wikipediaのhttpstatusからスクレイピングを行う

mix.exs

defmodule ScrapingWikiHttpstatus.Mixfile do
  use Mix.Project

  def project do
    [app: :scraping_wiki_httpstatus,
     version: "0.1.0",
     elixir: "~> 1.4",
     build_embedded: Mix.env == :prod,
     start_permanent: Mix.env == :prod,
     elixirc_paths: ["."],
     deps: deps()]
  end

  # Configuration for the OTP application
  #
  # Type "mix help compile.app" for more information
  def application do
    # Specify extra applications you'll use from Erlang/Elixir
    [
      extra_applications: [:logger],
      applications: [:httpoison]
    ]
  end

  # Dependencies can be Hex packages:
  #
  #   {:my_dep, "~> 0.3.0"}
  #
  # Or git/path repositories:
  #
  #   {:my_dep, git: "https://github.com/elixir-lang/my_dep.git", tag: "0.1.0"}
  #
  # Type "mix help deps" for more examples and options
  defp deps do
    [
      {:floki, "~> 0.17.2"},
      {:httpoison, "~> 0.11.2"}
    ]
  end
end

scraping_wiki_httpstatus.exs

defmodule Parser do
  def parse(nodes), do: parse(nodes, [], %{})
  def parse([], result, _), do: result
  def parse([head | tail], result, tmp) do
    {tag, _, children_nodes} = head
    text = Floki.text(children_nodes)

    {result, tmp} = case tag do
      "dt" ->
        status_code = text |> String.replace(~r/ .*/, "") |> String.to_integer
        {[tmp | result], %{summary: text, status_code: status_code}}
      "dd" ->
        description =
          case tmp[:description] do
            nil -> text
            desc -> "#{desc}\n#{text}"
          end
       {result, tmp |> Map.put(:description, description)}
    end

    parse(tail, result, tmp)
  end

end

%{body: html} = HTTPoison.get! "https://ja.wikipedia.org/wiki/HTTP%E3%82%B9%E3%83%86%E3%83%BC%E3%82%BF%E3%82%B9%E3%82%B3%E3%83%BC%E3%83%89"

result = html
|> Floki.find("dt, dd")
|> Parser.parse

IO.puts inspect result