tools_eget

#!/bin/sh
# eget - simply shell on wget for loading directories over http (wget does not support wildcard for http)
# Example use:
# eget http://ftp.altlinux.ru/pub/security/ssl/*
#
# Copyright (C) 2014-2014, 2016  Etersoft
# Copyright (C) 2014 Daniil Mikhailov <danil@etersoft.ru>
# Copyright (C) 2016-2017 Vitaly Lipatov <lav@etersoft.ru>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#

WGET="wget"

# TODO: passthrou all wget options
if [ "$1" = "-q" ] ; then
    WGET="wget -q"
    shift
fi

if [ "$1" = "--list" ] ; then
    LISTONLY="$1"
    shift
fi

fatal()
{
    echo "$*" >&2
    exit 1
}

# check man glob
filter_glob()
{
	# translate glob to regexp
	grep "^$(echo "$1" | sed -e "s|\*|.*|g" -e "s|\?|.|g")$"
}


# download to this file
WGET_OPTION_TARGET=
if [ "$1" = "-O" ] ; then
    TARGETFILE="$2"
    WGET_OPTION_TARGET="-O $2"
    shift 2
fi

# TODO:
# -P support

if [ -z "$1" ] ; then
    echo "eget - wget wrapper" >&2
    fatal "Run with URL, like http://somesite.ru/dir/*.log"
fi

if [ "$1" = "-h" ] || [ "$1" = "--help" ] ; then
    echo "eget - wget wrapper, with support"
    echo "Usage: eget [-O target file] [--list] http://somesite.ru/dir/na*.log"
    echo "Options:"
    echo "    --list - print files frm url with mask"
    echo
    wget --help
    exit
fi

# do not support /
if echo "$1" | grep -q "/$" ; then
    fatal "Use http://example.com/e/* to download all files in dir"
fi

# If ftp protocol, just download
if echo "$1" | grep -q "^ftp://" ; then
    [ -n "$LISTONLY" ] && fatal "Error: list files for ftp:// do not supported yet"
    $WGET $WGET_OPTION_TARGET "$1"
    exit
fi

# drop mask part
URL="$(dirname "$1")/"

if echo "$URL" | grep -q "[*?]" ; then
    fatal "Error: there are globbing symbols (*?) in $URL"
fi

# mask allowed only in last part of path
MASK=$(basename "$1")

# If have no wildcard symbol like asterisk, just download
if echo "$MASK" | grep -qv "[*?]" ; then
    $WGET $WGET_OPTION_TARGET "$1"
    exit
fi

get_urls()
{
    $WGET -O- $URL | \
        grep -o -E 'href="([^\*/"#]+)"' | cut -d'"' -f2
}

if [ -n "$LISTONLY" ] ; then
    WGET="$WGET -q"
    for fn in $(get_urls | filter_glob "$MASK") ; do
        echo "$(basename "$fn")"
    done
    exit
fi

ERROR=0
for fn in $(get_urls | filter_glob "$MASK") ; do
    $WGET "$URL/$(basename "$fn")" || ERROR=1
done
exit $ERROR