crawler now you can specify path not to include

This commit is contained in:
Peter Hedenskog 2012-10-18 22:52:50 +02:00
parent 3a7c864ec9
commit c0d3781ac6
2 changed files with 1 additions and 1 deletions

View File

@ -69,7 +69,7 @@ mkdir $REPORT_DATA_DIR
mkdir $REPORT_PAGES_DIR
mkdir $REPORT_DATA_PAGES_DIR
java -Xmx256m -Xms256m -cp dependencies/crawler-0.9-full.jar com.soulgalore.crawler.run.CrawlToFile -u $URL -l $DEPTH $FOLLOW_PATH -f $REPORT_DATA_DIR/urls.txt -ef $REPORT_DATA_DIR/nonworkingurls.txt
java -Xmx256m -Xms256m -cp dependencies/crawler-0.9.1-full.jar com.soulgalore.crawler.run.CrawlToFile -u $URL -l $DEPTH $FOLLOW_PATH -f $REPORT_DATA_DIR/urls.txt -ef $REPORT_DATA_DIR/nonworkingurls.txt
# read the urls
result=()