从html中获取table中数据

require \'net/http\'

#以http:\\finance.yahoo.com\q?s=IBM 页面为例子
http = Net::HTTP.new(\'finance.yahoo.com\', 80)
resp, page = http.get(\'/q?s=IBM\', nil )

#传入tag解析出数据
def parse_html(data,tag)
   return data.scan(%r{<#{tag}\s*.*?>(.*?)</#{tag}>}im).flatten
end
#flatten 是一维化数组

output = []
table_data = parse_html(page,"table")
table_data.each do |table|
   out_row = []
   row_data = parse_html(table,"tr")
   row_data.each do |row|
      cell_data = parse_html(row,"td")
      cell_data.each do |cell|
         cell.gsub!(%r{<.*?>},"")
      end
      out_row << cell_data
   end
   output << out_row
end

#组织显示
def parse_nested_array(array,tab = 0)
   n = 0
   array.each do |item|
      if(item.size > 0)
         puts "#{"\t" * tab}[#{n}] {"
         if(item.class == Array)
            parse_nested_array(item,tab+1)
         else
            puts "#{"\t" * (tab+1)}#{item}"
         end
         puts "#{"\t" * tab}}"
      end
      n += 1
   end
end

parse_nested_array(output)