pdfseparate ../source.pdf page%04d.pdf ls *.pdf | awk '1==1 {printf("convert -quality 100 -density 200 %s %s.tif\n",$0,$0)'} ls *.tif | gawk '1==1 {printf("tesseract -l eng+ita %s %s.txt pdf \n",$0,$0);}' | sh pdfunite *.txt.pdf out.pdf pdftotext out.pdf out.txt cat out.txt | tr "'" ' ' | tr ' ' '\n' | tr A-Z a-z | tr '.' ' ' | tr ',' ' ' | sort | uniq -c | sort -rn > words_frequency.txt convert -density 50 file.pdf[0] page.jpg # convert page #0 to jpg [0,10] 0 and 10