get content from tagged pdf

getcontent.lua

local doit = true
for line in io.lines(arg[1]) do
  if doit and line:find"<?MarkedContent " then
    local content = line:match">(.-)$"
    if content and content ~= "" then
      io.write(content)
    end
  elseif doit and line:find"</?P[%s>]" then
    io.write"\n"
  elseif line:find"<Lbl " then
    doit = false
  elseif line:find"</Lbl>" then
    doit = true
  elseif doit and line:find"<FENote " then
    io.write"\\footnote{"
  elseif doit and line:find"</FENote>" then
    io.write"}"
  end
end

getcontent2.lua

for line in io.lines(arg[1]) do
  if line:find"<?MarkedContent%s" then
    local content = line:match">(.-)$"
    if content and content ~= "" then
      io.write(content)
    end
  elseif line:find"</?P[%s>]" 
    or line:find"</?Title[%s>]"
    or line:find"</?H%d[%s>]"
    or line:find"<FENote[%s]" then
    io.write"\n" 
  end 
end