Packages

floki

0.23.1
0.38.4 0.38.3 0.38.2 0.38.1 0.38.0 0.37.1 0.37.0 0.36.3 0.36.2 0.36.1 0.36.0 0.35.4 0.35.3 0.35.2 0.35.1 0.35.0 0.34.3 0.34.2 0.34.1 0.34.0 0.33.1 0.33.0 0.32.1 0.32.0 0.31.0 0.30.1 0.30.0 0.29.0 0.28.0 0.27.0 0.26.0 0.25.0 0.24.0 0.23.1 0.23.0 0.22.0 0.21.0 0.20.4 0.20.3 0.20.2 0.20.1 0.20.0 0.19.3 0.19.2 0.19.1 0.19.0 0.18.1 0.18.0 0.17.2 0.17.1 0.17.0 0.16.0 0.15.0 0.14.0 0.13.2 0.13.1 0.13.0 0.12.1 0.12.0 0.11.0 0.10.1 0.10.0 0.9.0 0.8.1 0.8.0 0.7.2 0.7.1 0.7.0 0.6.1 0.6.0 0.5.0 0.4.1 0.4.0 0.3.3 0.3.2 0.3.1 0.3.0 0.2.1 0.2.0 0.1.1 0.1.0 0.0.5 0.0.4 0.0.3 0.0.2 0.0.1

Floki is a simple HTML parser that enables search for nodes using CSS selectors.

HexDocs

Current section

86 Versions

Jump to
Readme
86 Versions
1 Dependency
Dependants
Files
Activity
Hide whitespace

