Packages

floki

0.7.2
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

10 files changed
+128 additions
-157 deletions
  @@ -7,14 +7,11 @@
7 7
8 8 Floki is a simple HTML parser that enables search for nodes using CSS selectors.
9 9
10 - You can perform searches using classes, attributes, tag names and IDs.
11 - You can also combine selectors and use groups, like: `"a.foo[data-action='bar'], .baz.zaz"`.
12 -
13 10 [Check the documentation](http://hexdocs.pm/floki).
14 11
15 12 ## Usage
16 13
17 - Assuming that you have the following HTML:
14 + Take this HTML as an example:
18 15
19 16 ```html
20 17 <!doctype html>
  @@ -97,7 +94,7 @@ It is simple as that!
97 94
98 95 ## Installation
99 96
100 - You can install Floki by adding a dependency to your mix file (mix.exs):
97 + Add Floki in your `mix.exs`, as a dependency:
101 98
102 99 ```elixir
103 100 defp deps do
  @@ -1,7 +1,7 @@
1 1 {<<"app">>,<<"floki">>}.
2 2 {<<"build_tools">>,[<<"mix">>]}.
3 3 {<<"description">>,
4 - <<"A HTML parser and searcher.\n\nYou can search inside HTML documents using CSS selectors.">>}.
4 + <<"Floki is a simple HTML parser that enables search for nodes using CSS selectors.">>}.
5 5 {<<"elixir">>,<<">= 1.0.0">>}.
6 6 {<<"files">>,
7 7 [<<"lib/floki.ex">>,<<"lib/floki/attribute_selector.ex">>,
  @@ -22,4 +22,4 @@
22 22 [{<<"app">>,<<"mochiweb">>},
23 23 {<<"optional">>,false},
24 24 {<<"requirement">>,<<"~> 2.12.2">>}]}]}.
25 - {<<"version">>,<<"0.7.1">>}.
25 + {<<"version">>,<<"0.7.2">>}.
  @@ -1,13 +1,10 @@
1 1 defmodule Floki do
2 2 alias Floki.Finder
3 3 alias Floki.Parser
4 + alias Floki.FilterOut
4 5
5 6 @moduledoc """
6 - A HTML parser and seeker.
7 -
8 - This is a simple HTML parser that enables searching using CSS like selectors.
9 -
10 - You can search elements by class, tag name and id.
7 + Floki is a simple HTML parser that enables search for nodes using CSS selectors.
11 8
12 9 ## Example
13 10
  @@ -26,14 +23,14 @@ defmodule Floki do
26 23 </html>
27 24 ```
28 25
29 - You can perform the following queries:
26 + Examples of queries that you can perform:
30 27
31 - * Floki.find(html, "#content") : returns the section with all children;
32 - * Floki.find(html, ".headline") : returns a list with the `p` element;
33 - * Floki.find(html, "a") : returns a list with the `a` element;
34 - * Floki.find(html, "[data-model=user]") : returns a list with elements that match that data attribute;
35 - * Floki.find(html, "#content a") # returns all links inside content section;
36 - * Floki.find(html, ".headline, a") # returns the .headline elements and links.
28 + * Floki.find(html, "#content")
29 + * Floki.find(html, ".headline")
30 + * Floki.find(html, "a")
31 + * Floki.find(html, "[data-model=user]")
32 + * Floki.find(html, "#content a")
33 + * Floki.find(html, ".headline, a")
37 34
38 35 Each HTML node is represented by a tuple like:
39 36
  @@ -91,6 +88,8 @@ defmodule Floki do
91 88
92 89 """
93 90
91 + @spec raw_html(html_tree) :: binary
92 +
94 93 def raw_html(html_tree), do: raw_html(html_tree, "")
95 94 defp raw_html([], html), do: html
96 95 defp raw_html(tuple, html) when is_tuple(tuple), do: raw_html([tuple], html)
  @@ -138,7 +137,7 @@ defmodule Floki do
138 137 @spec find(binary | html_tree, binary) :: html_tree
139 138
140 139 def find(html, selector) when is_binary(html) do
141 - parse(html) |> Finder.find(selector)
