Packages

floki

0.25.0
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
+136 additions
-20 deletions
  @@ -60,7 +60,7 @@ Add Floki to your `mix.exs`:
60 60 ```elixir
61 61 defp deps do
62 62 [
63 - {:floki, "~> 0.24.0"}
63 + {:floki, "~> 0.25.0"}
64 64 ]
65 65 end
66 66 ```
  @@ -113,7 +113,7 @@ After Rust is set up, you need to add `html5ever` NIF to your dependency list:
113 113 ```elixir
114 114 defp deps do
115 115 [
116 - {:floki, "~> 0.24.0"},
116 + {:floki, "~> 0.25.0"},
117 117 {:html5ever, "~> 0.7.0"}
118 118 ]
119 119 end
  @@ -145,7 +145,7 @@ First, add `fast_html` to your dependencies:
145 145 ```elixir
146 146 defp deps do
147 147 [
148 - {:floki, "~> 0.24.0"},
148 + {:floki, "~> 0.25.0"},
149 149 {:fast_html, "~> 1.0"}
150 150 ]
151 151 end
  @@ -158,7 +158,7 @@ Then you need to configure your app to use `fast_html`:
158 158 ```elixir
159 159 # in config/config.exs
160 160
161 - config :floki, :html_parser, Floki.HTMLParser.FastHTML
161 + config :floki, :html_parser, Floki.HTMLParser.FastHtml
162 162 ```
163 163
164 164 ## More about Floki API
  @@ -15,10 +15,11 @@
15 15 <<"lib/floki/selector/combinator.ex">>,<<"lib/floki/deep_text.ex">>,
16 16 <<"lib/floki/filter_out.ex">>,<<"lib/floki/flat_text.ex">>,
17 17 <<"lib/floki/finder.ex">>,<<"lib/floki/traversal.ex">>,
18 - <<"lib/floki/raw_html.ex">>,<<"lib/floki/html_tree">>,
19 - <<"lib/floki/html_tree/id_seeder.ex">>,<<"lib/floki/html_tree/comment.ex">>,
20 - <<"lib/floki/html_tree/text.ex">>,<<"lib/floki/html_tree/html_node.ex">>,
21 - <<"lib/floki/selector.ex">>,<<"lib/floki/html_tree.ex">>,<<"lib/floki.ex">>,
18 + <<"lib/floki/raw_html.ex">>,<<"lib/floki/parse_error.ex">>,
19 + <<"lib/floki/html_tree">>,<<"lib/floki/html_tree/id_seeder.ex">>,
20 + <<"lib/floki/html_tree/comment.ex">>,<<"lib/floki/html_tree/text.ex">>,
21 + <<"lib/floki/html_tree/html_node.ex">>,<<"lib/floki/selector.ex">>,
22 + <<"lib/floki/html_tree.ex">>,<<"lib/floki.ex">>,
22 23 <<"src/floki_selector_lexer.xrl">>,<<"src/floki_mochi_html.erl">>,
23 24 <<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,<<"CODE_OF_CONDUCT.md">>,
24 25 <<"CONTRIBUTING.md">>]}.
  @@ -31,4 +32,4 @@
31 32 {<<"optional">>,false},
32 33 {<<"repository">>,<<"hexpm">>},
33 34 {<<"requirement">>,<<"~> 0.5.0">>}]]}.
34 - {<<"version">>,<<"0.24.0">>}.
35 + {<<"version">>,<<"0.25.0">>}.
  @@ -104,6 +104,28 @@ defmodule Floki do
104 104
105 105 defdelegate parse_document(document), to: Floki.HTMLParser
106 106
107 + @doc """
108 + Parses a HTML Document from a string.
109 +
110 + Similar to `Floki.parse_document/1`, but raises `Floki.ParseError` if there was an
111 + error parsing the document.
