swish-e/conf/example7.config

# ----- Example 7 - Spider using "http" method -------
#
#  Please see the swish-e documentation for
#  information on configuration directives.
#  Documentation is included with the swish-e
#  distribution, and also can be found on-line
#  at http://swish-e.org
#
#
#  This example demonstrates how to use the
#  the "http" method of spidering.
#
#  Indexing (spidering) is started with the following
#  command issued from the "conf" directory:
#
#     swish-e -S http -c example7.config
#
#  Note: You should have the current Bundle::LWP bundle
#  of perl modules installed.  This was tested with:
#     libwww-perl-5.53
#
#  ** Do not spider a web server without permission **
#
#---------------------------------------------------

# Include our site-wide configuration settings:

IncludeConfigFile example4.config

# Specify the URL (or URLs) to index:
IndexDir http://swish-e.org


# If a server goes by more than one name you can use this directive:

EquivalentServer http://swish-e.org  http://www.swish-e.org


# This defines how many links the spider should
# follow before stopping.  A value of 0 configures the spider to
# traverse all links. The default is 5
# The idea is to limit spidering, but seems of questionable use
# since depth may not be related to anything useful.

MaxDepth 10

# The number of seconds to wait between issuing
# requests to a server.  The default is 60 seconds.

Delay 1


# (default /var/tmp)  The location of a writeable temp directory
# on your system.  The HTTP access method tells the Perl helper to place
# its files there.  The default is defined in src/config.h and depends on
# the current OS.

TmpDir .


# The "http" method uses a perl helper program to fetch each document
# from the web called "swishspider" and is included in the src directory of
# the swish-e distribution.
SpiderDirectory ../src


# end of example
1	# ----- Example 7 - Spider using "http" method -------
2	#
3	# Please see the swish-e documentation for
4	# information on configuration directives.
5	# Documentation is included with the swish-e
6	# distribution, and also can be found on-line
7	# at http://swish-e.org
8	#
9	#
10	# This example demonstrates how to use the
11	# the "http" method of spidering.
12	#
13	# Indexing (spidering) is started with the following
14	# command issued from the "conf" directory:
15	#
16	# swish-e -S http -c example7.config
17	#
18	# Note: You should have the current Bundle::LWP bundle
19	# of perl modules installed. This was tested with:
20	# libwww-perl-5.53
21	#
22	# Do not spider a web server without permission
23	#
24	#---------------------------------------------------
25
26	# Include our site-wide configuration settings:
27
28	IncludeConfigFile example4.config
29
30	# Specify the URL (or URLs) to index:
31	IndexDir http://swish-e.org
32
33
34	# If a server goes by more than one name you can use this directive:
35
36	EquivalentServer http://swish-e.org http://www.swish-e.org
37
38
39
40	# This defines how many links the spider should
41	# follow before stopping. A value of 0 configures the spider to
42	# traverse all links. The default is 5
43	# The idea is to limit spidering, but seems of questionable use
44	# since depth may not be related to anything useful.
45
46	MaxDepth 10
47
48	# The number of seconds to wait between issuing
49	# requests to a server. The default is 60 seconds.
50
51	Delay 1
52
53
54	# (default /var/tmp) The location of a writeable temp directory
55	# on your system. The HTTP access method tells the Perl helper to place
56	# its files there. The default is defined in src/config.h and depends on
57	# the current OS.
58
59	TmpDir .
60
61
62	# The "http" method uses a perl helper program to fetch each document
63	# from the web called "swishspider" and is included in the src directory of
64	# the swish-e distribution.
65	SpiderDirectory ../src
66
67
68	# end of example