PatrickLerner/NHKEasyToKindle

## NHKEasyToKindle
#!/bin/bash

OPTIND=1
ruby=0
url=""
open=0
notvertical=0
download=0

show_help () {
        echo " Usage:"
        echo "   -u URL"
        echo ""
        echo " Optional:"
        echo "   -n (not vertical, i.e. horizontal)"
        echo "   -o (open with Kindle for Mac after generation)"
        echo "   -r (include furigana)"
        echo "   -h (show help)"
        echo "   -d (download mp3)"
        echo ""
        echo ""
        echo " This script was only tested on a Mac."
        echo " (most of it should work on Linux just fine)"
        echo ""
        echo " Required packages:"
        echo "   - pandoc"
        echo "   - kindlegen"
        echo "   - wget"
        echo ""
        echo " Optional packages:"
        echo "   - Kindle for Mac"
        echo ""
        echo " Author: Patrick Lerner - patricklerner@me.com"
}

while getopts "h?rondu:" opt; do
    case "$opt" in
    h|\?)
        show_help
        exit 0
        ;;
    r)  ruby=1
        ;;
    n)  notvertical=1
        ;;
    u)  url=$OPTARG
        ;;
    o)  open=1
        ;;
    d)  download=1
        ;;
    esac
done

if [[ -z "$url" ]] ; then
        echo "Call me with a valid url, dude."
        exit 1
fi

temp_dir=$(mktemp -d -t tmp.XXXXXXXXXX)

function finish {
        rm -rf "${temp_dir}"
}

trap finish EXIT

echo "body { font-family: serif; } h2 { font-size: 120%; font-weight: bold; padding-top: 2em; margin-right: 1em; margin-left: 1em; } p { text-indent: 1em; } #newsDate { font-size: 90%; font-weight:bold; line-height: 1.5; }" >"${temp_dir}/file.css"

if [[ "$notvertical" -eq 0 ]] ; then
        echo "body { -webkit-writing-mode: vertical-rl; } #newsDate { padding-top: 10em; text-indent: -4em;} " >>"${temp_dir}/file.css"
fi

removeRuby () {
        utf8sed 's/<ruby>(.*?)<rt>(.*?)<\/rt><\/ruby>/$1/g'
}

getContentWithTitle() {
        utf8sed 's/\n//' |
        utf8sed 's/.*<div id="newstitle">(.*?)<\/div>.*<div id="newsarticle">(.*?)<\/div>.*/$1\n$2/s' |
        utf8sed 's/<[\/]?(a|span).*?>//sg' |
        utf8sed 's/^[ ]+//g' |
        utf8sed "s/ [ ]+/\n/g" |
        utf8sed 'tr/0-9/０-９/' |
        utf8sed 's/h２/h2/g'
}

getTitle() {
        utf8sed 's/\n//' |
        utf8sed 's/.*<div id="newstitle">.*?<h2>(.*?)<\/h2>.*?<\/div>.*/$1/s' |
        utf8sed 's/<[\/]?(a|span).*?>//sg' |
        utf8sed 's/^[ ]+//g' |
        utf8sed "s/ [ ]+/\n/g" |
        utf8sed 'tr/0-9/０-９/' |
        utf8sed 's/h２/h2/g'
}

content="$(wget -q -O - "${url}")"

title="$(echo "$content" | getTitle | removeRuby)"

# opf file

echo "<?xml version=\"1.0\" encoding=\"UTF-8\"?>
<package version=\"3.0\" xmlns=\"http://www.idpf.org/2007/opf\"
         unique-identifier=\"BookId\">
 <metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\"
           xmlns:dcterms=\"http://purl.org/dc/terms/\">
   <dc:title>${title}</dc:title>
   <dc:contributor>NHK</dc:contributor>
   <dc:language>ja</dc:language>
   <dc:publisher>NHK</dc:publisher>
 </metadata>
 <manifest>
  <item id=\"style\" href=\"file.css\" media-type=\"text/css\" />
  <item id=\"titlepage\" href=\"file.html\" media-type=\"application/xhtml+xml\" />
 </manifest>
 <spine toc=\"tocncx\" page-progression-direction=\"rtl\">
  <itemref idref=\"titlepage\" />
 </spine>
</package>" >"${temp_dir}/file.opf"

