Author: kwright
Date: Sun Jul 8 22:54:53 2012
New Revision: 1358860
URL: http://svn.apache.org/viewvc?rev=1358860&view=rev
Log:
Fix for CONNECTORS-489.
Modified:
manifoldcf/trunk/CHANGES.txt
manifoldcf/trunk/connectors/rss/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/rss/RSSConnector.java
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
Modified: manifoldcf/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/CHANGES.txt?rev=1358860&r1=1358859&r2=1358860&view=diff
==============================================================================
--- manifoldcf/trunk/CHANGES.txt (original)
+++ manifoldcf/trunk/CHANGES.txt Sun Jul 8 22:54:53 2012
@@ -3,6 +3,10 @@ $Id$
======================= 0.6-dev =====================
+CONNECTORS-489: Fix user-agent string in web and rss connectors
+so that ISA proxies don't refuse to proxy the requests.
+(Jan van Haarst)
+
CONNECTORS-487: Upgrade to HSQLDB 2.2.9.
(Karl Wright)
Modified:
manifoldcf/trunk/connectors/rss/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/rss/RSSConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/rss/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/rss/RSSConnector.java?rev=1358860&r1=1358859&r2=1358860&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/rss/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/rss/RSSConnector.java
(original)
+++
manifoldcf/trunk/connectors/rss/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/rss/RSSConnector.java
Sun Jul 8 22:54:53 2012
@@ -172,7 +172,7 @@ public class RSSConnector extends org.ap
String emailAddress = params.getParameter(emailParameter);
if (emailAddress == null)
throw new ManifoldCFException("Missing email address");
- userAgent = "ApacheManifoldCFRSSFeedReader;
"+((emailAddress==null)?"":emailAddress)+")";
+ userAgent = "Mozilla/5.0 (ApacheManifoldCFRSSFeedReader;
"+((emailAddress==null)?"":emailAddress)+")";
from = emailAddress;
String robotsUsageString = params.getParameter(robotsUsageParameter);
Modified:
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java?rev=1358860&r1=1358859&r2=1358860&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
(original)
+++
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
Sun Jul 8 22:54:53 2012
@@ -361,7 +361,7 @@ public class WebcrawlerConnector extends
String emailAddress =
params.getParameter(WebcrawlerConfig.PARAMETER_EMAIL);
if (emailAddress == null)
throw new ManifoldCFException("Missing email address");
- userAgent = "ApacheManifoldCFWebCrawler; "+emailAddress+")";
+ userAgent = "Mozilla/5.0 (ApacheManifoldCFWebCrawler; "+emailAddress+")";
from = emailAddress;
x = params.getParameter(WebcrawlerConfig.PARAMETER_ROBOTSUSAGE);