Aakash BakhleandGitHub
568aae875b
# Pull Request Template ## Description - Wires up Controllers to auto-sync job - adds plan based sync schedule - a scheduler that runs every hour to check syncable documents - guards the whole feature behind feature flag by reclaiming `twilio_content_templates` - Adds a global and account level cap on how many documents to enqueue to prevent sudden burst at first run - some refactor to simplify code - specs Fixes # (issue) ## Type of change - [x] New feature (non-breaking change which adds functionality) ## How Has This Been Tested? Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration. specs and locally ## Checklist: - [x] My code follows the style guidelines of this project - [x] I have performed a self-review of my code - [x] I have commented on my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [x] Any dependent changes have been merged and published in downstream modules
80 lines
1.6 KiB
Ruby
80 lines
1.6 KiB
Ruby
class Captain::Tools::SimplePageCrawlService
|
|
attr_reader :external_link, :status_code
|
|
|
|
def initialize(external_link)
|
|
@external_link = external_link
|
|
@parser = Captain::Tools::HtmlPageParser.new(fetch_body)
|
|
@doc = @parser.doc
|
|
end
|
|
|
|
def success?
|
|
status_code.to_i.between?(200, 299)
|
|
end
|
|
|
|
def page_links
|
|
sitemap? ? extract_links_from_sitemap : extract_links_from_html
|
|
end
|
|
|
|
def page_title
|
|
@parser.title
|
|
end
|
|
|
|
def body_markdown
|
|
@parser.body_markdown
|
|
end
|
|
|
|
def meta_description
|
|
meta_desc = @doc.at_css('meta[name="description"]')
|
|
return nil unless meta_desc && meta_desc['content']
|
|
|
|
meta_desc['content'].strip
|
|
end
|
|
|
|
def favicon_url
|
|
favicon_link = @doc.at_css('link[rel*="icon"]')
|
|
return nil unless favicon_link && favicon_link['href']
|
|
|
|
resolve_url(favicon_link['href'])
|
|
end
|
|
|
|
private
|
|
|
|
def fetch_body
|
|
body = ''
|
|
SafeFetch.fetch(external_link, validate_content_type: false) do |result|
|
|
body = result.tempfile.read
|
|
end
|
|
@status_code = 200
|
|
body
|
|
rescue SafeFetch::HttpError => e
|
|
@status_code = e.message.to_i
|
|
''
|
|
rescue SafeFetch::Error
|
|
@status_code = nil
|
|
''
|
|
end
|
|
|
|
def sitemap?
|
|
@external_link.end_with?('.xml')
|
|
end
|
|
|
|
def extract_links_from_sitemap
|
|
@doc.xpath('//loc').to_set(&:text)
|
|
end
|
|
|
|
def extract_links_from_html
|
|
@doc.xpath('//a/@href').to_set do |link|
|
|
absolute_url = URI.join(@external_link, link.value).to_s
|
|
absolute_url
|
|
end
|
|
end
|
|
|
|
def resolve_url(url)
|
|
return url if url.start_with?('http')
|
|
|
|
URI.join(@external_link, url).to_s
|
|
rescue StandardError
|
|
url
|
|
end
|
|
end
|