└── scribd-dl


/scribd-dl:
--------------------------------------------------------------------------------
  1 | #!/bin/bash
  2 | 
  3 | #WORKINGDIR="/tmp/${0##*/}-$$"
  4 | WORKINGDIR=".${0##*/}-$$"
  5 | 
  6 | if (( ${#@} != 1 )) || [[ $1 = '--help' ]]; then
  7 | 	printf '%s\n' \
  8 | 		"Renders PDF files of books on Scribd." \
  9 | 		"Usage: ${0##*/} scribd_book_url"
 10 | 	exit 1
 11 | elif ! command -v wget > /dev/null; then
 12 | 	echo "This script requires wget."
 13 | 	exit 1
 14 | elif ! command -v convert > /dev/null; then
 15 | 	echo "This script requires ImageMagick."
 16 | 	exit 1
 17 | elif ! command -v pdftk > /dev/null; then
 18 | 	echo "This script requires PDFTK."
 19 | 	exit 1
 20 | fi
 21 | 
 22 | printf 'Getting HTML content... '
 23 | if ! html="$(wget -qO - "$1")"; then
 24 | 	printf '%s\n' "error." "Could not download \"$1\"."
 25 | 	exit 1
 26 | fi
 27 | echo "done."
 28 | 
 29 | filename="${html#*<title>}"
 30 | filename="${filename%%</title>*}"
 31 | filename="${filename//\//-}"
 32 | 
 33 | echo "Destination PDF: \"$filename.pdf\"."
 34 | 
 35 | printf 'Searching for assetPrefix... '
 36 | regexPrefix="docManager.assetPrefix = \""
 37 | if ! [[ $html =~ $regexPrefix ]]; then
 38 | 	printf '%s\n' "error." "\"$1\" is not a valid Scribd book URL."
 39 | 	exit 1
 40 | fi
 41 | prefix="${html#*$regexPrefix}"
 42 | prefix="${prefix%%\"*}"
 43 | echo "\"$prefix\"."
 44 | 
 45 | printf 'Finding pages to download... '
 46 | regexJpg="http://html.scribd.com/$prefix/images/[0-9]+-[0-9a-z]+.jpg"
 47 | regexJsonp="http://html[1-4].scribdassets.com/$prefix/pages/[0-9]+-[0-9a-z]+.jsonp"
 48 | unset -v pages
 49 | while read line; do
 50 | 	if [[ $line =~ $regexJsonp ]]; then
 51 | 		page="${line##*/pages/}"
 52 | 		page="${page%%.jsonp*}"
 53 | 		pages+=("$page")
 54 | 		continue
 55 | 	fi
 56 | 
 57 | 	if [[ $line =~ $regexJpg ]]; then
 58 | 		page="${line##*/images/}"
 59 | 		page="${page%%.jpg*}"
 60 | 		pages+=("$page")
 61 | 	fi
 62 | done <<< "$html"
 63 | totalPages="${#pages[@]}"
 64 | echo "$totalPages pages."
 65 | 
 66 | clean-up() {
 67 | 	printf 'Cleaning up... '
 68 | 	rm -r "$WORKINGDIR"
 69 | 	echo "done."
 70 | }
 71 | 
 72 | trap 'echo; clean-up; exit 1' SIGINT SIGTERM
 73 | 
 74 | echo "Using working directory \"$WORKINGDIR\"."
 75 | mkdir "$WORKINGDIR"
 76 | 
 77 | padding="$(($totalPages-1))"
 78 | padding="${#totalPages}"
 79 | for pageIndex in ${!pages[@]}; do
 80 | 	pageNumber="$((pageIndex + 1))"
 81 | 	printf -v file "%.${padding}d" "$((pageIndex + 1))"
 82 | 
 83 | 	printf 'Rendering PDF data for page %s (of %s)... ' "$pageNumber" "$totalPages"
 84 | 	retries=0
 85 | 	until (( retries == 10 )); do
 86 | 		wget -qO "$WORKINGDIR/$file.jpg" "http://html.scribd.com/$prefix/images/${pages[$pageIndex]}.jpg" && break
 87 | 		sleep 2
 88 | 	done
 89 | 
 90 | 	if (( retries == 10 )); then
 91 | 		printf '%s\n' "error." "Error while downloading \"http://html.scribd.com/$prefix/images/${pages[$pageIndex]}.jpg\"."
 92 | 		clean-up
 93 | 		exit 1
 94 | 	fi
 95 | 
 96 | 	if ! convert "$WORKINGDIR/$file.jpg" "$WORKINGDIR/$file.pdf"; then
 97 | 		printf '%s\n' "error." "Could not convert \"$WORKINGDIR/$file.jpg\" to PDF."
 98 | 		clean-up
 99 | 		exit 1
100 | 	fi
101 | 
102 | 	rm "$WORKINGDIR/$file.jpg"
103 | 	echo "$(($(stat --printf '%s' "$WORKINGDIR/$file.pdf") / 1024)) KB."
104 | done
105 | 
106 | printf 'Combining all PDF files to one file... '
107 | pdftk "$WORKINGDIR/"*".pdf" cat output "$WORKINGDIR/$filename.pdf"
108 | mv "$WORKINGDIR/$filename.pdf" "$filename.pdf"
109 | echo "$(($(stat --printf '%s' "$filename.pdf") / 1024)) KB."
110 | 
111 | clean-up
112 | 
113 | echo "PDF file saved as \"$filename.pdf\"."
114 | 


--------------------------------------------------------------------------------