drought-gov_2025-04-03 (88 files)
crawls/crawl-20250403213430-ba290d7c423e.yaml |
346.47kB |
drought-gov-20250403.zim |
3.27GB |
pages/extraPages.jsonl |
643.19kB |
pages/pages.jsonl |
0.69kB |
warc-cdx/rec-ba290d7c423e-20250403211817602-0.warc.gz.cdx |
555.10kB |
warc-cdx/rec-ba290d7c423e-20250403211817787-1.warc.gz.cdx |
560.19kB |
warc-cdx/rec-ba290d7c423e-20250403211827614-4.warc.gz.cdx |
407.56kB |
warc-cdx/rec-ba290d7c423e-20250403211828063-2.warc.gz.cdx |
454.84kB |
warc-cdx/rec-ba290d7c423e-20250403211828085-3.warc.gz.cdx |
440.99kB |
warc-cdx/rec-ba290d7c423e-20250403211828293-5.warc.gz.cdx |
515.54kB |
warc-cdx/rec-ba290d7c423e-20250403211828368-9.warc.gz.cdx |
467.19kB |
warc-cdx/rec-ba290d7c423e-20250403211828397-8.warc.gz.cdx |
480.64kB |
warc-cdx/rec-ba290d7c423e-20250403211828409-7.warc.gz.cdx |
502.44kB |
warc-cdx/rec-ba290d7c423e-20250403211828427-11.warc.gz.cdx |
560.00kB |
warc-cdx/rec-ba290d7c423e-20250403211828464-12.warc.gz.cdx |
598.45kB |
warc-cdx/rec-ba290d7c423e-20250403211828467-6.warc.gz.cdx |
473.76kB |
warc-cdx/rec-ba290d7c423e-20250403211828504-14.warc.gz.cdx |
758.49kB |
warc-cdx/rec-ba290d7c423e-20250403211828799-18.warc.gz.cdx |
238.01kB |
warc-cdx/rec-ba290d7c423e-20250403211828808-17.warc.gz.cdx |
520.48kB |
warc-cdx/rec-ba290d7c423e-20250403211828819-19.warc.gz.cdx |
523.26kB |
warc-cdx/rec-ba290d7c423e-20250403211828870-10.warc.gz.cdx |
493.93kB |
warc-cdx/rec-ba290d7c423e-20250403211828922-13.warc.gz.cdx |
563.32kB |
warc-cdx/rec-ba290d7c423e-20250403211828968-15.warc.gz.cdx |
495.30kB |
warc-cdx/rec-ba290d7c423e-20250403211829113-16.warc.gz.cdx |
474.54kB |
warc/rec-ba290d7c423e-20250403211817602-0.warc.gz |
515.69MB |
warc/rec-ba290d7c423e-20250403211817787-1.warc.gz |
165.59MB |
warc/rec-ba290d7c423e-20250403211827614-4.warc.gz |
293.18MB |
warc/rec-ba290d7c423e-20250403211828063-2.warc.gz |
172.77MB |
warc/rec-ba290d7c423e-20250403211828085-3.warc.gz |
64.05MB |
warc/rec-ba290d7c423e-20250403211828293-5.warc.gz |
347.02MB |
warc/rec-ba290d7c423e-20250403211828368-9.warc.gz |
303.10MB |
warc/rec-ba290d7c423e-20250403211828397-8.warc.gz |
284.37MB |
warc/rec-ba290d7c423e-20250403211828409-7.warc.gz |
77.46MB |
warc/rec-ba290d7c423e-20250403211828427-11.warc.gz |
307.72MB |
warc/rec-ba290d7c423e-20250403211828464-12.warc.gz |
230.99MB |
warc/rec-ba290d7c423e-20250403211828467-6.warc.gz |
231.73MB |
warc/rec-ba290d7c423e-20250403211828504-14.warc.gz |
466.61MB |
warc/rec-ba290d7c423e-20250403211828799-18.warc.gz |
374.11MB |
warc/rec-ba290d7c423e-20250403211828808-17.warc.gz |
165.94MB |
warc/rec-ba290d7c423e-20250403211828819-19.warc.gz |
223.38MB |
warc/rec-ba290d7c423e-20250403211828870-10.warc.gz |
226.72MB |
warc/rec-ba290d7c423e-20250403211828922-13.warc.gz |
406.87MB |
warc/rec-ba290d7c423e-20250403211828968-15.warc.gz |
498.94MB |
warc/rec-ba290d7c423e-20250403211829113-16.warc.gz |
448.42MB |
Type: Dataset
Bibtex:
Tags:
Bibtex:
@article{,
title= {drought.gov zim/warc snapshot 2025-04-03},
journal= {},
author= {NOAA},
year= {},
url= {https://www.drought.gov/},
abstract= {Archive of drought.gov on word that NOAA's web infra will be taking a large hit in the next few days.
part of https://sciop.net/datasets/noaa-webrips},
keywords= {ncei, NOAA, climate, climate-data, drought, water},
terms= {},
license= {},
superseded= {}
}
crawls/crawl-20250403213430-ba290d7c423e.yaml