diff --git a/htroot/Network.html b/htroot/Network.html index 5f88e5f75..07b21ce76 100644 --- a/htroot/Network.html +++ b/htroot/Network.html @@ -215,7 +215,7 @@   lightred font : - passiv peers ( < 5 hour passiv time) + passiv peers ( < 5 hour passive time)   diff --git a/htroot/WatchCrawler_p.java b/htroot/WatchCrawler_p.java index 86dcfe6e4..99a312b89 100644 --- a/htroot/WatchCrawler_p.java +++ b/htroot/WatchCrawler_p.java @@ -271,11 +271,14 @@ public class WatchCrawler_p { yacyURL crawlURL = new yacyURL("file://" + file.toString(), null); plasmaCrawlProfile.entry profile = switchboard.profilesActiveCrawls.newEntry(fileName, crawlURL, newcrawlingfilter, newcrawlingfilter, newcrawlingdepth, newcrawlingdepth, crawlingIfOlder, crawlingDomFilterDepth, crawlingDomMaxPages, crawlingQ, indexText, indexMedia, storeHTCache, true, crawlOrder, xsstopw, xdstopw, xpstopw); + // pause local crawl here + switchboard.pauseCrawlJob(plasmaSwitchboard.CRAWLJOB_LOCAL_CRAWL); + // loop through the contained links - Iterator interator = hyperlinks.entrySet().iterator(); + Iterator linkiterator = hyperlinks.entrySet().iterator(); int c = 0; - while (interator.hasNext()) { - Map.Entry e = (Map.Entry) interator.next(); + while (linkiterator.hasNext()) { + Map.Entry e = (Map.Entry) linkiterator.next(); String nexturlstring = (String) e.getKey(); if (nexturlstring == null) continue; @@ -296,7 +299,7 @@ public class WatchCrawler_p { } // enqueuing the url for crawling - String rejectReason = switchboard.sbStackCrawlThread.stackCrawl(nexturlstring, null, yacyCore.seedDB.mySeed().hash, (String)e.getValue(), new Date(), 1, profile); + String rejectReason = switchboard.sbStackCrawlThread.stackCrawl(nexturlstring, null, yacyCore.seedDB.mySeed().hash, (String)e.getValue(), new Date(), 0, profile); // if something failed add the url into the errorURL list if (rejectReason == null) { @@ -320,7 +323,8 @@ public class WatchCrawler_p { prop.put("info_error", e.getMessage()); e.printStackTrace(); } - } + switchboard.continueCrawlJob(plasmaSwitchboard.CRAWLJOB_LOCAL_CRAWL); + } } else if (crawlingMode.equals(CRAWLING_MODE_SITEMAP)) { String sitemapURLStr = null; try { diff --git a/htroot/proxymsg/error.html b/htroot/proxymsg/error.html index 1520e6875..5076c8f41 100644 --- a/htroot/proxymsg/error.html +++ b/htroot/proxymsg/error.html @@ -1,7 +1,7 @@ - YaCy: Proxy Message + YaCy: Error Message #%env/templates/metas.template%# diff --git a/source/de/anomic/plasma/plasmaCrawlStacker.java b/source/de/anomic/plasma/plasmaCrawlStacker.java index 25db7200e..1880a64c7 100644 --- a/source/de/anomic/plasma/plasmaCrawlStacker.java +++ b/source/de/anomic/plasma/plasmaCrawlStacker.java @@ -288,9 +288,7 @@ public final class plasmaCrawlStacker { // check if ip is local ip address checkInterruption(); // TODO: this is protocol specific InetAddress hostAddress = serverDomains.dnsResolve(nexturl.getHost()); - if(this.sb.getConfig("yacyDebugMode", "true").equals("true")){ - //just ignore the check in debugmode (useful for tor(.eff.org) - }else if (hostAddress == null) { + if (hostAddress == null) { // if a http proxy is configured name resolution may not work if (this.sb.remoteProxyConfig == null || !this.sb.remoteProxyConfig.useProxy()) { reason = plasmaCrawlEURL.DENIED_UNKNOWN_HOST;