Files
leadchat/app/services/website_branding_service.rb
Shivam Mishra e5107604a0 feat: account enrichment using context.dev [UPM-27] (#13978)
## Account branding enrichment during signup

This PR does the following

### Replace Firecrawl with Context.dev

Switches the enterprise brand lookup from Firecrawl to Context.dev for
better data quality, built-in caching, and automatic filtering of
free/disposable email providers. The service interface changes from URL
to email input to match Context.dev's email endpoint. OSS still falls
back to basic HTML scraping with a normalized output shape across both
paths.

The enterprise path intentionally does not fall back to HTML scraping on
failure — speed matters more than completeness. We want the user on the
editable onboarding form fast, and a slow fallback scrape is worse than
letting them fill it in.

Requires `CONTEXT_DEV_API_KEY` in Super Admin → App Config. Without it,
falls back to OSS HTML scraping.

### Add job to enrich account details

After account creation, `Account::BrandingEnrichmentJob` looks up the
signup email and pre-fills the account name, colors, logos, social
links, and industry into `custom_attributes['brand_info']`.

The job signals completion via a short-lived Redis key (30s TTL) + an
ActionCable broadcast (`account.enrichment_completed`). The Redis key
lets the frontend distinguish "still running" from "finished with no
results."
2026-04-08 11:16:52 +05:30

110 lines
3.0 KiB
Ruby

class WebsiteBrandingService
include SocialLinkParser
attr_reader :http_status
DATA_DEFAULTS = { description: nil, slogan: nil, phone: nil, address: nil, links: nil, stock: nil, industries: [], is_nsfw: false }.freeze
def initialize(email)
@email = email
@domain = email.split('@').last&.downcase&.strip
@url = "https://#{@domain}"
@http_status = nil
end
def perform
doc = fetch_page
return nil if doc.nil?
links = extract_links(doc)
DATA_DEFAULTS.merge({
domain: @domain,
title: extract_title(doc),
colors: extract_colors(doc),
logos: extract_logos(doc),
socials: build_socials(links),
email: @email
})
rescue StandardError => e
Rails.logger.error "[WebsiteBranding] #{e.message}"
nil
end
private
def fetch_page
response = HTTParty.get(@url, follow_redirects: true, timeout: 15)
@http_status = response.code
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_title(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_colors(doc)
color = doc.at_css('meta[name="theme-color"]')&.[]('content')
return [] if color.blank?
[{ hex: color, name: nil }]
end
def extract_logos(doc)
favicon = doc.at_css('link[rel*="icon"]')&.[]('href')
return [] if favicon.blank?
url = resolve_url(favicon)
return [] if url.blank?
[{ url: url, type: nil, mode: nil, colors: [], resolution: { aspect_ratio: 1 } }]
end
def build_socials(links)
handles = extract_social_from_links(links)
handles.filter_map do |platform, handle|
next if handle.blank?
url = reconstruct_social_url(platform, handle)
{ type: platform.to_s, url: url }
end
end
def reconstruct_social_url(platform, handle)
base_urls = { whatsapp: 'https://wa.me/', line: 'https://line.me/', facebook: 'https://facebook.com/',
instagram: 'https://instagram.com/', telegram: 'https://t.me/', tiktok: 'https://tiktok.com/' }
"#{base_urls[platform]}#{handle}"
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 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')