metalx1000

HTML Table to CSV

May 13th, 2020
562
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. #!/bin/bash
  2. ######################################################################
  3. #Copyright (C) 2020  Kris Occhipinti
  4. #https://filmsbykris.com
  5.  
  6. #converts html tables to csv
  7.  
  8. #This program is free software: you can redistribute it and/or modify
  9. #it under the terms of the GNU General Public License as published by
  10. #the Free Software Foundation, either version 3 of the License, or
  11. #(at your option) any later version.
  12.  
  13. #This program is distributed in the hope that it will be useful,
  14. #but WITHOUT ANY WARRANTY; without even the implied warranty of
  15. #MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16. #GNU General Public License for more details.
  17.  
  18. #You should have received a copy of the GNU General Public License
  19. #along with this program.  If not, see <http://www.gnu.org/licenses/>.
  20. ######################################################################
  21.  
  22. output="$(date +%s).csv"
  23.  
  24. [[ "$1" == "" ]] && html="$(fzf)" || html="$*"
  25.  
  26. cat "$html"|\
  27.   tr -d "\n" |\
  28.   sed 's/<table /\n<table /g;s/table>/table>\n/g'|\
  29.   grep '<table '|\
  30.   sed 's/<\/td>/,/g;s/<tr>/\n/g'|\
  31.   sed -e 's/<[^>]*>//g'|\
  32.   sed 's/  //g'
RAW Paste Data