is_spammer.bash

BASH Shell 编程 经典教程 《高级SHELL脚本编程》中文版

#!/bin/bash

# $Id: is_spammer.bash,v 1.12.2.11 2004/10/01 21:42:33 mszick Exp $
# Above line is RCS info.

# The latest version of this script is available from http://www.morethan.org.
#
# Spammer-identification
# by Michael S. Zick
# Used in the ABS Guide with permission.



#######################################################
# Documentation
# See also "Quickstart" at end of script.
#######################################################

:<<-'__is_spammer_Doc_'

    Copyright (c) Michael S. Zick, 2004
    License: Unrestricted reuse in any form, for any purpose.
    Warranty: None -{Its a script; the user is on their own.}-

Impatient?
    Application code: goto "# # # Hunt the Spammer' program code # # #"
    Example output: ":<<-'_is_spammer_outputs_'"
    How to use: Enter script name without arguments.
                Or goto "Quickstart" at end of script.

Provides
    Given a domain name or IP(v4) address as input:

    Does an exhaustive set of queries to find the associated
    network resources (short of recursing into TLDs).

    Checks the IP(v4) addresses found against Blacklist
    nameservers.

    If found to be a blacklisted IP(v4) address,
    reports the blacklist text records.
    (Usually hyper-links to the specific report.)

Requires
    A working Internet connection.
    (Exercise: Add check and/or abort if not on-line when running script.)
    Bash with arrays (2.05b+).

    The external program 'dig' --
    a utility program provided with the 'bind' set of programs.
    Specifically, the version which is part of Bind series 9.x
    See: http://www.isc.org

    All usages of 'dig' are limited to wrapper functions,
    which may be rewritten as required.
    See: dig_wrappers.bash for details.
         ("Additional documentation" -- below)

Usage
    Script requires a single argument, which may be:
    1) A domain name;
    2) An IP(v4) address;
    3) A filename, with one name or address per line.

    Script accepts an optional second argument, which may be:
    1) A Blacklist server name;
    2) A filename, with one Blacklist server name per line.

    If the second argument is not provided, the script uses
    a built-in set of (free) Blacklist servers.

    See also, the Quickstart at the end of this script (after 'exit').

Return Codes
    0 - All OK
    1 - Script failure
    2 - Something is Blacklisted

Optional environment variables
    SPAMMER_TRACE
        If set to a writable file,
        script will log an execution flow trace.

    SPAMMER_DATA
        If set to a writable file, script will dump its
        discovered data in the form of GraphViz file.
        See: http://www.research.att.com/sw/tools/graphviz

    SPAMMER_LIMIT
        Limits the depth of resource tracing.

        Default is 2 levels.

        A setting of 0 (zero) means 'unlimited' . . .
          Caution: script might recurse the whole Internet!

        A limit of 1 or 2 is most useful when processing
        a file of domain names and addresses.
        A higher limit can be useful when hunting spam gangs.


Additional documentation
    Download the archived set of scripts
    explaining and illustrating the function contained within this script.
    http://personal.riverusers.com/mszick_clf.tar.bz2


Study notes
    This script uses a large number of functions.
    Nearly all general functions have their own example script.
    Each of the example scripts have tutorial level comments.

Scripting project
    Add support for IP(v6) addresses.
    IP(v6) addresses are recognized but not processed.

Advanced project
    Add the reverse lookup detail to the discovered information.

    Report the delegation chain and abuse contacts.

    Modify the GraphViz file output to include the
    newly discovered information.

__is_spammer_Doc_

#######################################################




#### Special IFS settings used for string parsing. ####

# Whitespace == :Space:Tab:Line Feed:Carriage Return:
WSP_IFS=$'\x20'$'\x09'$'\x0A'$'\x0D'

# No Whitespace == Line Feed:Carriage Return
NO_WSP=$'\x0A'$'\x0D'

# Field separator for dotted decimal IP addresses
ADR_IFS=${NO_WSP}'.'

# Array to dotted string conversions
DOT_IFS='.'${WSP_IFS}

# # # Pending operations stack machine # # #
# This set of functions described in func_stack.bash.
# (See "Additional documentation" above.)
# # #

# Global stack of pending operations.
declare -f -a _pending_
# Global sentinel for stack runners
declare -i _p_ctrl_
# Global holder for currently executing function
declare -f _pend_current_

# # # Debug version only - remove for regular use # # #
#
# The function stored in _pend_hook_ is called
# immediately before each pending function is
# evaluated.  Stack clean, _pend_current_ set.
#
# This thingy demonstrated in pend_hook.bash.
declare -f _pend_hook_
# # #

# The do nothing function
pend_dummy() { : ; }

# Clear and initialize the function stack.
pend_init() {
    unset _pending_[@]
    pend_func pend_stop_mark
    _pend_hook_='pend_dummy'  # Debug only.
}

