-
-
Save niazangels/bb53c431311eed3aa2eb7155d3bb0cfd to your computer and use it in GitHub Desktop.
convert a PDF to TIFF using gs, convert from TIFF to txt using tesseract
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# $1 is the first argument | |
# remove result.txt | |
#rm output/result.txt | |
fname=`echo "$1" | awk -F "/" '{print $(NF)}'` | |
# convert the pdf to a group of tiffs | |
if [ ! -e extracted_tz_parliament/$fname.txt ]; | |
then | |
echo "Working on $fname..." | |
gs -dNOPAUSE -dBATCH -sDEVICE=tiffg4 -sOutputFile=scan_%d.tif $1 | |
i=1 | |
while [ $i -ge 0 ] | |
do | |
if [ -a scan_$i.tif ] | |
then | |
tesseract scan_$i.tif scan_$i | |
# add the text to the result.txt file | |
cat scan_$i.txt >> output/result.txt | |
rm scan_$i.txt scan_$i.tif | |
i=$(( $i + 1 )) | |
else | |
i=-100 | |
fi | |
done | |
else | |
echo "File $fname.txt exists, moving on." | |
fi | |
mv output/result.txt extracted_tz_parliament/$fname.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment