floki

0.11.0

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

HexDocs

Current section

86 Versions

Jump to

Compare versions

From To

7 files changed

+36 additions

-14 deletions

	@@ -100,7 +100,7 @@ Add Floki in your `mix.exs`, as a dependency:
100 100	```elixir
101 101	defp deps do
102 102	[
103	- {:floki, "~> 0.10.1"}
103	+ {:floki, "~> 0.11.0"}
104 104	]
105 105	end
106 106	```

	@@ -18,8 +18,8 @@
18 18	{<<"maintainers">>,[<<"Philip Sampaio Silva">>]}.
19 19	{<<"name">>,<<"floki">>}.
20 20	{<<"requirements">>,
21	- [[{<<"app">>,<<"mochiweb_html">>},
22	- {<<"name">>,<<"mochiweb_html">>},
21	+ [[{<<"app">>,<<"mochiweb">>},
22	+ {<<"name">>,<<"mochiweb">>},
23 23	{<<"optional">>,false},
24 24	{<<"requirement">>,<<"~> 2.15">>}]]}.
25	- {<<"version">>,<<"0.10.1">>}.
25	+ {<<"version">>,<<"0.11.0">>}.

	@@ -74,7 +74,7 @@ defmodule Floki do
74 74	Parser.parse(html)
75 75	end
76 76
77	- @self_closing_tags ["area", "base", "br", "col", "command", "embed", "hr", "img", "input", "keygen", "link", "mete", "param", "source", "track", "wbr"]
77	+ @self_closing_tags ["area", "base", "br", "col", "command", "embed", "hr", "img", "input", "keygen", "link", "meta", "param", "source", "track", "wbr"]
78 78
79 79	@doc """
80 80	Converts HTML tree to raw HTML.
	@@ -149,6 +149,16 @@ defmodule Floki do
149 149	Finder.find(html_tree, selector)
150 150	end
151 151
152	+ def transform(html_tree_list, transformation) when is_list(html_tree_list) do
153	+ html_tree_list \|> Enum.map(fn
154	+ html_tree ->
155	+ Finder.apply_transformation(html_tree, transformation)
156	+ end)
157	+ end
158	+ def transform(html_tree, transformation) do
159	+ Finder.apply_transformation(html_tree, transformation)
160	+ end
161	+
152 162	@doc """
153 163	Returns the text nodes from a HTML tree.
154 164	By default, it will perform a deep search through the HTML tree.

	@@ -30,6 +30,18 @@ defmodule Floki.Finder do
30 30	find_selectors(html_tree, [selector])
31 31	end
32 32
33	+ def apply_transformation({name, attrs, rest}, transformation) do
34	+ {new_name, new_attrs} = transformation.({name, attrs})
35	+
36	+ new_rest = Enum.map(rest, fn(html_tree) ->
37	+ apply_transformation(html_tree, transformation)
38	+ end)
39	+
40	+ {new_name, new_attrs, new_rest}
41	+ end
42	+
43	+ def apply_transformation(other, _transformation), do: other
44	+
33 45	defp find_selectors(html_tree, selectors) do
34 46	html_tree
35 47	\|> traverse([], selectors, [])

	@@ -1,4 +1,6 @@
1 1	defmodule Floki.SelectorParser do
2	+ require Logger
3	+
2 4	@moduledoc """
3 5	Parses a list of tokens returned from `SelectorTokenizer` and transfor into a `Selector`.
4 6	"""
	@@ -59,8 +61,7 @@ defmodule Floki.SelectorParser do
59 61	do_parse(t, %{selector \| combinator: combinator})
60 62	end
61 63	defp do_parse([{:unknown, _, unknown}\|t], selector) do
62	- # TODO: find a better way to notify unknown tokens
63	- IO.puts("Unknown token #{inspect unknown}. Ignoring.")
64	+ Logger.warn("Unknown token #{inspect unknown}. Ignoring.")
64 65
65 66	do_parse(t, selector)
66 67	end
	@@ -84,8 +85,7 @@ defmodule Floki.SelectorParser do
84 85	consume_attribute(:done, t, attr_selector)
85 86	end
86 87	defp consume_attribute(:consuming, [unknown\|t], attr_selector) do
87	- # TODO: find a better way to notify unknown tokens
88	- IO.puts("Unknown token #{inspect unknown}. Ignoring.")
88	+ Logger.warn("Unknown token #{inspect unknown}. Ignoring.")
89 89	consume_attribute(:consuming, t, attr_selector)
90 90	end

Loading more files…

Operator	Description	Example
name:	Match package name. Supports * wildcards and repo/package form	name:phx* or name:hexpm/phoenix
description:	Full-text search of package descriptions	description:auth
depends:	Packages depending on a given package. Supports repo:package form	depends:ecto or depends:hexpm:ecto
build_tool:	Filter by build tool	build_tool:mix
updated_after:	Packages updated after an ISO8601 datetime	updated_after:2025-01-01T00:00:00Z
extra:	Match custom metadata (key,value). Nested keys are separated by commas	extra:license,MIT