112 +
113 + ## Example
114 +
115 + iex> Floki.parse_document!("<html><head></head><body>hello</body></html>")
116 + [{"html", [], [{"head", [], []}, {"body", [], ["hello"]}]}]
117 +
118 + """
119 +
120 + @spec parse_document!(binary()) :: html_tree()
121 +
122 + def parse_document!(document) do
123 + case parse_document(document) do
124 + {:ok, parsed_document} -> parsed_document
125 + {:error, message} -> raise Floki.ParseError, message: message
126 + end
127 + end
128 +
107 129 @doc """
108 130 Parses a HTML fragment from a string.
109 131
  @@ -113,7 +135,23 @@ defmodule Floki do
113 135
114 136 @spec parse_fragment(binary()) :: {:ok, html_tree()} | {:error, String.t()}
115 137
116 - defdelegate parse_fragment(document), to: Floki.HTMLParser
138 + defdelegate parse_fragment(fragment), to: Floki.HTMLParser
139 +
140 + @doc """
141 + Parses a HTML fragment from a string.
142 +
143 + Similar to `Floki.parse_fragment/1`, but raises `Floki.ParseError` if there was an
144 + error parsing the fragment.
145 + """
146 +
147 + @spec parse_fragment!(binary()) :: html_tree()
148 +
149 + def parse_fragment!(fragment) do
150 + case parse_fragment(fragment) do
151 + {:ok, parsed_fragment} -> parsed_fragment
152 + {:error, message} -> raise Floki.ParseError, message: message
153 + end
154 + end
117 155
118 156 @doc """
119 157 Converts HTML tree to raw HTML.
  @@ -285,21 +323,75 @@ defmodule Floki do
285 323 def map(html_tree, fun), do: Finder.map(html_tree, fun)
286 324
287 325 @doc """
288 - Traverses a HTML tree structure and returns a new tree structure that is the result of executing a function on all nodes. The function receives a tuple with {name, attributes, children}, and should either return a similar tuple or `nil` to delete the current node.
326 + Traverses and updates a HTML tree structure.
327 +
328 + This function returns a new tree structure that is the result of applying the
329 + given `fun` on all nodes.
330 +
331 + The function `fun` receives a tuple with `{name, attributes, children}`, and
332 + should either return a similar tuple or `nil` to delete the current node.
289 333
290 334 ## Examples
291 335
292 336 iex> html = {"div", [], ["hello"]}
293 - iex> Floki.traverse_and_update(html, fn {"div", attrs, children} -> {"p", attrs, children} end)
337 + iex> Floki.traverse_and_update(html, fn {"div", attrs, children} ->
338 + ...> {"p", attrs, children}
339 + ...> end)
294 340 {"p", [], ["hello"]}
295 341
296 342 iex> html = {"div", [], [{"span", [], ["hello"]}]}
297 - iex> Floki.traverse_and_update(html, fn {"span", _attrs, _children} -> nil; tag -> tag end)
343 + iex> Floki.traverse_and_update(html, fn
344 + ...> {"span", _attrs, _children} -> nil
345 + ...> tag -> tag
346 + ...> end)
298 347 {"div", [], []}
299 348 """
300 349
350 + @spec traverse_and_update(html_tree(), (html_tag() -> html_tag() | nil)) :: html_tree()
351 +
301 352 defdelegate traverse_and_update(html_tree, fun), to: Floki.Traversal
302 353
354 + @doc """
355 + Traverses and updates a HTML tree structure with an accumulator.
356 +
357 + This function returns a new tree structure and the final value of accumulator
358 + which are the result of applying the given `fun` on all nodes.
359 +
360 + The function `fun` receives a tuple with `{name, attributes, children}` and
361 + an accumulator, and should return a 2-tuple like `{new_node, new_acc}`, where
362 + `new_node` is either a similar tuple or `nil` to delete the current node, and
363 + `new_acc` is an updated value for the accumulator.
