gistfile1.sh

#!/bin/bash
awk 'NR>1{print;}' abstracts.txt | awk 'NR%2==0{print;}' | awk -F ',' '{print $1}' > abstractids.txt
awk 'NR>1{print;}' abstracts.txt | awk 'NR%2==0{print;}' | sed 's/ and / /g' | sed 's/ the / /g' | sed 's/ who / /g' | sed 's/ of / /g' | sed 's/ then / /g' | sed 's/ where / /g' | sed 's/<IMAGE>/ /g' | sed 's/ that / /g' | sed 's/[^a-zA-Z ]//g' | sed -e 's/ [a-zA-Z]\{1,2\}\b//g' | sed 's/  / /g' | sed 's/A / /g' | sed 's/The / /g' | sed 's/ The / /g' | sed 's/ Thus / /g' | sed 's/ are / /g' | sed 's/ one / /g' | sed 's/ two / /g' | sed 's/ three / /g' | sed 's/ four / /g' | sed 's/ five / /g' | sed 's/ six / /g' | sed 's/ seven / /g' | sed 's/ eight / /g' | sed 's/ nine / /g' | sed 's/ per / /g' | sed 's/ iii / /g' | sed 's/ III / /g' | sed 's/ may / /g' | sed -n '/[^[:upper:] ]/p' | tr '[:upper:]' '[:lower:]' | sed 's/ have / /g' | sed 's/ from / /g' | sed 's/ for / /g' | sed 's/ not / /g' | sed 's/ will / /g' | sed 's/ with / /g' | sed 's/ such / /g' | sed 's/ between / /g' | sed 's/ from / /g' | sed 's/ some / /g'> abstractsnew.txt