29 lines
868 B
Plaintext
29 lines
868 B
Plaintext
|
#!/bin/bash
|
||
|
#
|
||
|
#$ -t 1-256
|
||
|
#
|
||
|
# Usage:
|
||
|
# 1. Make sure conda environment "mypython35" exists.
|
||
|
# 2. Make sure to checkout ExtensionCrawler somehwere.
|
||
|
#
|
||
|
# Example invocation:
|
||
|
# qsub grepper256.sge DBPATH [EXTENSIONCRAWLERPATH]
|
||
|
# OUTPATH out path
|
||
|
# [EXTENSIONCRAWLERPATH] ExtensionCrawler git repo, defaults to ~/ExtensionCrawler
|
||
|
|
||
|
module -s load apps/python/conda 2> /dev/null
|
||
|
source activate mypython35
|
||
|
|
||
|
set -u
|
||
|
|
||
|
ABC=abcdefghijklmnopqrstuvwxyz
|
||
|
let "I1 = ((SGE_TASK_ID-1) / 16) % 16"
|
||
|
let "I2 = (SGE_TASK_ID-1) % 16"
|
||
|
LETTER=${ABC:$I1:1}${ABC:$I2:1}
|
||
|
|
||
|
SNAPSHOTDIR="$(find /shared/brucker_research1/Shared/BrowserExtensions/.snapshot -maxdepth 1 -mindepth 1 -name "Daily *" | sort -r | head -n 1)"
|
||
|
OUTPATH="$1"
|
||
|
EXTENSIONCRAWLERDIR="${2:-~/ExtensionCrawler}"
|
||
|
|
||
|
python "$EXTENSIONCRAWLERDIR/grepper" -a "$SNAPSHOTDIR" -p $LETTER "$OUTPATH" "amazon" "&tag="
|