nokodown 0.1.0

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.
Files changed (33) hide show
  1. checksums.yaml +7 -0
  2. data/CHANGELOG.md +12 -0
  3. data/LICENSE +202 -0
  4. data/NOTICE +10 -0
  5. data/README.md +246 -0
  6. data/lib/nokodown/boilerplate.rb +236 -0
  7. data/lib/nokodown/charset.rb +27 -0
  8. data/lib/nokodown/container_check.rb +174 -0
  9. data/lib/nokodown/content_locator.rb +118 -0
  10. data/lib/nokodown/dom.rb +140 -0
  11. data/lib/nokodown/extractor.rb +137 -0
  12. data/lib/nokodown/markdown/cleanup.rb +111 -0
  13. data/lib/nokodown/markdown/code_block.rb +71 -0
  14. data/lib/nokodown/markdown/image.rb +63 -0
  15. data/lib/nokodown/markdown/image_cleanup.rb +166 -0
  16. data/lib/nokodown/markdown/inline.rb +340 -0
  17. data/lib/nokodown/markdown/redundant_images.rb +142 -0
  18. data/lib/nokodown/markdown/renderer.rb +339 -0
  19. data/lib/nokodown/markdown/table.rb +93 -0
  20. data/lib/nokodown/markdown/text.rb +79 -0
  21. data/lib/nokodown/metadata.rb +316 -0
  22. data/lib/nokodown/patterns.rb +152 -0
  23. data/lib/nokodown/preprocessor.rb +226 -0
  24. data/lib/nokodown/product_reviews.rb +90 -0
  25. data/lib/nokodown/pruner.rb +337 -0
  26. data/lib/nokodown/result.rb +8 -0
  27. data/lib/nokodown/scorer.rb +230 -0
  28. data/lib/nokodown/stats.rb +79 -0
  29. data/lib/nokodown/tables.rb +62 -0
  30. data/lib/nokodown/url_resolver.rb +249 -0
  31. data/lib/nokodown/version.rb +5 -0
  32. data/lib/nokodown.rb +54 -0
  33. metadata +93 -0
metadata ADDED
@@ -0,0 +1,93 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: nokodown
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - SerpApi
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2026-11-02 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: nokolexbor
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '0.6'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '0.6'
27
+ description: Extracts the main content of articles, listings, product pages, docs
28
+ and every other kind of web page as Markdown, with Readability-style metadata. Built
29
+ on Nokolexbor.
30
+ email:
31
+ executables: []
32
+ extensions: []
33
+ extra_rdoc_files: []
34
+ files:
35
+ - CHANGELOG.md
36
+ - LICENSE
37
+ - NOTICE
38
+ - README.md
39
+ - lib/nokodown.rb
40
+ - lib/nokodown/boilerplate.rb
41
+ - lib/nokodown/charset.rb
42
+ - lib/nokodown/container_check.rb
43
+ - lib/nokodown/content_locator.rb
44
+ - lib/nokodown/dom.rb
45
+ - lib/nokodown/extractor.rb
46
+ - lib/nokodown/markdown/cleanup.rb
47
+ - lib/nokodown/markdown/code_block.rb
48
+ - lib/nokodown/markdown/image.rb
49
+ - lib/nokodown/markdown/image_cleanup.rb
50
+ - lib/nokodown/markdown/inline.rb
51
+ - lib/nokodown/markdown/redundant_images.rb
52
+ - lib/nokodown/markdown/renderer.rb
53
+ - lib/nokodown/markdown/table.rb
54
+ - lib/nokodown/markdown/text.rb
55
+ - lib/nokodown/metadata.rb
56
+ - lib/nokodown/patterns.rb
57
+ - lib/nokodown/preprocessor.rb
58
+ - lib/nokodown/product_reviews.rb
59
+ - lib/nokodown/pruner.rb
60
+ - lib/nokodown/result.rb
61
+ - lib/nokodown/scorer.rb
62
+ - lib/nokodown/stats.rb
63
+ - lib/nokodown/tables.rb
64
+ - lib/nokodown/url_resolver.rb
65
+ - lib/nokodown/version.rb
66
+ homepage: https://github.com/serpapi/nokodown
67
+ licenses:
68
+ - Apache-2.0
69
+ metadata:
70
+ homepage_uri: https://github.com/serpapi/nokodown
71
+ source_code_uri: https://github.com/serpapi/nokodown
72
+ changelog_uri: https://github.com/serpapi/nokodown/blob/main/CHANGELOG.md
73
+ bug_tracker_uri: https://github.com/serpapi/nokodown/issues
74
+ post_install_message:
75
+ rdoc_options: []
76
+ require_paths:
77
+ - lib
78
+ required_ruby_version: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '2.7'
83
+ required_rubygems_version: !ruby/object:Gem::Requirement
84
+ requirements:
85
+ - - ">="
86
+ - !ruby/object:Gem::Version
87
+ version: '0'
88
+ requirements: []
89
+ rubygems_version: 3.1.6
90
+ signing_key:
91
+ specification_version: 4
92
+ summary: Clean, low-noise Markdown from any web page
93
+ test_files: []