Posts tagged with “search”

eggdrop script: search on SearXNG instance, by cage

Written by Simone

You can try this script on #fediverso at irc.libera.chat, where me, cage, ndo and other friends hang out

bot: "verne", running on @wpn

SearXNG instance: https://search.woodpeckersnest.space/

Thanks to cage for the script and ndo for creating the channel o/

# © cage released under CC0, public domain
# https://creativecommons.org/publicdomain/zero/1.0/

# Date: 16-08-2024
# Version: 0.1

# Package description: do a web search using your searxng instance
# Public ones won't probably work because of "limiter"

# Authorize your channel from the partyline with:
# .chanset +searxng #your-channel

# Do a search
# .search <query> | .search paris (this query goes to default engine)
# .search +<engine> <query> | .search +wp paris (this query goes to
# wikipedia)
# .search !images paris | this query search only paris' images

# List of engines: https://docs.searxng.org/user/configured_engines.html

# tcllib is required

############## configuration directives ############################

# url of the HTTP(S) server of the search engine

set searxconfig(website_url)    "https://example.com/searxng"

# serach command to trigger the search

set searxconfig(cmd)            ".search"

# default search engine

set searxconfig(default_engine) "ddg"

# maximum number of search results printed

set searxconfig(max_results)    3

# time tracker file
# NB: when this script runs any file with the same name within the path in the
# working  directory  (depending of  what  is  considered the  working
# directory of the script) will be erased and overwritten!

set searxconfig(file_millis)    "searx_millis.tmp"

# Minimum search frequency in milliseconds.
# This is  the minimum  time that must  pass between  two consecutive
# search

set searxconfig(max_freq)       30000

############## configuration ends here #############

# tcllib is required
package require csv

setudef flag searxng

if { !([info exists searxconfig(lastmillis)]) } {
    set searxconfig(lastmillis) 0
}

bind pub - $searxconfig(cmd) search:searxng

proc send_message {message} {
    putserv "PRIVMSG $message"
}

proc slurp_file {path} {
    set fp [open $path r]
    set file_data [read $fp]
    close $fp
    return $file_data
}

proc process_csv {csv channel} {
    global searxconfig
    set rows [split $csv "\n"]
    set count 0
    #remove the header
    set rows [lrange $rows 1 [llength $rows]]
    if {[llength $rows] < 1} {
        send_message "$channel :Something gone wrong."
    } else {
        foreach row $rows {
            if {$count < $searxconfig(max_results)} {
                set row_splitted [csv::split $row]
                set title [lindex $row_splitted 0]
                set url   [lindex $row_splitted 1]
                send_message "$channel :$title $url"
                incr count
            } else {
                break
            }
        }
    }
}

proc encode {query} {
    set query [regsub -all { } $query "%20"]
    set query [regsub -all {&} $query "%26"]
    set query [regsub -all {=} $query "%3D"]
    set query [regsub -all {!} $query "%21"]
}

proc get_query_results {engine query} {
    global searxconfig
    set query [encode $query]
    set engine [encode $engine]
    set url "$searxconfig(website_url)search?q=$query&format=csv&engines=$engine"
    ## decomment the line below for debugging purposes
    # putlog $url
    return [exec curl -sS $url]
}

proc get_last_millis { } {
    global searxconfig
    if {[file exists $searxconfig(file_millis)]} {
        set searxconfig(lastmillis) [slurp_file $searxconfig(file_millis)]
    } else {
        set fp [open $searxconfig(file_millis) w]
        puts $fp 0
        close $fp
        get_last_millis
    }
}

proc set_last_millis { } {
    global searxconfig
    set fp [open $searxconfig(file_millis) w]
    puts $fp [clock milliseconds]
    close $fp
}

proc search:searxng {nick host hand chan text} {
    global searxconfig

    if {!([channel get $chan searxng])} {
        send_message "$chan :This script has not been authorized to run in this channel."
        return 0
    }

    set millis [clock milliseconds]

    get_last_millis

    if { [expr $millis - $searxconfig(lastmillis)] > $searxconfig(max_freq) } {
        ## test antiflood superato

        set_last_millis

        set text_splitted [split $text " {}"]
        set engine [lindex $text_splitted 0]
        set text_length [llength $text_splitted]
        set query [lrange $text_splitted 1 $text_length]


        if {![regexp {^\+} $engine]} {
            set engine $searxconfig(default_engine)
            set query $text_splitted
        } else {
            set engine [string range $engine 1 [string length $engine]]
        }

        if {$query == {}} {
            send_message "$chan :Missing search criteria."
        } else {
            set csv [get_query_results $engine $query]
            process_csv $csv $chan
        }

        return 1;
    }
        send_message "$chan :Try again later."
    return 0
}

putlog "SearXNG Loaded"`

gemlog