You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by Apache Wiki <wi...@apache.org> on 2007/09/20 19:20:33 UTC
[Nutch Wiki] Update of "Crawl" by susam
Dear Wiki user,
You have subscribed to a wiki page or wiki category on "Nutch Wiki" for change notification.
The following page has been changed by susam:
http://wiki.apache.org/nutch/Crawl
The comment on the change is:
fixed topN bug
------------------------------------------------------------------------------
== Script ==
{{{
#!/bin/sh
-
- # Runs the Nutch bot to crawl or re-crawl
- # Usage: bin/runbot [safe]
- # If executed in 'safe' mode, it doesn't delete the temporary
- # directories generated during crawl. This might be helpful for
- # analysis and recovery in case a crawl fails.
- #
- # Author: Susam Pal
-
- depth=2
+ depth=8
threads=50
adddays=5
- topN=2 # Comment this statement if you don't want to set topN value
+ topN=1000 #Comment this statement if you don't want to set topN value
# Parse arguments
if [ "$1" == "safe" ]
@@ -101, +92 @@
if [ -n "$topN" ]
then
- topN="--topN $rank"
+ topN="-topN $topN"
else
topN=""
fi
@@ -125, +116 @@
$NUTCH_HOME/bin/nutch fetch $segment -threads $threads
if [ $? -ne 0 ]
then
- echo "runbot: fetch $segment at depth $depth failed. Deleting segment $segment."
+ echo "runbot: fetch $segment at depth `expr $i + 1` failed. Deleting segment $segment."
rm -rf $segment
continue
fi
@@ -138, +129 @@
$NUTCH_HOME/bin/nutch mergesegs crawl/MERGEDsegments crawl/segments/*
if [ "$safe" != "yes" ]
then
- rm -rf crawl/segments/*
+ rm -rf crawl/segments
else
- mkdir crawl/FETCHEDsegments
- mv --verbose crawl/segments/* crawl/FETCHEDsegments
+ mv $MVARGS crawl/segments crawl/FETCHEDsegments
fi
- mv --verbose crawl/MERGEDsegments/* crawl/segments
+ mv $MVARGS crawl/MERGEDsegments crawl/segments
- rmdir crawl/MERGEDsegments
echo "----- Invert Links (Step 4 of $steps) -----"
$NUTCH_HOME/bin/nutch invertlinks crawl/linkdb crawl/segments/*