Annotation of libwww/Robot/src/robot.sh, revision 1.3
1.1 frystyk 1: #!/bin/sh
2: if [ $# -lt 3 ]
3: then
1.2 frystyk 4: echo "A simple example of how the libwww robot can be used"
5: echo "For a full description, see"
6: echo
7: echo " http://www.w3.org/Robot/User/CommandLine.html"
1.1 frystyk 8: echo
9: echo "Usage: $0 RootURI ImageRootURI LogPrefix [ flags ]"
10: echo
11: echo "where"
1.2 frystyk 12: echo " RootURI is the URI prefix for links, for example http://www.w3.org/Robot/"
1.1 frystyk 13: echo " ImageRootURI is the URI prefix for inlined images, for example http://www.w3.org"
1.2 frystyk 14: echo " LogPrefix is the prefix for log files, for example robot"
1.1 frystyk 15: echo " flags are any additional command line flags, for example -vp"
16: echo
17: echo "See"
18: echo " http://www.w3.org/Robot/"
19: echo
20: echo "for more information"
21: exit 1
22: fi
23:
24: ROOT=$1
25: IMGROOT=$2
26: LOG=$3
27: FLAGS=$4
28:
1.3 ! frystyk 29: ROBOT=./webbot
1.1 frystyk 30:
1.2 frystyk 31: ${ROBOT} ${FLAGS} -q -ss -n -depth 99 \
1.1 frystyk 32: -exclude "/ArchiveBrowser/|/History/|/member/|/team/" \
1.3 ! frystyk 33: -check "\.gz$|\.tar$|\.tgz$|\.Z$|\.zip$|\.ZIP$|\.exe$|\.EXE$|\.ps$|\.doc$|\.pdf$|\.xplot$|\.java$|\.c$|\.h$|\.txt$|\.ppt$|\.gif$|\.GIF$|\.tiff$|\.png$|\.PNG$|\.jpeg$|\.jpg$|\.JPE$" \
1.1 frystyk 34: -prefix ${ROOT} \
35: -img -imgprefix ${IMGROOT} \
36: -l ${LOG}-log-clf.txt \
37: -alt ${LOG}-log-alt.txt \
38: -hit ${LOG}-log-hit.txt \
1.2 frystyk 39: -rellog ${LOG}-log-link-relations.txt -relation stylesheet \
1.1 frystyk 40: -lm ${LOG}-log-lastmodified.txt \
41: -title ${LOG}-log-title.txt \
42: -referer ${LOG}-log-referer.txt \
43: -negotiated ${LOG}-log-negotiated.txt \
44: -404 ${LOG}-log-notfound.txt \
45: -reject ${LOG}-log-reject.txt \
46: -format ${LOG}-log-format.txt \
47: -charset ${LOG}-log-charset.txt \
48: ${ROOT}
Webmaster