# HG changeset patch # User Henry S. Thompson # Date 1776760127 -3600 # Node ID ecb73c2f03d1d9d99af55398b716e02784f2ca54 # Parent cf25927ef96514ea8cb674f4f094f58d00a8e831 add -d flag diff -r cf25927ef965 -r ecb73c2f03d1 bin/getcc_multi.aws --- a/bin/getcc_multi.aws Mon Apr 20 18:19:43 2026 +0100 +++ b/bin/getcc_multi.aws Tue Apr 21 09:28:47 2026 +0100 @@ -1,6 +1,13 @@ # courtesy wwaites # Usage: getcc.aws [nthreads] # Single segment, multiple threads + +if [ "$1" = "-d" ] +then + shift + debug=1 +fi + ARCHIVE="$1" SEG=$2 nthreads=${3:-2} @@ -50,6 +57,10 @@ g=$s/orig/warc/${f##*/} if [ ! -f "$g" ] then + if [ "$debug" ] + then + echo aws s3 cp s3://commoncrawl/$f $g $(cat debug) --only-show-errors 2> >( { echo $(date +%D:%T) $f ; cat ; } >>errlog_${SEG}_$i ) + fi aws s3 cp s3://commoncrawl/$f $g $(cat debug) --only-show-errors 2> >( { echo $(date +%D:%T) $f ; cat ; } >>errlog_${SEG}_$i ) fi done &