Skip to content

#2057 FetcherBolt: extract the sitemap autodiscovery #2204

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rzo1 merged 1 commit into from
Oct 2, 2026
Merged

#2057 FetcherBolt: extract the sitemap autodiscovery #2204

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 41 additions & 43 deletions core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,50 +214,8 @@ public void run() {
RobotRulesLookup.Result robots =
robotsLookup.lookup(protocol, fit.url, metadata);
BaseRobotRules rules = robots.rules();
boolean fromCache = robots.fromCache();

// autodiscovery of sitemaps
// the sitemaps will be sent down the topology
// if the robot file did not come from the cache
// to avoid sending them unnecessarily

// check in the metadata if discovery setting has been
// overridden

String localSitemapDiscoveryVal =
metadata.getFirstValue(SITEMAP_DISCOVERY_PARAM_KEY);

boolean smautodisco;

if ("true".equalsIgnoreCase(localSitemapDiscoveryVal)) {
smautodisco = true;
} else if ("false".equalsIgnoreCase(localSitemapDiscoveryVal)) {
smautodisco = false;
} else {
smautodisco = sitemapsAutoDiscovery;
}

if (!fromCache && smautodisco) {
for (String sitemapUrl : rules.getSitemaps()) {
if (rules.isAllowed(sitemapUrl)) {
emitOutlink(
fit.tuple,
url,
sitemapUrl,
metadata,
SiteMapParserBolt.isSitemapKey,
"true");
}
}
}

// has found sitemaps
// https://github.com/apache/stormcrawler/issues/710
// note: we don't care if the sitemap URLs where actually
// kept
boolean foundSitemap = (rules.getSitemaps().size() > 0);
metadata.setValue(
SiteMapParserBolt.foundSitemapKey, Boolean.toString(foundSitemap));
discoverSitemaps(fit.tuple, url, metadata, robots);

if (!rules.isAllowed(fit.url)) {
LOG.info("Denied by robots.txt: {}", fit.url);
Expand Down Expand Up @@ -544,6 +502,46 @@ public void run() {
}
}

/**
* Sends the sitemaps of robots.txt which its rules allow as outlinks, when sitemap discovery is
* on for the URL (its metadata overrides the configuration) and the rules did not come from the
* cache. Sets foundSitemap in the metadata to whether robots.txt declares any sitemap, sent or
* not (#710).
*/
private void discoverSitemaps(
Tuple tuple, URL url, Metadata metadata, RobotRulesLookup.Result robots) {
BaseRobotRules rules = robots.rules();

String localSitemapDiscoveryVal = metadata.getFirstValue(SITEMAP_DISCOVERY_PARAM_KEY);

boolean smautodisco;

if ("true".equalsIgnoreCase(localSitemapDiscoveryVal)) {
smautodisco = true;
} else if ("false".equalsIgnoreCase(localSitemapDiscoveryVal)) {
smautodisco = false;
} else {
smautodisco = sitemapsAutoDiscovery;
}

if (!robots.fromCache() && smautodisco) {
for (String sitemapUrl : rules.getSitemaps()) {
if (rules.isAllowed(sitemapUrl)) {
emitOutlink(
tuple,
url,
sitemapUrl,
metadata,
SiteMapParserBolt.isSitemapKey,
"true");
}
}
}

boolean foundSitemap = (rules.getSitemaps().size() > 0);
metadata.setValue(SiteMapParserBolt.foundSitemapKey, Boolean.toString(foundSitemap));
}

private void checkConfiguration(Config stormConf) {

// ensure that a value has been set for the agent name and that that
Expand Down
Loading