Parse Technorati-style Tags from HTML (See related posts)

class String
  # Strips any html markup from a string
  TYPO_TAG_KEY = TYPO_ATTRIBUTE_KEY = /[\w:_-]+/
  TYPO_ATTRIBUTE_VALUE = /(?:[A-Za-z0-9]+|(?:'[^']*?'|"[^"]*?"))/
  TYPO_ATTRIBUTE = /(?:#{TYPO_ATTRIBUTE_KEY}(?:\s*=\s*#{TYPO_ATTRIBUTE_VALUE})?)/
  TYPO_ATTRIBUTES = /(?:#{TYPO_ATTRIBUTE}(?:\s+#{TYPO_ATTRIBUTE})*)/
  TAG = %r{<[!/?\[]?(?:#{TYPO_TAG_KEY}|--)(?:\s+#{TYPO_ATTRIBUTES})?\s*(?:[!/?\]]+|--)?>}
  def strip_html
    self.gsub(TAG, '').gsub(/\s+/, ' ').strip
  end

  def tags
    scan(/<a\s+[^>]*\s*rel=\s*(.?)tag\1[^>]*>(.+?)<\/a>/i).
    map { |match| match.last.strip_html rescue nil }.
    compact.select { |s| !s.strip.empty? }
  end
end

# Example usage

s = %{<a href="http://www.docstrangelove.com/tag/civil-war" rel="tag">civil war</a> <a href="http://www.technorati.com/tag/civil+war" rel="tag"><img src="http://www.docstrangelove.com/wp-content/plugins/UltimateTagWarrior/technoratiicon.jpg" alt="Technorati tag page for civil war"/></a> <a href="http://www.docstrangelovecom/tag/iraq" rel="tag">iraq</a> <a href="http://www.technorati.com/tag/iraq" rel="tag"><img src="http://www.docstrangelove.com/wp-content/plugins/UltimateTagWarrior/technoratiicon.jpg" alt="Technorati tag page for iraq"/></a>}

s.tags
# => ["civil war", "iraq"]