Initial commit

2020-05-29 01:13:58 +05:30 · 2020-05-29 01:13:58 +05:30 · 20ecbdb3ae
commit 20ecbdb3ae
4 changed files with 68 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,3 @@
+*.html
+*.epub
+*.pdf
--- a/README.md
+++ b/README.md
@ -0,0 +1,23 @@
+# ickabog-ebook
+
+Generates ebooks for The Ickabog by J.K Rowling. Original text from https://www.theickabog.com/home/
+
+## Dependencies:
+
+- `wget`
+- [`pup`](https://github.com/ericchiang/pup)
+- [`pandoc`](https://pandoc.org/)
+
+## How to run
+
+`./generate.sh`
+
+You should have `ickabog.epub`, and `ickabog.pdf` in your directory after the script finishes.
+
+## Cover
+
+Currently no cover is available. If you'd like to submit a cover for this book, please let me know. I think a kid-drawn illustration would be perfect, keeping with the theme of the contest.
+
+## License
+
+Licensed under the [MIT License](https://nemo.mit-license.org/). See LICENSE file for details.
--- a/generate.sh
+++ b/generate.sh
@ -0,0 +1,38 @@
+#!/bin/bash
+
+HTML_FILE=ickabog.html
+echo "<html><head><title>The Ickabog</title></head><body>" > "$HTML_FILE"
+wget https://www.theickabog.com/king-fred-the-fearless/ -O ch1.html
+wget https://www.theickabog.com/the-ickabog/ -O ch2.html
+wget https://www.theickabog.com/death-of-a-seamstress/ -O ch3.html
+wget https://www.theickabog.com/the-quiet-house/ -O ch4.html
+wget https://www.theickabog.com/daisy-dovetail/ -O ch5.html
+wget https://www.theickabog.com/the-fight-in-the-courtyard/ -O ch6.html
+wget https://www.theickabog.com/lord-spittleworth-tells-tales/ -O ch7.html
+wget https://www.theickabog.com/the-day-of-petition/ -O ch8.html
+
+for i in $(seq 1 8); do
+  CHAPTER_TITLE=$(cat "ch$i.html" | pup 'h1.entry-title:nth-child(2) text{}')
+  echo "<h2>$CHAPTER_TITLE</h2>" >> "$HTML_FILE"
+  cat "ch$i.html" | pup 'article div.row:nth-child(2) div.entry-content' >> "$HTML_FILE"
+done
+
+echo "</body></html>" >> "$HTML_FILE"
+
+pandoc --from=html --to=pdf \
+    --output=ickabog.pdf \
+    --metadata title="The Ickabog" \
+    --metadata author="J.K Rowling" \
+    --pdf-engine=xelatex \
+    --dpi=300 \
+    -V book \
+    -V lang=en-US \
+    -V geometry=margin=3cm \
+    --columns=60 \
+    "$HTML_FILE"
+
+pandoc --from=html --to=epub \
+    --output=ickabog.epub \
+    --epub-metadata=metadata.xml \
+    --metadata title="The Ickabog" \
+    "$HTML_FILE"
--- a/metadata.xml
+++ b/metadata.xml
@ -0,0 +1,4 @@
+<dc:title id="epub-title-1">The Ickabog</dc:title>
+<dc:date>2020-05-20</dc:date>
+<dc:language>en-US</dc:language>
+<dc:creator id="epub-creator-1" opf:role="aut">The Ickabog</dc:creator>