# pup
#
# pup is a command line tool for processing HTML
# It reads from stdin, prints to stdout, and allows the user to filter parts of the page using CSS selectors.

# install pup
# (requires go)
go install github.com/ericchiang/pup

# indent and colorize HTML
cat file.html | pup --color

# filter by tag
cat file.html | pup 'title'

# pseudoclass: filter by content "History"
cat file.html | pup ':contains("History")'

# multiple groups of selectors
cat file.html | pup 'title, h1 span[dir="auto"]'