Advertisement
Guest User

Untitled

a guest
Oct 20th, 2019
104
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 0.79 KB | None | 0 0
  1. #!/bin/bash
  2.  
  3. CONVERT=pdftotext
  4. OUTPUT_FOLDER="text"
  5.  
  6. CONVERT_FLAGS1=
  7. CONVERT_FLAGS2=-layout
  8. VARIANT_FOLDER1="${OUTPUT_FOLDER}/plain"
  9. VARIANT_FOLDER2="${OUTPUT_FOLDER}/layout"
  10.  
  11. mkdir -p ${VARIANT_FOLDER1}
  12. mkdir -p ${VARIANT_FOLDER2}
  13.  
  14. for fn in *.pdf
  15. do
  16. basename=$(echo "$fn" | sed -r "s/\.pdf$//")
  17. echo "processing ${fn}..."
  18. FN_OUT1="${VARIANT_FOLDER1}/${basename}.txt"
  19. if [[ -f ${FN_OUT1} ]]; then
  20. echo "exists"
  21. else
  22. echo $CONVERT $CONVERT_FLAGS1 "$fn" ${FN_OUT1}
  23. $CONVERT $CONVERT_FLAGS1 "${fn}" "${FN_OUT1}"
  24. fi
  25. FN_OUT2="${VARIANT_FOLDER2}/${basename}.txt"
  26. if [[ -f ${FN_OUT2} ]]; then
  27. echo "exists"
  28. else
  29. echo $CONVERT $CONVERT_FLAGS2 "$fn" ${FN_OUT2}
  30. $CONVERT $CONVERT_FLAGS2 "${fn}" "${FN_OUT2}"
  31. fi
  32.  
  33. echo "done."
  34. done
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement