Quick-and-dirty converter from HTML table to Tab-delimited flat-file. Uses sed and bash. Converts the first table in a HTML document to a Tab-delimited file. Usage: `./tableConverter.sh < file.html`

format.sed

s![ \t]*<!<!g
s!>[ \t]*!>!g

s!<tr>!\
!g

s!</t[dh]><t[dh]>!	!g

s!<table>\n!!g

s!</table.*!!g
s!<[^>]+>!!g

tableConverter.sh

#!/bin/bash

cd "$(dirname "$0")"

tr -d '\n' \
| sed -E $'s!</?(table|t[rdh])!\\\n&!g' \
| sed -Enf trim.sed \
| tr -d '\n' \
| sed -Ef format.sed

trim.sed

/^<table/, /<\/table>/ {
	s!<(/?(table|t[rdh]))[^>]*>!<#\1>!g
	s!<[^#>][^>]*>!!g
	s!<#!<!g
	p
}