File: search_terms.cfg

package info (click to toggle)
httpry 0.1.8-5
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 436 kB
  • sloc: ansic: 1,358; perl: 1,336; sh: 155; makefile: 62
file content (47 lines) | stat: -rw-r--r-- 1,577 bytes parent folder | download | duplicates (6)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
#
# Config file for search_terms.pm
#
# $output_file (required)
#    A valid path to write an output file
#    containing the collected summary data.
#
# %domains (required)
#    A hash containing domain/name pairs to
#    search. The format is self-explanatory;
#    to augment it, simply add the domain and
#    the CGI name of the element to extract
#    the search term.
#
# %ignore (not required)
#    A hash containing domain/regexp pairs to
#    prune from the results list. The regexps
#    are an array of all patterns to match to
#    that particular domain. To ignore all
#    results from a domain, use a regexp of "."

$output_file = "search_terms.txt";
%domains = (
             ".altavista.com"    => "q",
             "search.aol.com"    => "q",
             ".ask.com"          => "q",
             ".bing.com"         => "q",
             ".google.com"       => "q",
             ".lycos.com"        => "query",
             ".yahoo.com"        => "p",

             ".amazon.com"       => "field-keywords",
             "search.ebay.com"   => "satitle",
             "stumbleupon.com"   => "q",
             "www.facebook.com"  => "q",
             ".wikipedia.org"    => "search",
             ".wolframalpha.com" => "i",
             ".youtube.com"      => "search_query"
           );
%ignore = (
             ".google.com"         => [ "^tbn:", "^info:", "^http:", "^music/image" ],
             "clients1.google.com" => [ "." ],
             ".mail.yahoo.com"     => [ "^mail_candygram" ],
             ".adserver.yahoo.com" => [ "." ]
          );

1;