nemo
/
ickabog-ebook
mirror of https://github.com/captn3m0/ickabog-ebook
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Only english editions should be via Web Archive

master
Nemo 2020-07-28 22:16:49 +05:30
parent a4b44684e4
commit 775d4c7dab
2 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -1,6 +1,6 @@
# ickabog-ebook ![](https://img.shields.io/badge/Chapters%20Published-64-yellow)
# ickabog-ebook ![](https://img.shields.io/badge/Chapters%20Published-64-green)
Generates ebooks for The Ickabog by J.K Rowling. Original text from https://www.theickabog.com/. Supports all 9 languages. Note that not all languages have the complete book translated yet, but the english variants are now complete.
Generates ebooks for The Ickabog by J.K Rowling. Uses original text from https://www.theickabog.com/. Supports all 9 languages.
## Dependencies:

24
generate.sh
View File

@ -13,11 +13,17 @@ LC=${LC:-""}
if [[ "$LC" != "" ]]; then
LC="/$LC"
fi
MAIN_STORY_URL="https://web.archive.org/web/20200713135719/https://www.theickabog.com$LC/read-the-story/"
if [[ "$LC" == "" || "$LC" == "en-US" ]]; then
MAIN_STORY_URL="https://web.archive.org/web/20200713135650/https://www.theickabog.com/$LC/read-the-story/"
else
# Non-english editions are still accessible on the original website.
MAIN_STORY_URL="https://www.theickabog.com$LC/read-the-story/"
fi
echo "[+] Fetching $MAIN_STORY_URL"
wget --quiet "$MAIN_STORY_URL" --output-document "$MAIN_STORY_OUTPUT_FILE"
wget --quiet --timeout=10 "$MAIN_STORY_URL" --output-document "$MAIN_STORY_OUTPUT_FILE"
LANG=$(cat "$MAIN_STORY_OUTPUT_FILE"| pup 'html attr{lang}')
echo "[+] Language set to $LANG"
@ -31,8 +37,18 @@ echo "<html lang=$LANG><head><meta charset=UTF-8><title>$MAIN_TITLE</title></hea
# args = "$url" "$chapter" "$title"
function download_chapter() {
[[ $2 =~ 1$ ]] && MAIN_TITLE=$3
URL=$( [[ $1 =~ ^http ]] && echo "$1" || echo "https://web.archive.org$1" )
[ -s "html/$2.html" ] || wget --quiet "$URL" -O "html/$2.html"
# We have a direct link, so lets use that
if [[ $1 =~ ^http ]]; then
URL="$1"
# For english, we need to make sure we are using the archive link
elif [[ "$LANG" == "en-US" || "$LANG" == "en-GB" ]]; then
URL="https://web.archive.org$1"
# For others cases, let us make it a absolute URL
else
URL="https://www.theickabog.com$1"
fi
echo $URL
[ -s "html/$2.html" ] || wget --timeout=10 --quiet "$URL" -O "html/$2.html"
echo "<h1>$3</h1>" >> "$HTML_FILE"
cat "html/$2.html" | pup -p --charset UTF-8 'article div.row:nth-child(2) div.entry-content' >> "$HTML_FILE"
}