A little script to download manga from wakascan.com and convert them to pdf

download_manga_wakascan.sh

#!/bin/bash

set -e

PDF_DIR="$HOME/Documents/books/berserk"

[ $# == 1 ] || (echo "expected one argument, the URL of the manga's volume.
example: 'https://wakascan.com/manga/berserk/vol-05/'" && exit 1)

DIR=$(dirname "$0")
IMG_DIR="$DIR/manga_images"

rm -rf "$IMG_DIR"
mkdir "$IMG_DIR"

page_url="$1/"
url=`curl -s $page_url | grep "image-0" | sed 's/<img id="image-0" data-image-paged="0" src="//' | sed 's/" class="wp-manga-chapter-img">//'`
name=`curl -s $page_url | grep "chapter-heading" | sed 's/<h1 id="chapter-heading">//' | sed 's.</h1>..'`
url_suffix=${url: -4}

cd "$IMG_DIR"

# Download images
page=1
while : ; do
	len=`python -c "import math; print(int(math.log10($page)))"`
	url_prefix=${url:: -5 - len}
	page_url="$url_prefix$page$url_suffix"
	[ $page -eq 0 ] || echo "downloading page $page..."
	if ! wget -q "$page_url"; then
		echo "$page pages downloaded, done."
		break
	fi
	((page=page+1))
done

# Convert to PDF
if [ $url_suffix == ".png" ]; then
	echo "png source"
	convert "./*.png" "../manga.pdf"
elif [ $url_suffix == ".jpg" ]; then
	echo "jpeg source"
	find -iname "*.jpg" | parallel -I'{}' convert {} {}.pdf
	pdfunite *.pdf "../manga.pdf"
	rm *.pdf
else
	echo "unknown source"
	false
fi

mv ../manga.pdf "$PDF_DIR"/"$name".pdf
rm -rf "$IMG_DIR"