# Discard the top function on the stack.
pend_pop() {
    if [ ${#_pending_[@]} -gt 0 ]
    then
        local -i _top_
        _top_=${#_pending_[@]}-1
        unset _pending_[$_top_]
    fi
}

# pend_func function_name [$(printf '%q\n' arguments)]
pend_func() {
    local IFS=${NO_WSP}
    set -f
    _pending_[${#_pending_[@]}]=$@
    set +f
}

# The function which stops the release:
pend_stop_mark() {
    _p_ctrl_=0
}

pend_mark() {
    pend_func pend_stop_mark
}

# Execute functions until 'pend_stop_mark' . . .
pend_release() {
    local -i _top_             # Declare _top_ as integer.
    _p_ctrl_=${#_pending_[@]}
    while [ ${_p_ctrl_} -gt 0 ]
    do
       _top_=${#_pending_[@]}-1
       _pend_current_=${_pending_[$_top_]}
       unset _pending_[$_top_]
       $_pend_hook_            # Debug only.
       eval $_pend_current_
    done
}

# Drop functions until 'pend_stop_mark' . . .
pend_drop() {
    local -i _top_
    local _pd_ctrl_=${#_pending_[@]}
    while [ ${_pd_ctrl_} -gt 0 ]
    do
       _top_=$_pd_ctrl_-1
       if [ "${_pending_[$_top_]}" == 'pend_stop_mark' ]
       then
           unset _pending_[$_top_]
           break
       else
           unset _pending_[$_top_]
           _pd_ctrl_=$_top_
       fi
    done
    if [ ${#_pending_[@]} -eq 0 ]
    then
        pend_func pend_stop_mark
    fi
}

#### Array editors ####

# This function described in edit_exact.bash.
# (See "Additional documentation," above.)
# edit_exact &lt;excludes_array_name&gt; &lt;target_array_name&gt;
edit_exact() {
    [ $# -eq 2 ] ||
    [ $# -eq 3 ] || return 1
    local -a _ee_Excludes
    local -a _ee_Target
    local _ee_x
    local _ee_t
    local IFS=${NO_WSP}
    set -f
    eval _ee_Excludes=\( \$\{$1\[@\]\} \)
    eval _ee_Target=\( \$\{$2\[@\]\} \)
    local _ee_len=${#_ee_Target[@]}     # Original length.
    local _ee_cnt=${#_ee_Excludes[@]}   # Exclude list length.
    [ ${_ee_len} -ne 0 ] || return 0    # Can't edit zero length.
    [ ${_ee_cnt} -ne 0 ] || return 0    # Can't edit zero length.
    for (( x = 0; x < ${_ee_cnt} ; x++ ))
    do
        _ee_x=${_ee_Excludes[$x]}
        for (( n = 0 ; n < ${_ee_len} ; n++ ))
        do
            _ee_t=${_ee_Target[$n]}
            if [ x"${_ee_t}" == x"${_ee_x}" ]
            then
                unset _ee_Target[$n]     # Discard match.
                [ $# -eq 2 ] && break    # If 2 arguments, then done.
            fi
        done
    done
    eval $2=\( \$\{_ee_Target\[@\]\} \)
    set +f
    return 0
}

# This function described in edit_by_glob.bash.
# edit_by_glob &lt;excludes_array_name&gt; &lt;target_array_name&gt;
edit_by_glob() {
    [ $# -eq 2 ] ||
    [ $# -eq 3 ] || return 1
    local -a _ebg_Excludes
    local -a _ebg_Target
    local _ebg_x
    local _ebg_t
    local IFS=${NO_WSP}
    set -f
    eval _ebg_Excludes=\( \$\{$1\[@\]\} \)
    eval _ebg_Target=\( \$\{$2\[@\]\} \)
    local _ebg_len=${#_ebg_Target[@]}
    local _ebg_cnt=${#_ebg_Excludes[@]}
    [ ${_ebg_len} -ne 0 ] || return 0
    [ ${_ebg_cnt} -ne 0 ] || return 0
    for (( x = 0; x < ${_ebg_cnt} ; x++ ))
    do
        _ebg_x=${_ebg_Excludes[$x]}
        for (( n = 0 ; n < ${_ebg_len} ; n++ ))
        do
            [ $# -eq 3 ] && _ebg_x=${_ebg_x}'*'  #  Do prefix edit
            if [ ${_ebg_Target[$n]:=} ]          #+ if defined & set.
            then
                _ebg_t=${_ebg_Target[$n]/#${_ebg_x}/}
                [ ${#_ebg_t} -eq 0 ] && unset _ebg_Target[$n]
            fi
        done
    done
    eval $2=\( \$\{_ebg_Target\[@\]\} \)
    set +f
    return 0
}

