Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/scripts/pdftohtml.sh @ 2:b50eed0cc0ef upstream

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4. The directory name has changed: no version number in the expanded directory now.
author Franz Glasner <fzglas.hg@dom66.de>
date Mon, 15 Sep 2025 11:43:07 +0200
parents
children
comparison
equal deleted inserted replaced
1:1d09e1dec1d9 2:b50eed0cc0ef
1 #!/bin/bash
2 #
3 # Convert PDF to hybrid HTML output with images and line art rendered to a
4 # background image, and text overlaid on top as absolutely positioned HTML
5 # text.
6
7 input=$1
8 out=${2:-out}
9 fmt=${3:-png}
10 dpi=${4:-96}
11
12 scale=$(expr 72 '*' $dpi / 96)
13
14 if test -f "$1"
15 then
16 echo Processing "$input" out=$out fmt=$fmt dpi=$dpi
17 else
18 echo "usage: pdftohtml.sh input.pdf output-stem image-format dpi"
19 echo " example: pdftohtml.sh input.pdf output png 96"
20 exit
21 fi
22
23 title=$(basename "$input" | sed 's/.pdf$//')
24
25 mutool convert -Oresolution=$dpi -o $out.html "$input"
26
27 sed -i -e "/<head>/a<title>$title</title>" $out.html
28 sed -i -e "/^<div/s/page\([0-9]*\)\" style=\"/page\1\" style=\"background-image:url('$out\1.$fmt');/" $out.html
29
30 mutool draw -K -r$dpi -o$out%d.png "$input"
31
32 echo Converting to $fmt
33 for png in $out*.png
34 do
35 xxx=$(basename $png .png).$fmt
36 case $fmt in
37 png)
38 if command -v optipng >/dev/null
39 then
40 optipng -silent -strip all $png
41 fi
42 ;;
43 jpg)
44 if command -v mozjpeg >/dev/null
45 then
46 mozjpeg -outfile $xxx $png
47 else
48 convert -format $fmt $png $xxx
49 fi
50 ;;
51 webp)
52 if command -v cwebp >/dev/null
53 then
54 cwebp -quiet -o $xxx $png
55 else
56 convert -format $fmt $png $xxx
57 fi
58 ;;
59 *)
60 convert -format $fmt $png $xxx
61 ;;
62 esac
63 done