view bin/cdx_tab.sh @ 190:f2bf736c2d40

working, with issues: 1) warc.export.cdx.path is not set 2) mime property isn't getting through 3) lastMod isn't showing up
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Tue, 24 Sep 2024 17:08:05 +0100
parents ef961d91eea5
children
line wrap: on
line source

#!/bin/bash
# Invoke this as e.g. sbatch -n 30 -c 10 masterJob.sh cdx_segment CC-MAIN-2019-35
# run cdx_segment.py in parallel 
n=$SLURM_NTASKS
c=$SLURM_CPUS_PER_TASK
node=$SLURMD_NODENAME
local=$SLURM_LOCALID
proc=$SLURM_PROCID
echo $(date) $node:$proc start

type parallel
#module load gnu-parallel

PYTHONPATH=$PYTHONPATH:$HOME/lib/python
parallel --will-cite -j $c doC2T.sh "$1" '{}' < cdx_tab/$proc.txt

echo $(date) $proc end