Packages

floki

0.13.2
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

6 files changed
+39 additions
-31 deletions
  @@ -34,13 +34,16 @@ Here are some queries that you can perform (with return examples):
34 34 ```elixir
35 35 Floki.find(html, "#content")
36 36 # => [{"section", [{"id", "content"}],
37 - # => [{"p", [{"class", "headline"}], ["Floki"]},
38 - # => {"a", [{"href", "http://github.com/philss/floki"}], ["Github page"]}]}]
37 + # => [{"p", [{"class", "headline"}], ["Floki"]},
38 + # => {"span", [{"class", "headline"}], ["Enables search using CSS selectors"]},
39 + # => {"a", [{"href", "http://github.com/philss/floki"}], ["Github page"]},
40 + # => {"span", [{"data-model", "user"}], ["philss"]}]}]
39 41
40 42
41 43 Floki.find(html, "p.headline")
42 44 # => [{"p", [{"class", "headline"}], ["Floki"]}]
43 45
46 +
44 47 Floki.find(html, "p.headline")
45 48 |> Floki.raw_html
46 49 # => <p class="headline">Floki</p>
  @@ -52,8 +55,7 @@ Floki.find(html, "a")
52 55
53 56
54 57 Floki.find(html, "a[href^=https]")
55 - # => [{"a", [{"href", "http://github.com/philss/floki"}], ["Github page"]},
56 - # => {"a", [{"href", "https://hex.pm/packages/floki"}], ["Hex package"]}]
58 + # => [{"a", [{"href", "https://hex.pm/packages/floki"}], ["Hex package"]}]
57 59
58 60
59 61 Floki.find(html, "#content a")
  @@ -64,7 +66,7 @@ Floki.find(html, "[data-model=user]")
64 66 # => [{"span", [{"data-model", "user"}], ["philss"]}]
65 67
66 68
67 - Floki.find(html, ".headline, a")
69 + Floki.find(html, ".headline:nth-child(1), a")
68 70 # => [{"p", [{"class", "headline"}], ["Floki"]},
69 71 # => {"a", [{"href", "http://github.com/philss/floki"}], ["Github page"]},
70 72 # => {"a", [{"href", "https://hex.pm/packages/floki"}], ["Hex package"]}]
  @@ -95,12 +97,12 @@ It is simple as that!
95 97
96 98 ## Installation
97 99
98 - Add Floki in your `mix.exs`, as a dependency:
100 + Add Floki to your `mix.exs`:
99 101
100 102 ```elixir
101 103 defp deps do
102 104 [
103 - {:floki, "~> 0.13.1"}
105 + {:floki, "~> 0.13.2"}
104 106 ]
105 107 end
106 108 ```
  @@ -25,4 +25,4 @@
25 25 {<<"name">>,<<"mochiweb">>},
26 26 {<<"optional">>,false},
27 27 {<<"requirement">>,<<"~> 2.15">>}]]}.
28 - {<<"version">>,<<"0.13.1">>}.
28 + {<<"version">>,<<"0.13.2">>}.
  @@ -154,9 +154,8 @@ defmodule Floki do
154 154 end
155 155
156 156 def transform(html_tree_list, transformation) when is_list(html_tree_list) do
157 - html_tree_list |> Enum.map(fn
158 - html_tree ->
159 - Finder.apply_transformation(html_tree, transformation)
157 + Enum.map(html_tree_list, fn(html_tree) ->
158 + Finder.apply_transformation(html_tree, transformation)
160 159 end)
161 160 end
162 161 def transform(html_tree, transformation) do
  @@ -68,8 +68,7 @@ defmodule Floki.Finder do
68 68 end
69 69
70 70 defp get_matches_for_selectors(tree, html_node, selectors) do
71 - selectors
72 - |> Enum.flat_map(fn(selector) -> get_matches(tree, html_node, selector) end)
71 + Enum.flat_map(selectors, fn(selector) -> get_matches(tree, html_node, selector) end)
73 72 end
74 73
75 74 defp get_matches(tree, html_node, selector = %Selector{combinator: nil}) do
  @@ -157,8 +156,7 @@ defmodule Floki.Finder do
157 156 results =
158 157 Enum.flat_map(stack, fn(html_node) ->
159 158 ids_to_match = get_descendant_ids(html_node.node_id, tree)
160 - nodes = ids_to_match
161 - |> get_nodes(tree)
159 + nodes = get_nodes(ids_to_match, tree)
162 160
163 161 Enum.filter(nodes, fn(html_node) -> Selector.match?(html_node, s) end)
