hn.sh

#!/bin/sh

# example converts an html table to json using pup & jq
# unfortunately, it appears pup does not natively decode characters within the
# html transform? tried using the --plain flag but no dice.
curl -s https://news.ycombinator.com/ \
    | pup 'table table tr:nth-last-of-type(n+2) td.title a json{}' \
    | jq '.[]|{href,text}|select(.text!=null)' \
    | jq -s '.'


# example using htmlq and hxclean to extract a simple table from existing html
curl -s https://news.ycombinator.com/ \
    | htmlq --pretty tr[class="athing"] -b https://news.ycombinator.com \
    | hxclean > hn.html