notes on exporting a wordpress site

how.sh

#!/bin/bash

# Create a list of pages from the website, one url per line, in a file named "pages". Easiest
# way for small sites is to get them from the admin interface, open each page in a tab then
# copy all tab URLs to the clipboard via chrome extension:
# https://chrome.google.com/webstore/detail/copy-all-urls/djdmadneanknadilpjiknlnanaolmbfk?hl=en
# Have ripgrep and wget handy. The heavy lifting is done by an html to markdown lib, wrapped here:
# https://github.com/suntong/html2md#usage

for page in $(cat pages); do 
	echo $(basename $page)
	html2md -i $page > $(basename $page)
done 

for image in $(rg -Iio '\(.*\.(png|jpg)\)' | tr -d '()' | sort | uniq); do
	wget $image
done