Merge pull request #202 from getmaxun/develop

feat: feat: handle relative src & href paths in scrapeList & scrapeSchema (missing in v0.0.2)

docker-compose.yml

@@ -43,7 +43,7 @@ services:
     #build:
       #context: .
       #dockerfile: server/Dockerfile
-    image: getmaxun/maxun-backend:v0.0.1
+    image: getmaxun/maxun-backend:v0.0.2
     ports:
       - "8080:8080"
     env_file: .env

maxun-core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "maxun-core",
-  "version": "0.0.3",
+  "version": "0.0.4",
   "description": "Core package for Maxun, responsible for data extraction",
   "main": "build/index.js",
   "typings": "build/index.d.ts",
@@ -20,7 +20,12 @@
     "automation",
     "workflow",
     "data extraction",
-    "scraping"
+    "scraping",
+    "web scraper",
+    "web scraping",
+    "data scraping",
+    "no-code web scraper",
+    "no-code web scraping"
   ],
   "author": "Maxun",
   "license": "AGPL-3.0-or-later",

maxun-core/src/browserSide/scraper.js

@@ -235,9 +235,11 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
 
         switch (attribute) {
           case 'href':
-            return elem.getAttribute('href');
+            const relativeHref = elem.getAttribute('href');
+            return relativeHref ? new URL(relativeHref, window.location.origin).href : null;
           case 'src':
-            return elem.getAttribute('src');
+            const relativeSrc = elem.getAttribute('src');
+            return relativeSrc ? new URL(relativeSrc, window.location.origin).href : null;
           case 'innerText':
             return elem.innerText;
           case 'textContent':
@@ -281,9 +283,13 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
             } else if (attribute === 'innerHTML') {
               record[label] = fieldElement.innerHTML.trim();
             } else if (attribute === 'src') {
-              record[label] = fieldElement.src;
+               // Handle relative 'src' URLs
+               const src = fieldElement.getAttribute('src');
+               record[label] = src ? new URL(src, baseUrl).href : null;
             } else if (attribute === 'href') {
-              record[label] = fieldElement.href;
+              // Handle relative 'href' URLs
+              const href = fieldElement.getAttribute('href');
+              record[label] = href ? new URL(href, baseUrl).href : null;
             } else {
               record[label] = fieldElement.getAttribute(attribute);
             }

package.json

@@ -42,7 +42,7 @@
     "jwt-decode": "^4.0.0",
     "loglevel": "^1.8.0",
     "loglevel-plugin-remote": "^0.6.8",
-    "maxun-core": "^0.0.3",
+    "maxun-core": "0.0.4",
     "minio": "^8.0.1",
     "moment-timezone": "^0.5.45",
     "node-cron": "^3.0.3",
@@ -110,4 +110,4 @@
     "ts-node": "^10.4.0",
     "vite": "^5.4.10"
   }
-}
+}

server/src/workflow-management/utils.ts

@@ -17,7 +17,7 @@ export const getBestSelectorForAction = (action: Action) => {
         selectors?.text?.length != null &&
           selectors?.text?.length < 25 &&
           action.hasOnlyText
-          ? `text=${selectors.text}`
+          ? selectors.generalSelector
           : null;
 
       if (action.tagName === TagName.Input) {