7651c18b48
Adds `WebsiteBrandingService` (OSS) with an Enterprise override using
Firecrawl v2 to extract branding and business data from a URL for
onboarding auto-fill.
OSS version uses HTTParty + Nokogiri to extract:
- Business name (og:site_name or title)
- Language (html lang)
- Favicon
- Social links from `<a>` tags
Enterprise version makes a single Firecrawl call to fetch:
- Structured JSON (name, language, industry via LLM)
- Branding (favicon, primary color)
- Page links
Falls back to OSS if Firecrawl is unavailable or fails.
Social handles (WhatsApp, Facebook, Instagram, Telegram, TikTok, LINE)
are parsed deterministically via a shared `SocialLinkParser`.
> We use links for socials, since the LLM extraction was unreliable,
mostly returned empty, and hallucinated in some rare scenarios
## How to test
```ruby
# OSS (no Firecrawl key needed)
WebsiteBrandingService.new('chatwoot.com').perform
# Enterprise (requires CAPTAIN_FIRECRAWL_API_KEY)
WebsiteBrandingService.new('notion.so').perform
WebsiteBrandingService.new('postman.com').perform
```
Verify the returned hash includes business_name, language,
industry_category, social_handles, and branding with
favicon/primary_color.
<img width="908" height="393" alt="image"
src="https://github.com/user-attachments/assets/e3696887-d366-485a-89a0-8e1a9698a788"
/>
94 lines
2.2 KiB
Ruby
94 lines
2.2 KiB
Ruby
class WebsiteBrandingService
|
|
include SocialLinkParser
|
|
|
|
def initialize(url)
|
|
@url = normalize_url(url)
|
|
end
|
|
|
|
def perform
|
|
doc = fetch_page
|
|
return nil if doc.nil?
|
|
|
|
links = extract_links(doc)
|
|
|
|
{
|
|
business_name: extract_business_name(doc),
|
|
language: extract_language(doc),
|
|
industry_category: nil,
|
|
social_handles: extract_social_from_links(links),
|
|
branding: extract_branding(doc)
|
|
}
|
|
rescue StandardError => e
|
|
Rails.logger.error "[WebsiteBranding] #{e.message}"
|
|
nil
|
|
end
|
|
|
|
private
|
|
|
|
def normalize_url(url)
|
|
url.match?(%r{\Ahttps?://}) ? url : "https://#{url}"
|
|
end
|
|
|
|
def fetch_page
|
|
response = HTTParty.get(@url, follow_redirects: true, timeout: 15)
|
|
return nil unless response.success?
|
|
|
|
Nokogiri::HTML(response.body)
|
|
rescue StandardError => e
|
|
Rails.logger.error "[WebsiteBranding] Failed to fetch #{@url}: #{e.message}"
|
|
nil
|
|
end
|
|
|
|
def extract_business_name(doc)
|
|
og_site_name = doc.at_css('meta[property="og:site_name"]')&.[]('content')
|
|
return og_site_name.strip if og_site_name.present?
|
|
|
|
title = doc.at_xpath('//title')&.text
|
|
title&.strip&.split(/\s*[|\-–—·:]+\s*/)&.first
|
|
end
|
|
|
|
def extract_language(doc)
|
|
doc.at_css('html')&.[]('lang')&.split('-')&.first&.downcase
|
|
end
|
|
|
|
def extract_links(doc)
|
|
doc.css('a[href]').filter_map do |a|
|
|
href = a['href']&.strip
|
|
next if href.blank? || href.start_with?('#', 'javascript:', 'mailto:', 'tel:')
|
|
|
|
href.start_with?('http') ? href : URI.join(@url, href).to_s
|
|
rescue URI::InvalidURIError
|
|
nil
|
|
end.uniq
|
|
end
|
|
|
|
def extract_branding(doc)
|
|
{
|
|
favicon: extract_favicon(doc),
|
|
primary_color: extract_theme_color(doc)
|
|
}
|
|
end
|
|
|
|
def extract_favicon(doc)
|
|
favicon = doc.at_css('link[rel*="icon"]')&.[]('href')
|
|
return nil if favicon.blank?
|
|
|
|
resolve_url(favicon)
|
|
end
|
|
|
|
def extract_theme_color(doc)
|
|
doc.at_css('meta[name="theme-color"]')&.[]('content')
|
|
end
|
|
|
|
def resolve_url(url)
|
|
return nil if url.blank?
|
|
return url if url.start_with?('http')
|
|
|
|
URI.join(@url, url).to_s
|
|
rescue URI::InvalidURIError
|
|
nil
|
|
end
|
|
end
|
|
|
|
WebsiteBrandingService.prepend_mod_with('WebsiteBrandingService')
|