link-scrapers: reutilizar codigo sitemaps

link-scrapers/carrefour.ts

@@ -1,6 +1,6 @@
 import pMap from "p-map";
-import { decodeXML } from "entities";
 import { saveUrls } from "db-datos/urlHelpers.js";
+import { getUrlsFromSitemap } from "./common.js";
 
 export async function scrapCarrefourProducts() {
   await scrapBySitemap();
@@ -26,17 +26,7 @@ async function scrapBySitemap() {
     async (sitemapUrl) => {
       const res = await fetch(sitemapUrl);
       const xml = await res.text();
-      let urls = new Set<string>();
-      new HTMLRewriter()
-        .on("loc", {
-          text(element) {
-            const txt = element.text.trim();
-            if (!txt) return;
-            urls.add(decodeXML(txt));
-          },
-        })
-        .transform(new Response(xml));
-      saveUrls(Array.from(urls));
+      saveUrls(getUrlsFromSitemap(xml));
     },
     { concurrency: 3 }
   );

link-scrapers/common.ts

@@ -0,0 +1,14 @@
+import { decodeXML } from "entities";
+export function getUrlsFromSitemap(xml: string) {
+  let urls = new Set<string>();
+  new HTMLRewriter()
+    .on("loc", {
+      text(element) {
+        const txt = element.text.trim();
+        if (!txt) return;
+        urls.add(decodeXML(txt));
+      },
+    })
+    .transform(new Response(xml));
+  return Array.from(urls);
+}

link-scrapers/dia.ts

@@ -1,7 +1,7 @@
 import pMap from "p-map";
-import { decodeXML } from "entities";
 import { parseHTML } from "linkedom";
 import { saveUrls } from "db-datos/urlHelpers.js";
+import { getUrlsFromSitemap } from "./common.js";
 
 const categorias = [
   "https://diaonline.supermercadosdia.com.ar/almacen",
@@ -81,21 +81,15 @@ async function scrapBySitemap() {
     "https://diaonline.supermercadosdia.com.ar/sitemap/product-5.xml",
   ];
 
-  await pMap(sitemaps, async (sitemapUrl) => {
+  await pMap(
+    sitemaps,
+    async (sitemapUrl) => {
       const res = await fetch(sitemapUrl);
       const xml = await res.text();
-    let urls = new Set<string>();
-    new HTMLRewriter()
-      .on("loc", {
-        text(element) {
-          const txt = element.text.trim();
-          if (!txt) return;
-          urls.add(decodeXML(txt));
+      saveUrls(getUrlsFromSitemap(xml));
     },
-      })
-      .transform(new Response(xml));
-    saveUrls(Array.from(urls));
-  });
+    { concurrency: 3 }
+  );
 }
 
 async function scrapBySite() {

link-scrapers/package.json

@@ -11,6 +11,7 @@
   "author": "",
   "license": "ISC",
   "dependencies": {
+    "entities": "^4.5.0",
     "linkedom": "^0.16.5",
     "p-queue": "^8.0.1"
   }

scraper/package.json

@@ -17,7 +17,6 @@
     "date-fns": "^3.0.6",
     "db-datos": "workspace:^",
     "drizzle-orm": "=0.29.1",
-    "entities": "^4.5.0",
     "linkedom": "^0.16.5",
     "nanoid": "^5.0.4",
     "p-map": "^7.0.1",