# This function described in unique_lines.bash.
# unique_lines &lt;in_name&gt; &lt;out_name&gt;
unique_lines() {
    [ $# -eq 2 ] || return 1
    local -a _ul_in
    local -a _ul_out
    local -i _ul_cnt
    local -i _ul_pos
    local _ul_tmp
    local IFS=${NO_WSP}
    set -f
    eval _ul_in=\( \$\{$1\[@\]\} \)
    _ul_cnt=${#_ul_in[@]}
    for (( _ul_pos = 0 ; _ul_pos < ${_ul_cnt} ; _ul_pos++ ))
    do
        if [ ${_ul_in[${_ul_pos}]:=} ]      # If defined & not empty
        then
            _ul_tmp=${_ul_in[${_ul_pos}]}
            _ul_out[${#_ul_out[@]}]=${_ul_tmp}
            for (( zap = _ul_pos ; zap < ${_ul_cnt} ; zap++ ))
            do
                [ ${_ul_in[${zap}]:=} ] &&
                [ 'x'${_ul_in[${zap}]} == 'x'${_ul_tmp} ] &&
                    unset _ul_in[${zap}]
            done
        fi
    done
    eval $2=\( \$\{_ul_out\[@\]\} \)
    set +f
    return 0
}

# This function described in char_convert.bash.
# to_lower &lt;string&gt;
to_lower() {
    [ $# -eq 1 ] || return 1
    local _tl_out
    _tl_out=${1//A/a}
    _tl_out=${_tl_out//B/b}
    _tl_out=${_tl_out//C/c}
    _tl_out=${_tl_out//D/d}
    _tl_out=${_tl_out//E/e}
    _tl_out=${_tl_out//F/f}
    _tl_out=${_tl_out//G/g}
    _tl_out=${_tl_out//H/h}
    _tl_out=${_tl_out//I/i}
    _tl_out=${_tl_out//J/j}
    _tl_out=${_tl_out//K/k}
    _tl_out=${_tl_out//L/l}
    _tl_out=${_tl_out//M/m}
    _tl_out=${_tl_out//N/n}
    _tl_out=${_tl_out//O/o}
    _tl_out=${_tl_out//P/p}
    _tl_out=${_tl_out//Q/q}
    _tl_out=${_tl_out//R/r}
    _tl_out=${_tl_out//S/s}
    _tl_out=${_tl_out//T/t}
    _tl_out=${_tl_out//U/u}
    _tl_out=${_tl_out//V/v}
    _tl_out=${_tl_out//W/w}
    _tl_out=${_tl_out//X/x}
    _tl_out=${_tl_out//Y/y}
    _tl_out=${_tl_out//Z/z}
    echo ${_tl_out}
    return 0
}

#### Application helper functions ####

# Not everybody uses dots as separators (APNIC, for example).
# This function described in to_dot.bash
# to_dot &lt;string&gt;
to_dot() {
    [ $# -eq 1 ] || return 1
    echo ${1//[#|@|%]/.}
    return 0
}

# This function described in is_number.bash.
# is_number &lt;input&gt;
is_number() {
    [ "$#" -eq 1 ]    || return 1  # is blank?
    [ x"$1" == 'x0' ] && return 0  # is zero?
    local -i tst
    let tst=$1 2>/dev/null         # else is numeric!
    return $?
}

# This function described in is_address.bash.
# is_address &lt;input&gt;
is_address() {
    [ $# -eq 1 ] || return 1    # Blank ==> false
    local -a _ia_input
    local IFS=${ADR_IFS}
    _ia_input=( $1 )
    if  [ ${#_ia_input[@]} -eq 4 ]  &&
        is_number ${_ia_input[0]}   &&
        is_number ${_ia_input[1]}   &&
        is_number ${_ia_input[2]}   &&
        is_number ${_ia_input[3]}   &&
        [ ${_ia_input[0]} -lt 256 ] &&
        [ ${_ia_input[1]} -lt 256 ] &&
        [ ${_ia_input[2]} -lt 256 ] &&
        [ ${_ia_input[3]} -lt 256 ]
    then
        return 0
    else
        return 1
    fi
}

# This function described in split_ip.bash.
# split_ip &lt;IP_address&gt; &lt;array_name_norm&gt; [&lt;array_name_rev&gt;]
split_ip() {
    [ $# -eq 3 ] ||              #  Either three
    [ $# -eq 2 ] || return 1     #+ or two arguments
    local -a _si_input
    local IFS=${ADR_IFS}
    _si_input=( $1 )
    IFS=${WSP_IFS}
    eval $2=\(\ \$\{_si_input\[@\]\}\ \)
    if [ $# -eq 3 ]