Download all links in a referenced input file using GNU parallel

wfox-parallel.sh

#! /usr/bin/env bash
#>------------------------------------------------------------------------------
#>
#> [ wfox-parallel ]
#>
#>    Download all links in a referenced input file using GNU parallel
#>
#>    Outputs will be situated into a new directory hierarchy that mirrors the
#>    origin website URL path for each file. File exif data will be retained
#>    if the 'xattr' package is installed on the local machine.
#>
#> USAGE:
#>
#>    wfox-parallel <FILE>
#>    wfox-parallel <OPTION>
#>
#>    where "FILE" is a valid file reference; and where "FILE" contains a
#>    vertical list of valid URLs; and where "OPTION" is one of the following:
#>
#>                |
#>    -h, --help  | Print this help text to the terminal
#>                |
#>
#> ATTRIBUTION:
#>
#>    Created on 20201115 by h8rt3rmin8r ([email protected])
#>
#>------------------------------------------------------------------------------

# Declare functions

function _get() {

    function _domain() {
        local ID_INX="${1}"
        local ID_PRO="${2//\//\\\/}"
        local ID_A="${ID_INX#$ID_PRO}"
        local ID_B="${ID_A//\/*}"
        local ID_C="${ID_B//*\@}"

        echo "${ID_C//\?*}"

        return $?
    }

    function _uag() {
        local nonce="${RANDOM: -1}"

        case "${nonce}" in
            0)
                echo 'Chrome/15.0.860.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/15.0.860.0'
                ;;
            1)
                echo 'Mozilla/4.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/11.0.1245.0 Safari/537.36'
                ;;
            2)
                echo 'Mozilla/5.0 (Linux; U; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13'
                ;;
            3)
                echo 'Mozilla/5.0 (Macintosh; AMD Mac OS X 10_8_2) AppleWebKit/535.22 (KHTML, like Gecko) Chrome/18.6.872'
                ;;
            4)
                echo 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36'
                ;;
            5)
                echo 'Mozilla/5.0 (Macintosh; PPC Mac OS X 10_6_7) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.790.0 Safari/535.1'
                ;;
            6)
                echo 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'
                ;;
            7)
                echo 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0'
                ;;
            8)
                echo 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.5 Safari/532.2'
                ;;
            9)
                echo 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.127 Safari/534.16'
                ;;
        esac

        return $?
    }

    local trg_url="${1}"
    local in_p=$(grep -Eo '^(([a-z0-9]+[-]?[a-z0-9]+[:])|([a-z0-9]+[:]))(//)' <<<"${trg_url}" 2>/dev/null)
    local in_m=$(_domain "${trg_url}" "${in_p}")
    local in_u=$(_uag)

    echo "$(date '+%s.%N')|${PPID}|$(printf "\e[38;5;25mwfox-parallel\e[0m")|$(echo -en '\e[38;5;25minfo\e[0m___')|${trg_url}" &>/dev/stderr

    wget -q --xattr --force-directories --content-disposition --no-clobber --adjust-extension --no-check-certificate --timeout=3 --tries=1 \
        -U "${in_u}" \
        --referer="${trg_url}" \
        --header="Authority: ${in_m}" \
        --header="Origin: ${in_p}${in_m}" \
        --header="Host: ${in_m}" \
        --header="Accept: */*" \
        --header="Upgrade-Insecure-Requests: 1" \
        --header="Cache-Control: max-age=0" \
        --header="TE: Trailers" \
        --header="Pragma: no-cache" \
        --header="Connection: keep-alive" \
        --header="DNT: 1" "${trg_url}"

    return $?
}

function _help() {
    cat "${0}" \
        | grep -E '^#[>]' \
        | sed 's/^..//'
    
    return $?
}

# Parse inputs and execute operations

in_f=$(readlink -f "${1}")

if [[ "${1}" =~ ^[-][hH]$ || "${1}" =~ ^[-]+help$ ]]; then
    _help

    exit $?
fi

if [[ ! -f "${1}" ]]; then
    echo "$(date '+%s.%N')|${PPID}|$(printf "\e[38;5;196mwfox-parallel\e[0m")|$(echo -en '\e[38;5;196merror\e[0m__')|Missing required input: <FILE>" &>/dev/stderr
    echo "$(date '+%s.%N')|${PPID}|$(printf "\e[38;5;25mwfox-parallel\e[0m")|$(echo -en '\e[38;5;25minfo\e[0m___')|Use '--help' for more information" &>/dev/stderr

    exit 1
fi

export -f _get

cat "${in_f}" \
    | parallel --no-notice -k _get "{}"

e_c="$?"

unset _get

exit ${e_c}