Website:
Corpus:

digitalcorpora.org Reports

Available Reports:

DARPA SAFEDOCS and UNSAFEDOCS downloads over past 90 days

SELECT substr(s3key,1,64) as s3_prefix, round(sum(bytes_sent)/max(bytes)) as count, min(dtime) as first,max(dtime) as last FROM downloads LEFT JOIN downloadable ON downloads.did = downloadable.id WHERE s3key like 'corpora/files/CC%%' and dtime > DATE_ADD(NOW(), INTERVAL -90 DAY) GROUP BY s3_prefix HAVING count>=1 ORDER BY s3_prefix

s3_prefix count first last
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/cc-hosts- 35 2024-02-23 00:00:00 2024-05-19 16:24:12
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/cc-proven 45 2024-02-23 00:00:00 2024-05-22 02:02:15
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/pdfinfo-2 33 2024-02-23 00:00:00 2024-05-22 00:03:09
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/README.md 509 2024-02-23 00:00:00 2024-05-22 14:48:13
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/tika-2023 35 2024-02-23 00:00:00 2024-05-22 03:03:47
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/tika-with 9 2024-02-23 00:00:00 2024-05-19 23:25:21
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/README.md 1974 2024-02-23 00:00:00 2024-05-22 09:25:37
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/0000-0999 13303 2024-02-23 00:00:00 2024-05-22 14:58:35
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/1000-1999 7479 2024-02-23 00:00:00 2024-05-22 14:48:34
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/2000-2999 7908 2024-02-23 00:00:00 2024-05-22 14:43:29
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/3000-3999 8804 2024-02-23 00:00:00 2024-05-22 14:22:28
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/4000-4999 7265 2024-02-23 00:00:00 2024-05-22 14:59:42
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/5000-5999 6526 2024-02-23 00:00:00 2024-05-22 14:54:57
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/6000-6999 8319 2024-02-23 00:00:00 2024-05-22 14:38:11
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/7000-7999 6817 2024-02-23 00:00:00 2024-05-22 14:23:44
corpora/files/CC-MAIN-2021-31-UNSAFE/common-crawl/common-crawl-x 59 2024-02-25 00:00:00 2024-05-21 22:58:09
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-icc.zip 10 2024-02-25 00:00:00 2024-05-22 03:35:46
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-nitf-01.zip 5 2024-02-29 00:00:00 2024-05-14 18:40:14
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-nitf-02.zip 3 2024-03-13 14:21:53 2024-05-09 07:26:08
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x00 14 2024-02-25 00:00:00 2024-05-20 23:46:44
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x01 12 2024-04-12 16:03:27 2024-05-20 12:39:34
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x02 8 2024-04-05 04:44:42 2024-05-21 01:39:09
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x03 5 2024-04-12 16:57:29 2024-05-20 12:41:01
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x04 10 2024-04-12 17:26:27 2024-05-20 13:43:27
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x05 15 2024-04-12 17:48:48 2024-05-20 12:43:09
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x06 17 2024-04-12 18:10:41 2024-05-20 12:42:16
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x07 17 2024-04-12 18:31:01 2024-05-20 11:32:31
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x08 17 2024-04-12 18:51:45 2024-05-20 11:55:11
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x09 11 2024-04-12 19:15:26 2024-05-20 12:40:39
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x10 9 2024-04-13 11:32:04 2024-05-20 12:50:40
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x11 9 2024-04-13 11:52:18 2024-05-20 12:11:38
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x12 9 2024-04-13 12:13:21 2024-05-20 16:05:56
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x13 10 2024-04-13 12:34:13 2024-05-20 12:08:12
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x14 9 2024-04-13 12:54:16 2024-05-20 12:41:33
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x15 9 2024-04-13 13:12:21 2024-05-20 11:55:31
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x16 10 2024-03-13 06:11:52 2024-05-20 12:37:22
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x17 10 2024-04-13 13:54:24 2024-05-20 11:52:33
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x18 11 2024-04-13 14:13:05 2024-05-20 13:44:04
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x19 10 2024-04-13 14:32:06 2024-05-20 12:40:21
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x20 11 2024-04-13 14:53:07 2024-05-20 12:10:40
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x21 9 2024-04-13 15:13:15 2024-05-20 13:44:42
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x22 9 2024-04-13 15:34:04 2024-05-20 11:33:16
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x23 10 2024-04-13 15:54:26 2024-05-20 16:06:38
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x24 10 2024-04-13 16:13:53 2024-05-20 11:26:48
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x25 10 2024-04-13 16:33:30 2024-05-20 12:37:16
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x26 10 2024-04-13 16:53:12 2024-05-20 12:42:39
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x27 8 2024-04-13 17:12:25 2024-05-20 15:20:27
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x28 9 2024-04-13 17:33:29 2024-05-20 12:42:27
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x29 10 2024-04-13 17:54:11 2024-05-20 12:51:15
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x30 2 2024-04-13 18:13:34 2024-05-20 12:40:15
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x31 2 2024-05-09 12:57:22 2024-05-20 16:07:18
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x32 1 2024-05-17 11:29:10 2024-05-20 12:43:37
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x33 1 2024-05-17 01:34:43 2024-05-20 12:38:01
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x34 1 2024-05-17 06:35:10 2024-05-20 14:30:25
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x35 1 2024-05-17 02:28:28 2024-05-20 14:31:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x36 2 2024-05-09 12:55:05 2024-05-20 12:08:48
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x37 2 2024-05-09 12:37:29 2024-05-20 12:40:50
