Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/bin/bash
- CONVERT=pdftotext
- OUTPUT_FOLDER="text"
- CONVERT_FLAGS1=
- CONVERT_FLAGS2=-layout
- VARIANT_FOLDER1="${OUTPUT_FOLDER}/plain"
- VARIANT_FOLDER2="${OUTPUT_FOLDER}/layout"
- mkdir -p ${VARIANT_FOLDER1}
- mkdir -p ${VARIANT_FOLDER2}
- for fn in *.pdf
- do
- basename=$(echo "$fn" | sed -r "s/\.pdf$//")
- echo "processing ${fn}..."
- FN_OUT1="${VARIANT_FOLDER1}/${basename}.txt"
- if [[ -f ${FN_OUT1} ]]; then
- echo "exists"
- else
- echo $CONVERT $CONVERT_FLAGS1 "$fn" ${FN_OUT1}
- $CONVERT $CONVERT_FLAGS1 "${fn}" "${FN_OUT1}"
- fi
- FN_OUT2="${VARIANT_FOLDER2}/${basename}.txt"
- if [[ -f ${FN_OUT2} ]]; then
- echo "exists"
- else
- echo $CONVERT $CONVERT_FLAGS2 "$fn" ${FN_OUT2}
- $CONVERT $CONVERT_FLAGS2 "${fn}" "${FN_OUT2}"
- fi
- echo "done."
- done
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement