readability-rb 0.3.1 → 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +2 -0
- data/lib/readability/metadata.rb +5 -3
- data/lib/readability/version.rb +1 -1
- data/lib/readability.rb +7 -4
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: d1b1f82a83ce6cdeb11e08496ffdac052e828ae70938e9febf1f054cf0fffff1
|
|
4
|
+
data.tar.gz: 26b68d2cf32967ea3e0aaa486eb591639001831b461f2ad0b86015d26b9c41f7
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ccabf0a76b0f48e7047e97303e13314801159fa368329729ab34079f7f679ab92e86fe3a055a0251c3b4c13dd9028d447c3f560d4762e58b770f7853966f96f3
|
|
7
|
+
data.tar.gz: 7ac4044347dc3f4efc7e24ce182a0b3cfd53504ebf9429a8ca6950f4a140663a3a5f84e19578692d0fc8ba1299bf730d9b1c127b14cc2d0b6bb266d1d5d39cf2
|
data/README.md
CHANGED
|
@@ -92,6 +92,8 @@ result = Readability.parse(html, serializer: ->(el) { el.to_html })
|
|
|
92
92
|
| `allowed_video_regex` | Regex for allowed video embed URLs | built-in |
|
|
93
93
|
| `link_density_modifier` | Adjust link density calculation | `0` |
|
|
94
94
|
| `serializer` | Lambda to serialize the content element | `inner_html` |
|
|
95
|
+
| `max_attributes` | Max attributes per element at parse time | `1000` |
|
|
96
|
+
| `max_tree_depth` | Max document tree depth at parse time (`-1` to disable) | `1000` |
|
|
95
97
|
|
|
96
98
|
## Contributing
|
|
97
99
|
|
data/lib/readability/metadata.rb
CHANGED
|
@@ -41,7 +41,7 @@ module Readability
|
|
|
41
41
|
|
|
42
42
|
if parsed.is_a?(Array)
|
|
43
43
|
parsed = parsed.find do |it|
|
|
44
|
-
it["@type"]
|
|
44
|
+
Array(it["@type"]).any? { |t| t.match?(JSON_LD_ARTICLE_TYPES) }
|
|
45
45
|
end
|
|
46
46
|
next unless parsed
|
|
47
47
|
end
|
|
@@ -58,11 +58,13 @@ module Readability
|
|
|
58
58
|
|
|
59
59
|
if !parsed["@type"] && parsed["@graph"].is_a?(Array)
|
|
60
60
|
parsed = parsed["@graph"].find do |it|
|
|
61
|
-
|
|
61
|
+
next unless it.is_a?(Hash)
|
|
62
|
+
|
|
63
|
+
Array(it["@type"]).any? { |t| t.is_a?(String) && t.match?(JSON_LD_ARTICLE_TYPES) }
|
|
62
64
|
end
|
|
63
65
|
end
|
|
64
66
|
|
|
65
|
-
next if !parsed || !parsed["@type"] || !parsed["@type"].match?(JSON_LD_ARTICLE_TYPES)
|
|
67
|
+
next if !parsed || !parsed["@type"] || !Array(parsed["@type"]).any? { |t| t.is_a?(String) && t.match?(JSON_LD_ARTICLE_TYPES) }
|
|
66
68
|
|
|
67
69
|
metadata = {}
|
|
68
70
|
|
data/lib/readability/version.rb
CHANGED
data/lib/readability.rb
CHANGED
|
@@ -15,13 +15,16 @@ require_relative "readability/document"
|
|
|
15
15
|
require_relative "readability/readerable"
|
|
16
16
|
|
|
17
17
|
module Readability
|
|
18
|
-
|
|
19
|
-
|
|
18
|
+
DEFAULT_MAX_ATTRIBUTES = 1000
|
|
19
|
+
DEFAULT_MAX_TREE_DEPTH = 1000
|
|
20
|
+
|
|
21
|
+
def self.parse(html, url: nil, max_attributes: DEFAULT_MAX_ATTRIBUTES, max_tree_depth: DEFAULT_MAX_TREE_DEPTH, **options)
|
|
22
|
+
doc = Nokogiri::HTML5(html, max_attributes: max_attributes, max_tree_depth: max_tree_depth)
|
|
20
23
|
Document.new(doc, url: url, **options).parse
|
|
21
24
|
end
|
|
22
25
|
|
|
23
|
-
def self.readerable?(html, **options)
|
|
24
|
-
doc = Nokogiri::HTML5(html)
|
|
26
|
+
def self.readerable?(html, max_attributes: DEFAULT_MAX_ATTRIBUTES, max_tree_depth: DEFAULT_MAX_TREE_DEPTH, **options)
|
|
27
|
+
doc = Nokogiri::HTML5(html, max_attributes: max_attributes, max_tree_depth: max_tree_depth)
|
|
25
28
|
Readerable.probably_readerable?(doc, **options)
|
|
26
29
|
end
|
|
27
30
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: readability-rb
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.5.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Andy Croll
|
|
@@ -49,7 +49,7 @@ licenses:
|
|
|
49
49
|
metadata:
|
|
50
50
|
homepage_uri: https://github.com/andycroll/readability-rb
|
|
51
51
|
source_code_uri: https://github.com/andycroll/readability-rb
|
|
52
|
-
changelog_uri: https://github.com/andycroll/readability-rb/
|
|
52
|
+
changelog_uri: https://github.com/andycroll/readability-rb/blob/main/CHANGELOG.md
|
|
53
53
|
bug_tracker_uri: https://github.com/andycroll/readability-rb/issues
|
|
54
54
|
rdoc_options: []
|
|
55
55
|
require_paths:
|