Packages

floki

0.0.5
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
0 Dependencies
Dependants
Files
Activity
Hide whitespace

Compare versions

4 files changed
+67 additions
-21 deletions
  @@ -3,8 +3,6 @@ Floki
3 3
4 4 [![Build Status](https://travis-ci.org/philss/floki.svg?branch=master)](https://travis-ci.org/philss/floki)
5 5
6 - A HTML parser and seeker.
7 -
8 6 This is a simple HTML parser that enables searching using CSS like selectors.
9 7
10 8 You can search elements by class, tag name and id.
  @@ -16,6 +14,7 @@ You can search elements by class, tag name and id.
16 14 Assuming that you have the following HTML:
17 15
18 16 ```html
17 + <!doctype html>
19 18 <html>
20 19 <body>
21 20 <section id="content">
  @@ -90,10 +89,19 @@ You can also get attributes from elements that you already have:
90 89
91 90 ```elixir
92 91 Floki.find(html, ".example")
93 - |> Floki.attribute("class")
92 + |> Floki.attribute("class")
94 93 # => ["example"]
95 94 ```
96 95
96 + If you want to get the text from an element, try:
97 +
98 + ```elixir
99 + Floki.find(html, ".headline")
100 + |> Floki.text
101 +
102 + # => "Floki"
103 + ```
104 +
97 105 ## License
98 106
99 107 Floki is under MIT license. Check the `LICENSE` file for more details.
  @@ -3,7 +3,7 @@
3 3 {<<"contributors">>,[<<"Philip Sampaio Silva">>]}.
4 4 {<<"description">>,
5 5 <<"A HTML parser and seeker.\n\nYou can search inside HTML documents using CSS like selectors.\n">>}.
6 - {<<"elixir">>,<<"~> 1.0.0">>}.
6 + {<<"elixir">>,<<">= 1.0.0">>}.
7 7 {<<"files">>,
8 8 [<<"lib/floki.ex">>,<<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,
9 9 <<"src/mochinum.erl">>,<<"src/mochiutf8.erl">>,
  @@ -14,4 +14,4 @@
14 14 <<"GitHub">> => <<"https://github.com/philss/floki">>}}.
15 15 {<<"name">>,<<"floki">>}.
16 16 {<<"requirements">>,#{}}.
17 - {<<"version">>,<<"0.0.4">>}.
17 + {<<"version">>,<<"0.0.5">>}.
  @@ -71,7 +71,7 @@ defmodule Floki do
71 71 It is possible to compose searches:
72 72
73 73 Floki.find(html_string, ".class")
74 - |> Floki.find(".another-class-inside-small-scope"
74 + |> Floki.find(".another-class-inside-small-scope")
75 75
76 76 ## Examples
77 77
  @@ -90,22 +90,22 @@ defmodule Floki do
90 90
91 91 def find(html, selector) when is_binary(html) do
92 92 parse(html)
93 - |> find(selector)
93 + |> find(selector)
94 94 end
95 95
96 96 def find(html_tree, "." <> class) do
97 97 find_by_selector(class, html_tree, &class_matcher/3, [])
98 - |> Enum.reverse
98 + |> Enum.reverse
99 99 end
100 100
101 101 def find(html_tree, "#" <> id) do
102 102 find_by_selector(id, html_tree, &id_matcher/3, [])
103 - |> List.first
103 + |> List.first
104 104 end
105 105
106 106 def find(html_tree, tag_name) do
107 107 find_by_selector(tag_name, html_tree, &tag_matcher/3, [])
108 - |> Enum.reverse
108 + |> Enum.reverse
109 109 end
110 110
111 111 @doc """
  @@ -122,8 +122,8 @@ defmodule Floki do
122 122
123 123 def attribute(html, selector, attribute_name) do
124 124 html
125 - |> find(selector)
126 - |> get_attribute_values(attribute_name)
125 + |> find(selector)
126 + |> get_attribute_values(attribute_name)
127 127 end
128 128
129 129 @doc """
  @@ -140,21 +140,52 @@ defmodule Floki do
140 140
141 141 def attribute(elements, attribute_name) do
142 142 elements
143 - |> get_attribute_values(attribute_name)
143 + |> get_attribute_values(attribute_name)
144 + end
145 +
146 +
147 + @doc """
148 + Returns the text nodes from a html tree.
149 +
150 + ## Examples
151 +
152 + iex> Floki.text("<div><span>something else</span>hello world</div>")
153 + "hello world"
154 +
155 + """
156 +
157 + @spec text(html_tree | binary) :: binary
158 +
159 + def text(html) when is_binary(html), do: parse(html) |> text
160 + def text(element) when is_tuple(element), do: text(element, "")
161 + def text(elements) do
162 + Enum.reduce elements, "", fn(element, str) ->
163 + text(element, str)
164 + end
165 + end
166 +
167 + defp text({_, _, children}, acc) do
168 + Enum.reduce children, acc, fn(child, istr) ->
169 + if is_binary(child) do
170 + (istr <> "\s" <> child) |> String.strip
171 + else
172 + istr
173 + end
174 + end
144 175 end
145 176
146 177
147 178 defp attribute_match?(attributes, attribute_name) do
148 - attributes |> Enum.find(fn({attr_name, _}) ->
179 + Enum.find(attributes, fn({ attr_name, _ }) ->
149 180 attr_name == attribute_name
150 181 end)
151 182 end
152 183
153 - defp attribute_match?(attributes, attribute_name, value) do
184 + defp attribute_match?(attributes, attribute_name, selector_value) do
154 185 Enum.find(attributes, fn(attribute) ->
155 186 { attr_name, attr_value } = attribute
156 187
157 - attr_name == attribute_name && String.contains?(attr_value, value)
188 + attr_name == attribute_name && value_match?(attr_value, selector_value)
158 189 end)
159 190 end
160 191
  @@ -165,6 +196,7 @@ defmodule Floki do
165 196 acc = find_by_selector(selector, h, matcher, acc)
166 197 find_by_selector(selector, t, matcher, acc)
167 198 end
199 + # Ignores comments
168 200 defp find_by_selector(_selector, { :comment, _comment }, _, acc), do: acc
169 201 defp find_by_selector(selector, node, matcher, acc) when is_tuple(node) do
170 202 { _, _, child_node } = node
  @@ -184,8 +216,8 @@ defmodule Floki do
184 216
185 217 attribute_match?(attributes, attr_name)
186 218 end)
187 - |> Enum.reject(fn(x) -> is_nil(x) end)
188 - |> Enum.map(fn({_attr_name, value}) -> value end)
219 + |> Enum.reject(fn(x) -> is_nil(x) end)
220 + |> Enum.map(fn({_attr_name, value}) -> value end)
189 221 end
190 222
191 223 defp class_matcher(class_name, node, acc) do
  @@ -217,4 +249,10 @@ defmodule Floki do
217 249
218 250 acc
219 251 end
252 +
253 + defp value_match?(attribute_value, selector_value) do
254 + attribute_value
255 + |> String.split
256 + |> Enum.any?(fn(x) -> x == selector_value end)
257 + end
220 258 end
  @@ -3,11 +3,11 @@ defmodule Floki.Mixfile do
3 3
4 4 def project do
5 5 [app: :floki,
6 - version: "0.0.4",
7 - elixir: "~> 1.0.0",
6 + version: "0.0.5",
7 + elixir: ">= 1.0.0",
8 8 package: package,
9 9 description: description,
10 - docs: [readme: true, main: "README"],
10 + docs: [readme: "README.md"],
11 11 deps: deps]
12 12 end