Swish-e

swishbuild Building Swish-e package

swish-
swishbuild-
swishbuild-again 

Important

• Do not run swish-e as root.

swish-e configuration (spider.conf)

my %dayabay = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/',
    delay_sec   => '1',
    max_depth   => '1',
    credentials => 'dayabay:3quarks'
);

my %documents = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.bnl.gov/private/documents/',
    delay_sec   => '1',
    max_depth   => '1',
    credentials => 'dayabay:3quarks'
);

my %docdb = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/cgi-bin/DocDB/ListBy?alldocs=1',
    delay_sec   => '1',
    max_depth   => '1',
    credentials => 'dayabay:3quarks'
);

my %engdb = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/cgi-bin/EngDB/ListBy?alldocs=1',
    delay_sec   => '1',
    max_depth   => '1',
    credentials => 'dayabay:3quarks'
);

my %internal = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/internal/',
    delay_sec   => '1',
    max_depth   => '1',
    credentials => 'dayabay:3quarks'
);

my %publicwiki = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'https://wiki.bnl.gov/dayabay/index.php?title=Main_Page',
    delay_sec   => '1',
    max_depth   => '2',
);

my %privatewiki = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'https://wiki.bnl.gov/dayabay-private/index.php?title=Main_Page',
    delay_sec   => '1',
    max_depth   => '2',
    credentials => 'dayabay:3quarks'
);

my %repository  = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/tracs/dybsvn/browser/',
    delay_sec   => '1',
    max_depth   => '10',
    credentials => 'dayabay:3quarks'
);

my %trac  = (
    email       => 'tianxc@ihep.ac.cn',
    base_url    => 'http://dayabay.ihep.ac.cn/tracs/dybsvn',
    delay_sec   => '1',
    max_depth   => '2',
    credentials => 'dayabay:3quarks'
);

@servers = ( \%dayabay, \%documents, \%docdb, \%internal, \%engdb, \%publicwiki, \%privatewiki, \%repository, \%trac );
1;

swish.conf

# Example configuration file

# Tell Swish-e what to index (same as -i switch above):
IndexDir spider.pl


# And pass the name of spider config file to the spider:
SwishProgParameters spider.conf


# Tell Swish-e that .txt files are to use the text parser:
IndexContents TXT* .txt


# Otherwise, use the HTML parser:
DefaultContents HTML*


# Ask libxml2 to report any parsing errors and warnings or
# any UTF-8 to 8859-1 conversion errors:
ParserWarnLevel 9

Indexing

touch indexing_time.file
/usr/local/bin/swish-e -c swish.conf -S prog