Difference between
modified post 98b by Anonymous on Wed 11th Jul 2018 03:18
original post e410ed8 by Anonymous on Mon 4th Jun 2018 01:33
Download diff
Show old version | new version | both versions

pdfseparate ../source.pdf page%04d.pdf

1	1		pdfseparate ../source.pdf page%04d.pdf
2	2		ls *.pdf \| awk '1==1 {printf("convert -quality 100 -density 200 %s %s.tif\n",$0,$0)'}
3	3		ls *.tif \| gawk '1==1 {printf("tesseract -l eng+ita %s %s.txt pdf \n",$0,$0);}' \| sh
4	4		pdfunite *.txt.pdf out.pdf
5	5		pdftotext out.pdf out.txt
6	6		cat out.txt \| tr "'" ' ' \| tr ' ' '\n' \| tr A-Z a-z \| tr '.' ' ' \| tr ',' ' ' \| sort \| uniq -c \| sort -rn > words_frequency.txt
7	7
8	8
9	9
10	10		convert -density 50 file.pdf[0] page.jpg # convert page #0 to jpg [0,10] 0 and 10
11	11
12	12
13	13
14		-
	14	+	pdfunite *.pdf out.pdf
15		-
	15	+	ls *.jpg \| awk '1==1 {printf("convert -resample 300 -quality 50 %s %s.pdf\n",$0,$0);}' \| cat
16	16