# opf file end

fileContent="$(echo "$content" | getContentWithTitle)"
if [[ "$ruby" -eq "0" ]] ; then
        fileContent=$(echo "$fileContent" | removeRuby)
fi

echo "$fileContent" > "${temp_dir}/file.proto.md"

pandoc "${temp_dir}/file.proto.md" -c "${temp_dir}/file.css" -o "${temp_dir}/file.html"
fileContent=$(cat "${temp_dir}/file.html")
echo "$fileContent" |
        sed "s/<title>/<title>${title}/" |
        sed "s/<\/head>/<link rel=\"Schema\.DC\" href=\"http:\/\/purl\.org\/dc\/elements\/1\.1\/\" \/><meta name=\"DC\.Title\" content=\"${title}\" \/><meta name=\"DC\.Creator\" content=\"NHK\" \/><meta name=\"DC\.Publisher\" content=\"NHK\" \/><\/head>/" |
        sed "s/<html /<html xml:lang=\"ja\" /" > "${temp_dir}/file.html"
kindlegen "${temp_dir}/file.opf"
cp "${temp_dir}/file.mobi" "${title}.mobi"

if [[ "$open" -eq "1" ]] ; then
        killall Kindle
        rm -rf "$HOME/Library/Application Support/Kindle/My Kindle Content/${title}.mobi"
        open "${title}.mobi"
fi

if [[ "$download" -eq "1" ]] ; then
        wget -c "$(echo "${url}" | sed 's/html/mp3/')" -O "${title}.mp3"
fi

## utf8sed
perl -Mutf8 -CSAD -pe "$1"
	#!/bin/bash

	OPTIND=1
	ruby=0
	url=""
	open=0
	notvertical=0
	download=0

	show_help () {
	echo " Usage:"
	echo " -u URL"
	echo ""
	echo " Optional:"
	echo " -n (not vertical, i.e. horizontal)"
	echo " -o (open with Kindle for Mac after generation)"
	echo " -r (include furigana)"
	echo " -h (show help)"
	echo " -d (download mp3)"
	echo ""
	echo ""
	echo " This script was only tested on a Mac."
	echo " (most of it should work on Linux just fine)"
	echo ""
	echo " Required packages:"
	echo " - pandoc"
	echo " - kindlegen"
	echo " - wget"
	echo ""
	echo " Optional packages:"
	echo " - Kindle for Mac"
	echo ""
	echo " Author: Patrick Lerner - patricklerner@me.com"
	}

	while getopts "h?rondu:" opt; do
	case "$opt" in
	h\|\?)
	show_help
	exit 0
	;;
	r) ruby=1
	;;
	n) notvertical=1
	;;
	u) url=$OPTARG
	;;
	o) open=1
	;;
	d) download=1
	;;
	esac
	done

	if [[ -z "$url" ]] ; then
	echo "Call me with a valid url, dude."
	exit 1
	fi

	temp_dir=$(mktemp -d -t tmp.XXXXXXXXXX)

	function finish {
	rm -rf "${temp_dir}"
	}

	trap finish EXIT

	echo "body { font-family: serif; } h2 { font-size: 120%; font-weight: bold; padding-top: 2em; margin-right: 1em; margin-left: 1em; } p { text-indent: 1em; } #newsDate { font-size: 90%; font-weight:bold; line-height: 1.5; }" >"${temp_dir}/file.css"

	if [[ "$notvertical" -eq 0 ]] ; then
	echo "body { -webkit-writing-mode: vertical-rl; } #newsDate { padding-top: 10em; text-indent: -4em;} " >>"${temp_dir}/file.css"
	fi

