[root@sd cgi-bin]# estwaver init camel

[root@sd cgi-bin]# ls

camel/　estseek.cgi*　estseek.conf　estseek.help　estseek.tmpl
estseek.top　estseek_web.cgi*　estseek_web.conf　index/


[root@sd cgi-bin]# nano estseek_web.conf
#
indexname: /home/camel/html/cgi-bin/camel/_index

tmplfile: estseek.tmpl

topfile: estseek.top

helpfile: estseek.help

lockindex: true

pseudoindex:

#replace: ^file:///home/mikio/public_html/{{!}}http://localhost/
#replace: /index\.html?${{!}}/

#


[root@sd cgi-bin]# cd camel

[root@sd camel]# ls

_conf  _index/  _log  _meta  _queue  _tmp/  _trace/


[root@sd camel]# nano _conf

# seed documents (weight and URL)

seed: 3.0|http://s1.servers.net/
seed: 3.0|http://s2.servers.net/
seed: 3.0|http://s3.servers.net/
seed: 3.0|http://s4.servers.net/
seed: 3.0|http://s5.servers.net/
seed: 3.0|http://s6.servers.net/
seed: 3.0|http://s7.servers.net/
seed: 3.0|http://s8.servers.net/

# host name of the proxy
proxyhost:

# port number of the proxy
proxyport:

# waiting interval of each request (in milliseconds)
interval: 500

# timeout of each request (in seconds)
timeout: 30

# strategy of crawling path (0:balanced, 1:similarity, 2:depth, 3:width, 4:random)
strategy: 3

# inheritance ratio of similarity from the parent
inherit: 0.4

# maximum depth of seed documents
seeddepth: 0

# maximum depth of recursion
maxdepth: 8

# standard value for checking mass sites
masscheck: 500

# maximum number of records of the priority queue
queuesize: 50000

# regular expressions and replacement strings to normalize URLs
# replace: ^http://127.0.0.1/{{!}}http://localhost/

# allowing regular expressions of URLs to be visited
allowrx: ^http://

# denying regular expressions of URLs to be visited
denyrx: \.(css|js|csv|tsv|log|md5|crc|conf|ini|inf|lnk|sys|tmp|bak)$
denyrx: \.(xml|xsl|xslt|rdf|rss|dtd|sgml|sgm)$
denyrx: \.(pgp|sig|cer|csr|pem|key|b64|uu|uue|[0-9])$
denyrx: \.(rtf|pdf|ps|eps|ai|doc|xls|ppt|sxw|sxc|sxi|xdw|jtd|oas|swf)$
denyrx: \.(zip|tar|tgz|gz|bz2|tbz2|z|lha|lzh)(\?.*)?$
denyrx: \.(7z|lzo|lzma|cpio|shar|cab|rar|sit|ace|hqx)(\?.*)?$
denyrx: \.(bin|o|a|so|exe|dll|lib|obj|ocx|class|jar|war)(\?.*)?$
denyrx: \.(rpm|deb|qdb|qdb|dbx|dbf|dat|msi|bat|com|iso)(\?.*)?$
denyrx: \.(png|gif|jpg|jpeg|tif|tiff|bmp|ico|pbm|pgm|ppm|xbm|xpm|dvi)$
denyrx: \.(au|snd|mid|midi|kar|smf|mp2|mp3|m3u|wav|wma|wmp|asx|at3|aif)$
denyrx: \.(mpg|mpeg|qt|mov|avi|wmv|wvx|asf|ram|rm)$
denyrx: (/core$|/core\.[0-9]*$|/camel/)
denyrx: ://(localhost|[a-z]*\.localdomain|127\.0\.0\.1)/


# preferred language (0:English, 1:Japanese, 2:Chinese, 3:Korean, 4:misc)
language: 1

# text size limitation (in kilobytes)
textlimit: 128

# total number of keywords for seed documents
seedkeynum: 256

# number of keywords saved for each document
savekeynum: 32

# number of threads running in parallel
threadnum: 10

# number of documents to collect
docnum: 30000

# running time period (in s:seconds, m:minutes, h:hours, d:days)
period: 10000s

# revisit span (in s:seconds, m:minutes, h:hours, d:days)
revisit: 7d

# maximum size of the index cache (in megabytes)
cachesize: 256

#


[root@sd camel]# su -

[root@sd ~]# cd /home/camel/html/cgi-bin

[root@sd cgi-bin]# estwaver crawl camel