Website:
Corpus:

digitalcorpora.org Reports

Available Reports:

DARPA SAFEDOCS and UNSAFEDOCS downloads over past 7 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 -7 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- 2 2024-07-09 00:00:00 2024-07-15 22:33:40
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/cc-proven 2 2024-07-09 00:00:00 2024-07-14 22:41:27
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/pdfinfo-2 2 2024-07-09 00:00:00 2024-07-14 20:51:07
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/README.md 52 2024-07-09 00:00:00 2024-07-15 09:28:58
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/README.md 185 2024-07-09 00:00:00 2024-07-16 02:12:10
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/0000-0999 2320 2024-07-09 00:00:00 2024-07-15 20:34:30
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/1000-1999 849 2024-07-09 00:00:00 2024-07-13 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/2000-2999 2701 2024-07-09 00:00:00 2024-07-14 23:32:07
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/3000-3999 1362 2024-07-09 00:00:00 2024-07-13 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/4000-4999 1190 2024-07-09 00:00:00 2024-07-16 00:05:55
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/5000-5999 1050 2024-07-09 00:00:00 2024-07-15 21:23:30
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/6000-6999 1765 2024-07-09 00:00:00 2024-07-15 19:35:55
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/7000-7999 1190 2024-07-09 00:00:00 2024-07-16 00:08:35
corpora/files/CC-MAIN-2021-31-UNSAFE/common-crawl/common-crawl-x 3 2024-07-10 00:00:00 2024-07-16 01:59:47
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-video/README.md 17 2024-07-09 00:00:00 2024-07-14 17:02:54
corpora/files/CC-MAIN-2021-31-UNSAFE/README.md 10 2024-07-09 00:00:00 2024-07-15 14:53:46