Archives/Athou_commafeed
1
0
Fork 1
mirror of https://github.com/Athou/commafeed.git synced 2026-03-21 21:37:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

extract url from html if possible

Browse Source
This commit is contained in:
Athou
2013-03-31 09:53:19 +02:00
parent 5b36df1ab3
commit b4ebfa4b74
2 changed files with 24 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/main/java/com/commafeed/backend/feeds/FeedFetcher.java
View File

@@ -11,6 +11,9 @@ import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.HttpConnectionParams;
import org.apache.http.params.HttpProtocolParams;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -40,7 +43,13 @@ public class FeedFetcher {
HttpResponse response = httpclient.execute(httpget);
HttpEntity entity = response.getEntity();
String content = EntityUtils.toString(entity, "UTF-8");
feed = parser.parse(feedUrl, content);
String extractedUrl = extractFeedUrl(content);
if (extractedUrl != null) {
feed = fetch(extractedUrl);
} else {
feed = parser.parse(feedUrl, content);
}
} catch (Exception e) {
throw new FeedException(e.getMessage(), e);
} finally {
@@ -49,4 +58,18 @@ public class FeedFetcher {
return feed;
}
private String extractFeedUrl(String html) {
Document doc = Jsoup.parse(html);
Elements rss = doc.select("link[type=application/rss+xml]");
Elements atom = doc.select("link[type=application/atom+xml]");
if (rss.size() > 0) {
return rss.get(0).attr("abs:href").toString();
} else if (atom.size() > 0) {
return atom.get(0).attr("abs:href").toString();
} else {
return null;
}
}
}