This script uses bash commands to retrieve data from the Jobs.ie front page and process it into a spreadsheet friendly format

JobsRetrievalScript.sh

#!/bin/bash
#jobs.ie retrieval script

# This command invokes wget and saves the output file to temp1.txt

wget www.jobs.ie -O source-file.txt 

# Prints current date to file

date >> scraper-dir/results.txt

#This chain of commands selects the correct table, removes html formatting and creates a tabbed output.

cat source-file.txt | grep cphMain | sed 's/<td>/\t/g'  | sed 's/<tr>/\n/g' |  sed 's/<\/td>/\t/g' |  sed -e 's/<[^>]*>//g' >> scraper-dir/results.txt

# Removes the original file

rm source-file.txt