Compare versions

7 files changed
+77 additions
-28 deletions
  @@ -2,7 +2,7 @@
2 2 [![Floki version](https://img.shields.io/hexpm/v/floki.svg)](https://hex.pm/packages/floki)
3 3 [![Hex.pm](https://img.shields.io/hexpm/dt/floki.svg)](https://hex.pm/packages/floki)
4 4 [![Inline docs](https://inch-ci.org/github/philss/floki.svg?branch=master)](https://inch-ci.org/github/philss/floki)
5 - [![Ebert](https://ebertapp.io/github/philss/floki.svg)](https://ebertapp.io/github/philss/floki)
5 + [![SourceLevel](https://app.sourcelevel.io/github/philss/floki.svg)](https://app.sourcelevel.io/github/philss/floki)
6 6
7 7 <img src="assets/images/floki-logo-with-type.svg" width="500" alt="Floki logo">
  @@ -4,23 +4,23 @@
4 4 <<"Floki is a simple HTML parser that enables search for nodes using CSS selectors.">>}.
5 5 {<<"elixir">>,<<"~> 1.5">>}.
6 6 {<<"files">>,
7 - [<<"lib">>,<<"lib/floki">>,<<"lib/floki/html_parser.ex">>,
8 - <<"lib/floki/html_parser">>,<<"lib/floki/html_parser/mochiweb.ex">>,
9 - <<"lib/floki/html_parser/html5ever.ex">>,<<"lib/floki/selector">>,
10 - <<"lib/floki/selector/functional.ex">>,<<"lib/floki/selector/parser.ex">>,
7 + [<<"lib">>,<<"lib/floki">>,<<"lib/floki/html_parser">>,
8 + <<"lib/floki/html_parser/html5ever.ex">>,
9 + <<"lib/floki/html_parser/mochiweb.ex">>,<<"lib/floki/traversal.ex">>,
10 + <<"lib/floki/raw_html.ex">>,<<"lib/floki/selector.ex">>,
11 + <<"lib/floki/selector">>,<<"lib/floki/selector/combinator.ex">>,
11 12 <<"lib/floki/selector/attribute_selector.ex">>,
12 - <<"lib/floki/selector/pseudo_class.ex">>,
13 - <<"lib/floki/selector/tokenizer.ex">>,
14 - <<"lib/floki/selector/combinator.ex">>,<<"lib/floki/deep_text.ex">>,
15 - <<"lib/floki/filter_out.ex">>,<<"lib/floki/flat_text.ex">>,
16 - <<"lib/floki/finder.ex">>,<<"lib/floki/traversal.ex">>,
17 - <<"lib/floki/raw_html.ex">>,<<"lib/floki/html_tree">>,
13 + <<"lib/floki/selector/tokenizer.ex">>,<<"lib/floki/selector/parser.ex">>,
14 + <<"lib/floki/selector/functional.ex">>,
15 + <<"lib/floki/selector/pseudo_class.ex">>,<<"lib/floki/html_tree">>,
18 16 <<"lib/floki/html_tree/id_seeder.ex">>,<<"lib/floki/html_tree/comment.ex">>,
19 - <<"lib/floki/html_tree/text.ex">>,<<"lib/floki/html_tree/html_node.ex">>,
20 - <<"lib/floki/selector.ex">>,<<"lib/floki/html_tree.ex">>,<<"lib/floki.ex">>,
21 - <<"src/floki_selector_lexer.xrl">>,<<"src/floki_mochi_html.erl">>,
22 - <<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,<<"CODE_OF_CONDUCT.md">>,
23 - <<"CONTRIBUTING.md">>]}.
17 + <<"lib/floki/html_tree/html_node.ex">>,<<"lib/floki/html_tree/text.ex">>,
18 + <<"lib/floki/finder.ex">>,<<"lib/floki/filter_out.ex">>,
19 + <<"lib/floki/html_tree.ex">>,<<"lib/floki/html_parser.ex">>,
20 + <<"lib/floki/deep_text.ex">>,<<"lib/floki/flat_text.ex">>,
21 + <<"lib/floki.ex">>,<<"src/floki_selector_lexer.xrl">>,
22 + <<"src/floki_mochi_html.erl">>,<<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,
23 + <<"CODE_OF_CONDUCT.md">>,<<"CONTRIBUTING.md">>]}.
24 24 {<<"licenses">>,[<<"MIT">>]}.
25 25 {<<"links">>,[{<<"GitHub">>,<<"https://github.com/philss/floki">>}]}.
26 26 {<<"name">>,<<"floki">>}.
  @@ -29,5 +29,5 @@
29 29 {<<"name">>,<<"html_entities">>},
30 30 {<<"optional">>,false},
31 31 {<<"repository">>,<<"hexpm">>},
32 - {<<"requirement">>,<<"~> 0.4.0">>}]]}.
33 - {<<"version">>,<<"0.23.0">>}.
32 + {<<"requirement">>,<<"~> 0.5.0">>}]]}.
33 + {<<"version">>,<<"0.23.1">>}.
  @@ -302,6 +302,37 @@ defmodule Floki do
302 302 end
303 303 end
304 304
305 + @doc """
306 + Returns the direct child nodes of a HTML tree.
307 +
308 + By default, it will also include all texts. You can disable this behaviour
309 + by using the option `include_text` to `false`
310 +
311 + ## Examples
312 +
313 + iex> Floki.children({"div", [], ["text", {"span", [], []}]})
314 + ["text", {"span", [], []}]
315 +
316 + iex> Floki.children({"div", [], ["text", {"span", [], []}]}, include_text: false)
317 + [{"span", [], []}]
318 +
319 + """
320 +
321 + @spec children(html_tree, Keyword.t()) :: html_tree
322 +
323 + def children(html, opts \\ [include_text: true]) do
324 + case html do
325 + {_, _, subtree} ->
326 + filter_children(subtree, opts[:include_text])
327 +
328 + _ ->
329 + nil
330 + end
331 + end
332 +
333 + defp filter_children(children, false), do: Enum.filter(children, &is_tuple(&1))
334 + defp filter_children(children, _), do: children
335 +
305 336 @doc """
306 337 Returns a list with attribute values for a given selector.
  @@ -34,6 +34,7 @@ defmodule Floki.RawHTML do
34 34 end
35 35
36 36 defp build_raw_html([], html, _encoder), do: html
37 +
37 38 defp build_raw_html(string, _html, encoder) when is_binary(string), do: encoder.(string)
38 39
39 40 defp build_raw_html(tuple, html, encoder) when is_tuple(tuple),
  @@ -88,11 +89,7 @@ defmodule Floki.RawHTML do
88 89 end
89 90
90 91 defp build_attrs({attr, <<value::binary>>}, attrs) do
91 - if String.contains?(value, "\"") do
92 - ~s(#{attrs} #{attr}='#{value}')
93 - else
94 - ~s(#{attrs} #{attr}="#{value}")
95 - end
92 + "#{attrs} #{attr}=\"#{html_escape_attribute_value(value)}\""
96 93 end
97 94
98 95 defp build_attrs(<<attr::binary>>, attrs), do: "#{attrs} #{attr}"
  @@ -116,4 +113,20 @@ defmodule Floki.RawHTML do
116 113 & &1
117 114 end
118 115 end
116 +
117 + # html_escape
118 +
119 + def html_escape_attribute_value(attribute_value) do
120 + html_escape_chars(attribute_value, ~r/&|"/)
121 + end
122 +
123 + defp html_escape_chars(subject, escaped_chars_regex) do
124 + Regex.replace(escaped_chars_regex, subject, &html_escape_char/1)
125 + end
126 +
127 + defp html_escape_char("<"), do: "&lt;"
128 + defp html_escape_char(">"), do: "&gt;"
129 + defp html_escape_char("&"), do: "&amp;"
130 + defp html_escape_char("\""), do: "&quot;"
131 + defp html_escape_char("'"), do: "&#39;"
119 132 end
  @@ -38,7 +38,7 @@ defmodule Floki.Selector.AttributeSelector do
38 38 def match?(attributes, s = %AttributeSelector{match_type: :includes}) do
39 39 value = get_value(s.attribute, attributes)
40 40
41 - whitespace_values = String.split(value, " ")
41 + whitespace_values = String.split(value, ~r/\s+/)
42 42
43 43 Enum.any?(whitespace_values, fn v -> v == s.value end)
44 44 end
Loading more files…