o2o-infinith-demo/supabase/functions/scrape-website/index.ts

import "@supabase/functions-js/edge-runtime.d.ts";
import { createClient } from "https://esm.sh/@supabase/supabase-js@2";

const corsHeaders = {
  "Access-Control-Allow-Origin": "*",
  "Access-Control-Allow-Headers":
    "authorization, x-client-info, apikey, content-type",
};

interface ScrapeRequest {
  url: string;
  clinicName?: string;
}

Deno.serve(async (req) => {
  // Handle CORS preflight
  if (req.method === "OPTIONS") {
    return new Response("ok", { headers: corsHeaders });
  }

  try {
    const { url, clinicName } = (await req.json()) as ScrapeRequest;

    if (!url) {
      return new Response(
        JSON.stringify({ error: "URL is required" }),
        { status: 400, headers: { ...corsHeaders, "Content-Type": "application/json" } }
      );
    }

    const FIRECRAWL_API_KEY = Deno.env.get("FIRECRAWL_API_KEY");
    if (!FIRECRAWL_API_KEY) {
      throw new Error("FIRECRAWL_API_KEY not configured");
    }

    // Step 1: Scrape the main website
    const scrapeResponse = await fetch("https://api.firecrawl.dev/v1/scrape", {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${FIRECRAWL_API_KEY}`,
      },
      body: JSON.stringify({
        url,
        formats: ["json", "links"],
        jsonOptions: {
          prompt:
            "Extract clinic information: clinic name, address, phone number, services offered, doctors with specialties, social media links (instagram, youtube, blog, facebook), business hours, and any marketing-related content like slogans or key messages",
          schema: {
            type: "object",
            properties: {
              clinicName: { type: "string" },
              address: { type: "string" },
              phone: { type: "string" },
              businessHours: { type: "string" },
              slogan: { type: "string" },
              services: {
                type: "array",
                items: { type: "string" },
              },
              doctors: {
                type: "array",
                items: {
                  type: "object",
                  properties: {
                    name: { type: "string" },
                    title: { type: "string" },
                    specialty: { type: "string" },
                  },
                },
              },
              socialMedia: {
                type: "object",
                properties: {
                  instagram: { type: "string" },
                  youtube: { type: "string" },
                  blog: { type: "string" },
                  facebook: { type: "string" },
                },
              },
            },
          },
        },
        waitFor: 5000,
      }),
    });

    const scrapeData = await scrapeResponse.json();

    if (!scrapeData.success) {
      throw new Error(scrapeData.error || "Scraping failed");
    }

    // Step 2: Map the site to discover all pages
    const mapResponse = await fetch("https://api.firecrawl.dev/v1/map", {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${FIRECRAWL_API_KEY}`,
      },
      body: JSON.stringify({
        url,
        limit: 50,
      }),
    });

    const mapData = await mapResponse.json();

    // Step 3: Search for reviews and ratings
    const searchName = clinicName || scrapeData.data?.json?.clinicName || url;
    const searchResponse = await fetch("https://api.firecrawl.dev/v1/search", {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${FIRECRAWL_API_KEY}`,
      },
      body: JSON.stringify({
        query: `${searchName} 리뷰 평점 후기 강남언니 바비톡`,
        limit: 5,
      }),
    });

    const searchData = await searchResponse.json();

    // Combine all data
    const result = {
      clinic: scrapeData.data?.json || {},
      siteLinks: scrapeData.data?.links || [],
      siteMap: mapData.success ? mapData.links || [] : [],
      reviews: searchData.data || [],
      scrapedAt: new Date().toISOString(),
      sourceUrl: url,
    };

    // Save to Supabase if configured
    const supabaseUrl = Deno.env.get("SUPABASE_URL");
    const supabaseKey = Deno.env.get("SUPABASE_SERVICE_ROLE_KEY");

    if (supabaseUrl && supabaseKey) {
      const supabase = createClient(supabaseUrl, supabaseKey);
      await supabase.from("scrape_results").insert({
        url,
        clinic_name: result.clinic.clinicName || searchName,
        data: result,
      });
    }

    return new Response(JSON.stringify({ success: true, data: result }), {
      headers: { ...corsHeaders, "Content-Type": "application/json" },
    });
  } catch (error) {
    return new Response(
      JSON.stringify({ success: false, error: error.message }),
      {
        status: 500,
        headers: { ...corsHeaders, "Content-Type": "application/json" },
      }
    );
  }
});