Module: Nous
- Defined in:
- lib/nous.rb,
lib/nous/cli.rb,
lib/nous/command.rb,
lib/nous/crawler.rb,
lib/nous/fetcher.rb,
lib/nous/version.rb,
lib/nous/converter.rb,
lib/nous/serializer.rb,
lib/nous/url_resolver.rb,
lib/nous/extractor/jina.rb,
lib/nous/primitives/url.rb,
lib/nous/primitives/page.rb,
lib/nous/extractor/default.rb,
lib/nous/crawler/url_filter.rb,
lib/nous/configuration_builder.rb,
lib/nous/extractor/jina/client.rb,
lib/nous/crawler/link_extractor.rb,
lib/nous/fetcher/page_extractor.rb,
lib/nous/primitives/fetch_record.rb,
lib/nous/primitives/fetch_result.rb,
lib/nous/extractor/default/client.rb,
lib/nous/primitives/configuration.rb,
lib/nous/crawler/redirect_follower.rb,
lib/nous/fetcher/extraction_runner.rb,
lib/nous/crawler/async_page_fetcher.rb,
lib/nous/crawler/single_page_fetcher.rb,
lib/nous/primitives/extracted_content.rb,
lib/nous/crawler/recursive_page_fetcher.rb,
sig/nous.rbs
Defined Under Namespace
Modules: Extractor
Classes: Cli, Command, Configuration, ConfigurationBuilder, Converter, Crawler, ExtractedContent, FetchRecord, FetchResult, Fetcher, Page, Serializer, Url, UrlResolver
Constant Summary
collapse
- VERSION =
"0.4.0"
Class Attribute Summary collapse
Class Method Summary
collapse
Class Attribute Details
.configuration ⇒ Object
Returns the value of attribute configuration.
11
12
13
|
# File 'lib/nous.rb', line 11
def configuration
@configuration
end
|
Class Method Details
.fetch(seed_url, extractor: Extractor::Default.new, http_client: nil, details: false, **options) ⇒ Object
21
22
23
24
25
26
27
28
|
# File 'lib/nous.rb', line 21
def fetch(seed_url, extractor: Extractor::Default.new, http_client: nil, details: false, **options)
configure(**options)
result = Fetcher.call(seed_url:, extractor:, http_client:, details:)
raise result.error if result.failure?
result.payload
end
|
.reset_configuration! ⇒ Object
17
18
19
|
# File 'lib/nous.rb', line 17
def reset_configuration!
@configuration = nil
end
|
.serialize(pages, format: :text) ⇒ Object
30
31
32
33
34
35
|
# File 'lib/nous.rb', line 30
def serialize(pages, format: :text)
result = Serializer.call(pages:, format:)
raise result.error if result.failure?
result.payload
end
|