164 162 end)
  @@ -202,7 +200,7 @@ defmodule Floki.Finder do
202 200 defp get_descendant_ids(node_id, tree) do
203 201 case get_node(node_id, tree) do
204 202 %{children_nodes_ids: node_ids} ->
205 - Enum.reverse(node_ids) ++ Enum.flat_map(node_ids, &( get_descendant_ids(&1, tree) ))
203 + Enum.reverse(node_ids) ++ Enum.flat_map(node_ids, &(get_descendant_ids(&1, tree)))
206 204 _ ->
207 205 []
208 206 end
  @@ -13,11 +13,12 @@ defmodule Floki.HTMLTree do
13 13
14 14 def build({tag, attrs, children}) do
15 15 root_id = IDSeeder.seed([])
16 + root_node = %HTMLNode{type: tag, attributes: attrs, node_id: root_id}
16 17
17 - %HTMLTree{root_nodes_ids: [root_id],
18 - node_ids: [root_id],
19 - nodes: %{root_id => %HTMLNode{type: tag, attributes: attrs, node_id: root_id}}}
20 - |> build_tree(children, root_id, [])
18 + build_tree(%HTMLTree{root_nodes_ids: [root_id],
19 + node_ids: [root_id],
20 + nodes: %{root_id => root_node}},
21 + children, root_id, [])
21 22 end
22 23
23 24 def build(html_tuples) when is_list(html_tuples) do
  @@ -27,10 +28,18 @@ defmodule Floki.HTMLTree do
27 28
28 29 root_node = %HTMLNode{type: tag, attributes: attrs, node_id: root_id}
29 30
30 - %{tree | nodes: Map.put(tree.nodes, root_id, root_node),
31 - node_ids: [root_id | tree.node_ids],
32 - root_nodes_ids: tree.root_nodes_ids ++ [root_id]}
33 - |> build_tree(children, root_id, [])
31 + build_tree(%{tree | nodes: Map.put(tree.nodes, root_id, root_node),
32 + node_ids: [root_id | tree.node_ids],
33 + root_nodes_ids: tree.root_nodes_ids ++ [root_id]},
34 + children, root_id, [])
35 + (text, tree) when is_binary(text) ->
36 + root_id = IDSeeder.seed(tree.node_ids)
37 +
38 + root_node = %Text{content: text, node_id: root_id}
39 + build_tree(%{tree | nodes: Map.put(tree.nodes, root_id, root_node),
40 + node_ids: [root_id | tree.node_ids],
41 + root_nodes_ids: tree.root_nodes_ids ++ [root_id]},
42 + [], root_id, [])
34 43 (_, tree) ->
35 44 tree
36 45 end
  @@ -97,8 +106,8 @@ defmodule Floki.HTMLTree do
97 106
98 107 nodes = put_new_node(tree.nodes, new_node)
99 108
100 - %{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]}
101 - |> build_tree(child_children, new_id, [{parent_id, children} | stack])
109 + build_tree(%{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]},
110 + child_children, new_id, [{parent_id, children} | stack])
102 111 end
103 112 defp build_tree(tree, [{:comment, comment} | children], parent_id, stack) do
104 113 new_id = IDSeeder.seed(tree.node_ids)
  @@ -106,8 +115,8 @@ defmodule Floki.HTMLTree do
106 115
107 116 nodes = put_new_node(tree.nodes, new_node)
108 117
109 - %{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]}
110 - |> build_tree(children, parent_id, stack)
118 + build_tree(%{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]},
119 + children, parent_id, stack)
111 120 end
112 121 defp build_tree(tree, [text | children], parent_id, stack) when is_binary(text) do
113 122 new_id = IDSeeder.seed(tree.node_ids)
  @@ -115,8 +124,8 @@ defmodule Floki.HTMLTree do
115 124
116 125 nodes = put_new_node(tree.nodes, new_node)
117 126
118 - %{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]}
119 - |> build_tree(children, parent_id, stack)
127 + build_tree(%{tree | nodes: nodes, node_ids: [new_id | tree.node_ids]},
128 + children, parent_id, stack)
120 129 end
121 130 defp build_tree(tree, [_other | children], parent_id, stack) do
122 131 build_tree(tree, children, parent_id, stack)
Loading more files…