A script for downloading manga from mangafox.me. Example usage: ./mangafox-downloader.sh -t sket_dance

mangafox-downloader.sh

#!/bin/bash

####################
# Parse chapters
####################
function parse_chapters {
    # Find all chapter links
    LINK_HTML_REGEX="<a href=\"$BASE_URL/v([0-9a-zA-Z]+)/c([0-9.]+)/([0-9]+).html\" title=\"(?:[a-zA-Z0-9.,?! -]+)?\" class=\"tips\">"
   
    # Loop through matches
    # TODO: Reverse this order
    echo $1 | grep -oP "$LINK_HTML_REGEX" | while read -r LINK_HTML ; do
        VOLUME=$(echo "$LINK_HTML" | grep -oP "href=\"$BASE_URL/v\K([0-9a-zA-Z]+)")
        CHAPTER=$(echo "$LINK_HTML" | grep -oP "href=\"$BASE_URL/v[0-9a-zA-Z]+/c\K([0-9.]+)")
       
        # Fetch chapter
        fetch_chapter $VOLUME $CHAPTER
    done
}

####################
# Fetch chapter
####################
function fetch_chapter {
    echo "CHAPTER $1/$2"
    echo "-------------------------------------------"
    echo ""
    echo -n "Getting pages "
        
    PAGE=1
    NEXT_PAGE="2.html"
    NEXT_PAGE_REGEX="[0-9].html"
    BASE_FILENAME="${1}_${2}"

    while [[ "$NEXT_PAGE" =~ $NEXT_PAGE_REGEX ]]
    do
        PAGE_NUMBER=$PAGE

        if [[ $PAGE_NUMBER -lt 10 ]]
            then
                PAGE_NUMBER="0$PAGE_NUMBER"
        fi

        CHAPTER_URL="$BASE_URL/v$1/c$2/$PAGE.html"
        CHAPTER_HTML=$(curl --silent --compressed $CHAPTER_URL)
        IMG_FILENAME="${BASE_FILENAME}_${PAGE_NUMBER}.jpg"
        
        # Find image
        IMAGE_URL=$(echo $CHAPTER_HTML | grep -m 1 -oP "http://h.mfcdn.net/store/manga/[0-9.]+/[0-9a-zA-Z.-]+/compressed/[a-zA-Z0-9._-]+.jpg.token=[a-z0-9]+.ttl=[0-9]+" | head -1)

        if [[ -z $IMAGE_URL ]]
        then
            echo "Image could not be found for URL $CHAPTER_URL"
            exit 1
        fi

        echo -n "$PAGE"

        # Download image
        wget -q "$IMAGE_URL" -O $TITLE/_img/$IMG_FILENAME
        
        # Find next link
        NEXT_PAGE=$(echo $CHAPTER_HTML | grep -oP "<a href=\"\K([0-9]+).html\" class=\"btn next_page\">")

        if [[ "$NEXT_PAGE" =~ $NEXT_PAGE_REGEX ]]
        then
            echo -n ", "
        fi

        ((PAGE++))
    done
   
    echo "" 

    # Create PDF
    echo "Creating PDF..."
    convert $TITLE/_img/*.jpg $TITLE/$BASE_FILENAME.pdf

    # Remove temp files
    echo "Removing temporary files..."
    rm -rf $TITLE/_img/*.jpg

    echo ""
}

# Get options first
DRYRUN=false
TITLE=''

while getopts "ds:t:" FLAG
do
    case $FLAG in
        d) DRYRUN=true ;;
        t) TITLE=$OPTARG ;;
        *) error "Unexpected option ${FLAG}" ;;
    esac
done

if [[ -z $TITLE ]]
then
    echo "Title not provided"
    exit 1
fi

# Remove and create directory
rm -rf "./$TITLE"
mkdir "./$TITLE"
mkdir "./$TITLE/_img"

# Generate URLs and start processing
BASE_URL=http://mangafox.me/manga/$TITLE
BASE_HTML=$(curl --silent --compressed $BASE_URL)

echo ""
echo "*********************************"
echo "*** Downloading $TITLE"
echo "*********************************"
echo ""

parse_chapters "$BASE_HTML"

rm -rf "./$TITLE/_img"

echo "DONE!"

# Exit
exit 0