vodorod/parcer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #228 from getmaxun/list-url

Browse Source 
fix: use `window.location.origin` as baseUrl for scrapeList
This commit is contained in:
Karishma Shukla
2024-12-09 21:14:43 +05:30
committed by GitHub
parent 236f3edcd4 429ddaa571
commit 7cd621bfae
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
maxun-core/src/browserSide/scraper.js
View File

@@ -283,13 +283,13 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
} else if (attribute === 'innerHTML') {
record[label] = fieldElement.innerHTML.trim();
} else if (attribute === 'src') {
// Handle relative 'src' URLs
const src = fieldElement.getAttribute('src');
record[label] = src ? new URL(src, baseUrl).href : null;
// Handle relative 'src' URLs
const src = fieldElement.getAttribute('src');
record[label] = src ? new URL(src, window.location.origin).href : null;
} else if (attribute === 'href') {
// Handle relative 'href' URLs
const href = fieldElement.getAttribute('href');
record[label] = href ? new URL(href, baseUrl).href : null;
record[label] = href ? new URL(href, window.location.origin).href : null;
} else {
record[label] = fieldElement.getAttribute(attribute);
}
@@ -346,5 +346,5 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
return results;
};
})(window);