140 + html |> parse |> Finder.find(selector)
142 141 end
143 142 def find(html_tree, selector) do
144 143 Finder.find(html_tree, selector)
  @@ -170,14 +169,15 @@ defmodule Floki do
170 169
171 170 def text(html, opts \\ [deep: true, js: false]) do
172 171 html_tree =
173 - case is_binary(html) do
174 - true -> parse(html)
175 - false -> html
172 + if is_binary(html) do
173 + parse(html)
174 + else
175 + html
176 176 end
177 177
178 178 cleaned_html_tree =
179 179 case opts[:js] do
180 - true -> html_tree
180 + true -> html_tree
181 181 _ -> filter_out(html_tree, "script")
182 182 end
183 183
  @@ -262,6 +262,9 @@ defmodule Floki do
262 262 iex> Floki.filter_out([{"body", [], [{"script", [], []},{"div", [], []}]}], "script")
263 263 [{"body", [], [{"div", [], []}]}]
264 264
265 + iex> Floki.filter_out("<div><!-- comment --> text</div>", :comment)
266 + {"div", [], [" text"]}
267 +
265 268 """
266 269
267 270 @spec filter_out(binary | html_tree, binary) :: list
  @@ -269,11 +272,9 @@ defmodule Floki do
269 272 def filter_out(html_tree, selector) when is_binary(html_tree) do
270 273 html_tree
271 274 |> parse
272 - |> Floki.FilterOut.filter_out(selector)
275 + |> FilterOut.filter_out(selector)
273 276 end
274 277 def filter_out(elements, selector) do
275 - Floki.FilterOut.filter_out(elements, selector)
278 + FilterOut.filter_out(elements, selector)
276 279 end
277 -
278 -
279 280 end
  @@ -22,7 +22,7 @@ defmodule Floki.AttributeSelector do
22 22
23 23 whitespace_values = String.split(value, " ")
24 24
25 - Enum.any? whitespace_values, fn(v) -> v == s.value end
25 + Enum.any?(whitespace_values, fn(v) -> v == s.value end)
26 26 end
27 27 def match?(attributes, s = %AttributeSelector{match_type: :dash_match}) do
28 28 value = get_value(s.attribute, attributes)
  @@ -30,24 +30,24 @@ defmodule Floki.AttributeSelector do
30 30 value == s.value || String.starts_with?(value, "#{s.value}-")
31 31 end
32 32 def match?(attributes, s = %AttributeSelector{match_type: :prefix_match}) do
33 - get_value(s.attribute, attributes) |> String.starts_with?(s.value)
33 + s.attribute |> get_value(attributes) |> String.starts_with?(s.value)
34 34 end
35 35 def match?(attributes, s = %AttributeSelector{match_type: :sufix_match}) do
36 - get_value(s.attribute, attributes) |> String.ends_with?(s.value)
36 + s.attribute |> get_value(attributes) |> String.ends_with?(s.value)
37 37 end
38 38 def match?(attributes, s = %AttributeSelector{match_type: :substring_match}) do
39 - get_value(s.attribute, attributes) |> String.contains?(s.value)
39 + s.attribute |> get_value(attributes) |> String.contains?(s.value)
40 40 end
41 41
42 42 defp get_value(attr_name, attributes) do
43 - {_attr_name, value} = Enum.find attributes, {attr_name, ""}, fn({k, _v}) ->
43 + {_attr_name, value} = Enum.find(attributes, {attr_name, ""}, fn({k, _v}) ->
44 44 k == attr_name
45 - end
45 + end)
46 46
47 47 value
48 48 end
49 49
50 50 defp attribute_present?(name, attributes) do
51 - Enum.any? attributes, fn({k, _v}) -> k == name end
51 + Enum.any?(attributes, fn({k, _v}) -> k == name end)
52 52 end
53 53 end
  @@ -29,6 +29,7 @@ defmodule Floki.DeepText do
29 29 end
30 30 end
31 31 defp get_text({:comment, _}, acc), do: acc
32 + defp get_text({"br", _, _}, acc), do: acc <> "\n"
32 33 defp get_text({_, _, nodes}, acc) do
33 34 get_text(nodes, acc)
34 35 end
Loading more files…