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

feat: handle relative href urls in scrape list

Browse Source
This commit is contained in:
amhsirak
2024-11-23 07:05:55 +05:30
parent fc2e3dc1c1
commit 94aa8bcf42
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
maxun-core/src/browserSide/scraper.js
View File

@@ -284,7 +284,9 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
} else if (attribute === 'src') { } else if (attribute === 'src') {
record[label] = fieldElement.src; record[label] = fieldElement.src;
} else if (attribute === 'href') { } 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 { } else {
record[label] = fieldElement.getAttribute(attribute); record[label] = fieldElement.getAttribute(attribute);
} }