	removeRuby () {
	utf8sed 's/<ruby>(.?)<rt>(.?)<\/rt><\/ruby>/$1/g'
	}

	getContentWithTitle() {
	utf8sed 's/\n//' \|
	utf8sed 's/.<div id="newstitle">(.?)<\/div>.<div id="newsarticle">(.?)<\/div>.*/$1\n$2/s' \|
	utf8sed 's/<[\/]?(a\|span).*?>//sg' \|
	utf8sed 's/^[ ]+//g' \|
	utf8sed "s/ [ ]+/\n/g" \|
	utf8sed 'tr/0-9/０-９/' \|
	utf8sed 's/h２/h2/g'
	}

	getTitle() {
	utf8sed 's/\n//' \|
	utf8sed 's/.<div id="newstitle">.?<h2>(.?)<\/h2>.?<\/div>.*/$1/s' \|
	utf8sed 's/<[\/]?(a\|span).*?>//sg' \|
	utf8sed 's/^[ ]+//g' \|
	utf8sed "s/ [ ]+/\n/g" \|
	utf8sed 'tr/0-9/０-９/' \|
	utf8sed 's/h２/h2/g'
	}

	content="$(wget -q -O - "${url}")"

	title="$(echo "$content" \| getTitle \| removeRuby)"

	# opf file

	echo "<?xml version=\"1.0\" encoding=\"UTF-8\"?>
	<package version=\"3.0\" xmlns=\"http://www.idpf.org/2007/opf\"
	unique-identifier=\"BookId\">
	<metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\"
	xmlns:dcterms=\"http://purl.org/dc/terms/\">
	<dc:title>${title}</dc:title>
	<dc:contributor>NHK</dc:contributor>
	<dc:language>ja</dc:language>
	<dc:publisher>NHK</dc:publisher>
	</metadata>
	<manifest>
	<item id=\"style\" href=\"file.css\" media-type=\"text/css\" />
	<item id=\"titlepage\" href=\"file.html\" media-type=\"application/xhtml+xml\" />
	</manifest>
	<spine toc=\"tocncx\" page-progression-direction=\"rtl\">
	<itemref idref=\"titlepage\" />
	</spine>
	</package>" >"${temp_dir}/file.opf"

	# opf file end

	fileContent="$(echo "$content" \| getContentWithTitle)"
	if [[ "$ruby" -eq "0" ]] ; then
	fileContent=$(echo "$fileContent" \| removeRuby)
	fi

	echo "$fileContent" > "${temp_dir}/file.proto.md"

	pandoc "${temp_dir}/file.proto.md" -c "${temp_dir}/file.css" -o "${temp_dir}/file.html"
	fileContent=$(cat "${temp_dir}/file.html")
	echo "$fileContent" \|
	sed "s/<title>/<title>${title}/" \|
	sed "s/<\/head>/<link rel=\"Schema\.DC\" href=\"http:\/\/purl\.org\/dc\/elements\/1\.1\/\" \/><meta name=\"DC\.Title\" content=\"${title}\" \/><meta name=\"DC\.Creator\" content=\"NHK\" \/><meta name=\"DC\.Publisher\" content=\"NHK\" \/><\/head>/" \|
	sed "s/<html /<html xml:lang=\"ja\" /" > "${temp_dir}/file.html"
	kindlegen "${temp_dir}/file.opf"
	cp "${temp_dir}/file.mobi" "${title}.mobi"

	if [[ "$open" -eq "1" ]] ; then
	killall Kindle
	rm -rf "$HOME/Library/Application Support/Kindle/My Kindle Content/${title}.mobi"
	open "${title}.mobi"
	fi

	if [[ "$download" -eq "1" ]] ; then
	wget -c "$(echo "${url}" \| sed 's/html/mp3/')" -O "${title}.mp3"
	fi