OCR_directory.sh

# pdftk thesis.pdf burst 

#using pdf2text, extract text for each page in assets/pdfs and store in asssets/txts with similar basename

for pdf in assets/pdfs/*.pdf
do
    echo
    #pdftotext $pdf assets/txts/$(basename $pdf .pdf).txt
    #pdf2txt.py -o assets/txts/$(basename $pdf .pdf).txt $pdf
done


for pdf in assets/pdfs/*.pdf
do
    convert -density 100 -quality 100 -colorspace RGB -alpha remove -alpha off $pdf assets/pngs/$(basename $pdf .pdf).png
done