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x38 1 2024-05-17 02:29:10 2024-05-20 15:21:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x39 1 2024-05-16 22:06:53 2024-05-20 15:21:35
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x40 1 2024-05-16 23:48:26 2024-05-20 12:07:34
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x41 2 2024-05-09 13:39:37 2024-05-20 15:22:10
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x42 2 2024-05-09 13:38:55 2024-05-20 12:06:22
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x43 1 2024-05-09 13:39:23 2024-05-20 14:31:35
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x44 1 2024-05-17 01:35:24 2024-05-20 11:36:12
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x45 1 2024-05-17 07:26:23 2024-05-20 12:38:37
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x46 1 2024-05-17 13:15:18 2024-05-20 11:54:41
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x47 1 2024-05-17 02:29:51 2024-05-20 12:37:05
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x48 1 2024-05-17 10:42:30 2024-05-20 11:52:53
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x49 2 2024-05-09 12:57:26 2024-05-20 12:42:22
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x50 1 2024-05-17 13:16:36 2024-05-20 15:23:12
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x51 2 2024-05-09 12:54:59 2024-05-20 15:23:45
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x52 1 2024-05-18 04:36:23 2024-05-20 12:41:23
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x53 1 2024-05-17 00:41:38 2024-05-20 16:07:58
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x54 1 2024-05-16 23:00:00 2024-05-20 16:08:39
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x55 1 2024-05-16 22:07:36 2024-05-20 11:56:20
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x56 1 2024-05-17 22:10:27 2024-05-20 15:24:17
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x57 1 2024-05-17 14:04:09 2024-05-20 16:09:13
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x58 2 2024-05-09 12:49:40 2024-05-20 12:39:29
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x59 1 2024-05-16 23:00:30 2024-05-20 13:46:37
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x60 2 2024-05-09 12:57:29 2024-05-20 12:40:44
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x61 1 2024-05-17 01:36:07 2024-05-20 13:47:15
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x62 1 2024-05-17 16:34:50 2024-05-20 12:39:12
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x63 1 2024-05-17 03:11:42 2024-05-20 11:33:02
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x64 2 2024-04-19 16:02:41 2024-05-20 12:39:18
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x65 1 2024-05-17 06:37:11 2024-05-20 12:43:27
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x66 1 2024-05-17 07:27:46 2024-05-20 12:41:46
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x67 3 2024-05-09 12:49:33 2024-05-20 12:42:51
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x68 1 2024-05-17 03:12:58 2024-05-20 12:11:02
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x69 1 2024-05-17 04:47:52 2024-05-20 11:56:56
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x70 1 2024-05-17 05:46:13 2024-05-20 12:39:45
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x71 2 2024-05-09 12:30:39 2024-05-20 14:32:11
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x72 1 2024-05-17 22:57:25 2024-05-20 12:43:03
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x73 1 2024-05-17 05:47:38 2024-05-20 12:41:07
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x74 1 2024-05-17 18:22:05 2024-05-20 12:08:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x75 2 2024-05-09 12:30:35 2024-05-20 12:42:45
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x76 2 2024-04-19 16:25:49 2024-05-20 16:09:52
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x77 3 2024-05-09 12:42:01 2024-05-20 11:55:36
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x78 1 2024-05-17 08:33:06 2024-05-20 12:37:55
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x79 1 2024-05-17 22:58:02 2024-05-20 12:38:08
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x80 1 2024-05-18 02:10:08 2024-05-20 11:27:08
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x81 1 2024-05-17 22:13:00 2024-05-20 13:48:32
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x82 1 2024-05-17 12:20:57 2024-05-20 12:37:28
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x83 1 2024-05-16 22:09:37 2024-05-20 12:41:58
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x84 1 2024-05-17 00:44:20 2024-05-20 12:37:44
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x85 2 2024-05-09 13:03:54 2024-05-20 11:56:41
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x86 1 2024-05-17 01:38:10 2024-05-20 11:52:06
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x87 3 2024-05-09 12:49:26 2024-05-20 11:53:39
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x88 1 2024-05-17 14:06:05 2024-05-20 12:10:51
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x89 1 2024-05-17 04:00:06 2024-05-20 16:10:32
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x90 1 2024-05-17 11:30:57 2024-05-20 12:40:26
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x91 2 2024-05-09 13:34:28 2024-05-20 12:07:16
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x92 2 2024-05-09 13:50:22 2024-05-20 12:52:27
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x93 1 2024-05-17 12:21:29 2024-05-20 10:56:53
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x94 2 2024-05-09 13:28:00 2024-05-20 12:37:39
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x95 2 2024-05-09 13:50:26 2024-05-20 12:53:01
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x96 2 2024-05-09 13:50:30 2024-05-20 12:40:03
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x97 1 2024-05-09 12:49:21 2024-05-20 12:11:20
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x98 4 2024-04-19 16:04:11 2024-05-20 12:10:56
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x99 3 2024-03-16 08:13:31 2024-05-20 12:11:14
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-video/corpora-video 10 2024-04-12 15:42:32 2024-05-20 14:32:45
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-video/README.md 258 2024-02-23 00:00:00 2024-05-22 08:18:32
corpora/files/CC-MAIN-2021-31-UNSAFE/README.md 105 2024-02-23 00:00:00 2024-05-22 03:35:13