common-crawl-utils.utils — lt.tokenmill/common-crawl-utils 0.1.0

get-crawls clj

(get-crawls)

(get-crawls index-collinfo)

get-http-error clj

(get-http-error {:keys [body error status]})

get-most-recent-crawl clj

(get-most-recent-crawl)

(get-most-recent-crawl index-collinfo)

gzip-line-seq clj

(gzip-line-seq path)

read-jsonl clj

(read-jsonl s)

request-json clj

(request-json url)

warc-record-seq clj

(warc-record-seq path)