From 5c3d28a397a381198dc8838ad95187e43f038ec4 Mon Sep 17 00:00:00 2001 From: "Robin. P. Clark" Date: Fri, 30 Dec 2022 12:15:51 +0000 Subject: [PATCH] for combined bank statements --- pdf_to_csv_mt_annual.sh | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100755 pdf_to_csv_mt_annual.sh diff --git a/pdf_to_csv_mt_annual.sh b/pdf_to_csv_mt_annual.sh new file mode 100755 index 0000000..ed74cb3 --- /dev/null +++ b/pdf_to_csv_mt_annual.sh @@ -0,0 +1,37 @@ +#!/bin/bash +# script to convert pdf bank statements to +# csv files + +# these files may have +# white space in files names +while IFS='' read -r -d '' fname ; do + nname="${fname##*/}" + mv -v -n "${fname}" "${fname%/*}/${nname//[[:space:]]/_}" +done < <(find "$(pwd)" -name "* *" -type f -print0) + +rm -rf dd.txt +a=`ls *.pdf` + +for l in $a; +do + echo "processing" $l + ps2ascii $l >> dd.txt; +done +view dd.txt +cat dd.txt | sed -n '/.*[0-9][0-9] \+[A-Z][a-z][a-z]/p' \ + | sed 's/\([0-9]\+\),\([0-9]\+\)/\1\2/g' \ + > ddd.txt + +view ddd.txt + +vi m_spreadsheet.txt +cat m_spreadsheet.txt | sed 's/\(Opening balance\)/,,,,,,,\1/' \ + | sed 's/\(Statement period\)/,,,,,,,\1/' \ + | sed 's/\(DR INTEREST\)/,,,,,,,\1/' \ + | sed 's/\(MONTHLY ACCOUNT FEE\)/,,,,,,,\1/' \ + | sed 's/\([0-9]\+\.[0-9]\+\) OD/\1,OD/' \ + | sed 's/.*\([0-9][0-9] \+[A-Z][a-z][a-z]\) \+\([A-Z][A-Z]\)/\1,\2/' \ + | sed 's/\(Your accounts at a glance as at\)/,,,,,,,\1/' > m_spreadsheet.csv +# +view m_spreadsheet.csv +#