spider.sh
713 Bytes
#!/bin/env sh
# chunk @ 2014
########################################################################################
##
## F**k World!
##
########################################################################################
export export TERM=linux
source /home/hadoop/.bashrc
workon envtmp
#SPIDER_DIR=/home/hadoop/workspace/pycharm/test/ImageR/mspider
SPIDER_DIR=/home/hadoop/Programs/newdist/mspider
cd $SPIDER_DIR
echo "vailable spiders:"
scrapy list
echo "\ncrawling:"
time scrapy crawl larvae
#scan 'MSPIDER2', { COLUMNS => 'cf_tag:class', LIMIT => 10, FILTER => "ValueFilter( =, 'binaryprefix:1' )" }
#scan 'MSPIDER2', { COLUMNS => 'cf_tag:class', FILTER => "ValueFilter( =, 'binaryprefix:1' )" }