
+        245	211
+        240	210
+        208	603
+        193	434
+        187	226
+        185	440
+        183	552
+        173	605
+        171	449
+        167	534
+        160	493
+        151	413
+        138	411
+        136	590
+        134	447
+        132	460
+        132	481
+        130	920
+        130	666
+        130	399
+        129	541
+        127	425
+        117	144
+        110	350
+        109	222
+        108	587
+         96	428
+         93	478
+         88	471
+         86	830
+         83	452
+         80	470
+         76	709
+         75	208
+         71	601
+         69	553
+         66	126
+         64	443
+         63	498
+         57	801
+         55	660
+         53	535
+         53	103
+         50	466
+         46	591
+         41	557
+         40	299
+         38	513
+         38	651
+         36	751
+         36	450
+         35	527
+         34	596
+         33	719
+         32	580
+         30	592
+         29	808
+         29	670
+         25	464
+         23	531
+         21	495
+         21	544
+         20	454
+         20	506
+         20	705
+         20	577
+         19	270
+         18	543
+         18	538
+         17	442
+         17	604
+         17	145
+         17	305
+         16	667
+         16	207
+         15	700
+         15	630
+         14	900
+         14	560
+         13	432
+         12	441
+         12	101
+         12	850
+         11	609
+         11	532
+         11	529
+         11	779
+         10	613
+         10	800
+         10	474
+         10	475
+          9	484
+          9	213
+          9	1
+          9	469
+          9	589
+          9	102
+          8	514
+          8	461
+          8	671
+          8	770
+          7	209
+          7	306
+          7	777
+          7	242
+          7	476
+          6	559
+          6	602
+          6	393
+          6	433
+          6	595
+          5	562
+          5	622
+          5	619
+          5	380
+          5	453
+          5	910
+          4	431
+          4	5
+          4	497
+          4	480
+          4	780
+          3	310
+          3	576
+          3	750
+          3	803
+          3	561
+          3	309
+          3	539
+          3	901
+          3	214
+          3	607
+          3	566
+          3	711
+          2	701
+          2	959
+          2	397
+          2	298
+          2	518
+          2	2
+          2	472
+          2	492
+          2	326
+          2	427
+          2	781
+          2	704
+          2	233
+          1	551
+          1	283
+          1	692
+          1	118
+          1	542
+          1	320
+          1	250
+          1	908
+          1	382
+          1	435
+          1	494
+          1	245
+          1	260
+          1	702
+          1	40
+          1	457
+          1	267
+          1	771
+          1	486
+          1	334
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/results/CC-MAIN-2019-35/warc_lmhx/statuses_by_year/oob	Mon Mar 02 13:32:18 2026 +0000
@@ -0,0 +1,6 @@
+ 18302	200
+  5240	302
+   390	500
+    42	301
+    17	404
+     6	201