364 +
365 + ## Examples
366 +
367 + iex> html = [{"div", [], ["hello"]}, {"div", [], ["world"]}]
368 + iex> Floki.traverse_and_update(html, 0, fn {"div", attrs, children}, acc ->
369 + ...> {{"p", [{"data-count", to_string(acc)} | attrs], children}, acc + 1}
370 + ...> end)
371 + {[
372 + {"p", [{"data-count", "0"}], ["hello"]},
373 + {"p", [{"data-count", "1"}], ["world"]}
374 + ], 2}
375 +
376 + iex> html = {"div", [], [{"span", [], ["hello"]}]}
377 + iex> Floki.traverse_and_update(html, [deleted: 0], fn
378 + ...> {"span", _attrs, _children}, acc ->
379 + ...> {nil, Keyword.put(acc, :deleted, acc[:deleted] + 1)}
380 + ...> tag, acc ->
381 + ...> {tag, acc}
382 + ...> end)
383 + {{"div", [], []}, [deleted: 1]}
384 + """
385 +
386 + @type traverse_acc :: any()
387 + @spec traverse_and_update(
388 + html_tree(),
389 + traverse_acc(),
390 + (html_tag(), traverse_acc() -> {html_tag() | nil, traverse_acc()})
391 + ) :: html_tree()
392 +
393 + defdelegate traverse_and_update(html_tree, acc, fun), to: Floki.Traversal
394 +
303 395 @doc """
304 396 Returns the text nodes from a HTML tree.
305 397 By default, it will perform a deep search through the HTML tree.
  @@ -0,0 +1,3 @@
1 + defmodule Floki.ParseError do
2 + defexception [:message]
3 + end
  @@ -1,7 +1,12 @@
1 1 defmodule Floki.Traversal do
2 2 @moduledoc false
3 3
4 + def traverse_and_update(html_node, fun)
5 + def traverse_and_update([], _fun), do: []
4 6 def traverse_and_update(text, _fun) when is_binary(text), do: text
7 + def traverse_and_update(xml_tag = {:pi, _, _}, fun), do: fun.(xml_tag)
8 + def traverse_and_update({:comment, children}, fun), do: fun.({:comment, children})
9 + def traverse_and_update(doctype = {:doctype, _, _, _}, fun), do: fun.(doctype)
5 10
6 11 def traverse_and_update([head | tail], fun) do
7 12 case traverse_and_update(head, fun) do
  @@ -10,16 +15,31 @@ defmodule Floki.Traversal do
10 15 end
11 16 end
12 17
13 - def traverse_and_update([], _fun), do: []
14 -
15 - def traverse_and_update(xml_tag = {:pi, _, _}, fun), do: fun.(xml_tag)
16 -
17 18 def traverse_and_update({elem, attrs, children}, fun) do
18 19 mapped_children = traverse_and_update(children, fun)
19 20 fun.({elem, attrs, mapped_children})
20 21 end
21 22
22 - def traverse_and_update({:comment, children}, fun), do: fun.({:comment, children})
23 + def traverse_and_update(html_node, acc, fun)
24 + def traverse_and_update([], acc, _fun), do: {[], acc}
25 + def traverse_and_update(text, acc, _fun) when is_binary(text), do: {text, acc}
26 + def traverse_and_update(xml_tag = {:pi, _, _}, acc, fun), do: fun.(xml_tag, acc)
27 + def traverse_and_update({:comment, children}, acc, fun), do: fun.({:comment, children}, acc)
28 + def traverse_and_update(doctype = {:doctype, _, _, _}, acc, fun), do: fun.(doctype, acc)
23 29
24 - def traverse_and_update(doctype = {:doctype, _, _, _}, fun), do: fun.(doctype)
30 + def traverse_and_update([head | tail], acc, fun) do
31 + case traverse_and_update(head, acc, fun) do
32 + {nil, new_acc} ->
33 + traverse_and_update(tail, new_acc, fun)
34 +
35 + {mapped_head, new_acc} ->
36 + {mapped_tail, new_acc2} = traverse_and_update(tail, new_acc, fun)
37 + {[mapped_head | mapped_tail], new_acc2}
38 + end
39 + end
40 +
41 + def traverse_and_update({elem, attrs, children}, acc, fun) do
42 + {mapped_children, new_acc} = traverse_and_update(children, acc, fun)
43 + fun.({elem, attrs, mapped_children}, new_acc)
44 + end
25 45 end
Loading more files…