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- 6 2026-09-03 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/cc-proven 23 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/commoncra 1 2026-09-03 00:00:00 2026-09-03 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/pdfinfo-2 13 2026-09-02 00:00:00 2026-09-07 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/README.md 18 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/tika-2023 21 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/tika-with 4 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/metadata/zipconten 2 2026-09-03 00:00:00 2026-09-07 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/README.md 80 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/0000-0999 1299 2026-09-02 00:00:00 2026-09-08 07:59:59
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/1000-1999 91 2026-09-02 00:00:00 2026-09-08 07:59:57
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/2000-2999 177 2026-09-02 00:00:00 2026-09-07 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/3000-3999 96 2026-09-02 00:00:00 2026-09-07 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/4000-4999 188 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/5000-5999 39 2026-09-02 00:00:00 2026-09-08 07:29:31
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/6000-6999 21 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-PDF-UNTRUNCATED/zipfiles/7000-7999 32 2026-09-02 00:00:00 2026-09-08 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/common-crawl/common-crawl-x 1 2026-09-02 00:00:00 2026-09-06 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-icc.zip 6 2026-09-02 00:00:00 2026-09-06 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x00 6 2026-09-02 00:00:00 2026-09-07 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x01 3 2026-09-03 00:00:00 2026-09-05 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x02 1 2026-09-02 00:00:00 2026-09-05 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x06 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x11 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x16 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x21 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x26 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x31 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x36 1 2026-09-02 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x45 1 2026-09-03 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-pdf/corpora-pdf-x92 1 2026-09-03 00:00:00 2026-09-04 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-video/corpora-video 1 2026-09-04 00:00:00 2026-09-06 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/corpora-video/README.md 8 2026-09-02 00:00:00 2026-09-06 00:00:00
corpora/files/CC-MAIN-2021-31-UNSAFE/README.md 7 2026-09-02 00:00:00 2026-09-07 00:00:00