ruby – 使用nokogiri在HTML标记之间提取文本

require 'rubygems'
require 'nokogiri'

h = '<h1> Header is here</h1>
  <h2>Header 2 is here</h2>
     <p> Extract me!</p>
     <p> Extract me too!</p>
  <h2> Next Header 2</h2>
     <p>not interested</p>
     <p>not interested</p>
  <h2>Header 2 is here</h2>
     <p> Extract me!</p>
     <p> Extract me too!</p>
'

doc = Nokogiri::HTML(h)

# Specify the range between delimiter tags that you want to extract
# triple dot is used to exclude the end point
# 1...2 means 1 and not 2
EXTRACT_RANGES = [
  2...3,4...5
]

# Tags which count as delimiters,not to be extracted
DELIMITER_TAGS = [
  "h1","h2"
]

extracted_text = []

i = 0
# Change /"html"/"body" to the correct path of the tag which contains this list
(doc/"html"/"body").children.each do |el|

  if (DELIMITER_TAGS.include? el.name)
    i += 1
  else
    extract = false
    EXTRACT_RANGES.each do |cur_range|
      if (cur_range.include? i)
        extract = true
        break
      end
    end

    if extract
      s = el.inner_text.strip
      unless s.empty?
        extracted_text << el.inner_text.strip
      end
    end
  end

end

# Print out extracted text (each element's inner text is separated by newlines)
puts extracted_text.join("n")