dnet-hadoop/dhp-workflows/dhp-bmuse/src/test/java/eu/dnetlib/dhp/bmuse/bioschema/SitemapTest.java

25 lines
563 B
Java

package eu.dnetlib.dhp.bmuse.bioschema;
import org.jsoup.select.Elements;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.bmuse.utils.UrlParser;
public class SitemapTest {
static Logger logger = LoggerFactory.getLogger(SitemapTest.class);
@Test
@Disabled
void sitemapGzTest() throws Exception {
Elements urls = UrlParser.getSitemapList("https://disprot.org/sitemap2.xml.gz", "loc");
urls.forEach(url -> {
logger.info(url.text());
});
}
}