ttts/spider/xmlyfetcher

#!/bin/bash
#
# Copyright (C) 2023 Wenva <lvyexuwenfa100@126.com>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is furnished
# to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

spushd() {
     pushd "$1" 2>&1> /dev/null
}

spopd() {
     popd 2>&1> /dev/null
}

info() {
     local green="\033[1;32m"
     local normal="\033[0m"
     echo -e "[${green}INFO${normal}] $1"
}

cmdcheck() {
    command -v $1>/dev/null 2>&1 || { error >&2 "Please install command $1 first."; exit 1; }
}

error() {
     local red="\033[1;31m"
     local normal="\033[0m"
     echo -e "[${red}ERROR${normal}] $1"
}

curdir() {
    if [ ${0:0:1} = '/' ] || [ ${0:0:1} = '~' ]; then
        echo "$(dirname $0)"
    elif [ -L $0 ];then
        name=`readlink $0`
        echo $(dirname $name)
    else
        echo "`pwd`/$(dirname $0)"
    fi
}

myos() {
    echo `uname|tr "[:upper:]" "[:lower:]"`
}

#########################################
###           GROBLE DEFINE           ###
#########################################

VERSION=2.0.1
AUTHOR=smallmuou

#########################################
###             ARG PARSER            ###
#########################################

usage() {

prog=`basename $0`

cat << EOF
$prog version $VERSION by $AUTHOR

USAGE: $prog [OPTIONS] albumId type [type-param1 [type-param1 ...]]

DESCRIPTION:
    This tool is used to download tracks under ximalaya.com.

    albumId - the id of album, you can see from url,like https://www.ximalaya.com/album/2677356, the albumId is 2677356
    type - all/page/track, when type is all, no type-params required; when type is page, the type-params is the pagenum (start with 1); when type is track, the type-params is trackid;
    trackId - the id of track, you can see from url,like https://www.ximalaya.com/sound/25202, the trackId is 25202

OPTIONS:
    -h      Show this help message and exit.
    -o      Output directory, default is current directory.

EXAMPLES:
    $prog 12891461 all
    $prog 12891461 page 1 2 3
    $prog 12891461 track 211393643
    $prog -o 'output_directory' 12891461 all

EOF
exit 1
}

# output set current directory
dst_dir=.

while getopts 'o:h' arg; do
    case $arg in
        h)
            usage
            ;;
        o)
           dst_dir=$OPTARG
            ;;
        ?)
            usage
            ;;
    esac
done

shift $(($OPTIND - 1))

[ ! -d $dst_dir ] && { error "The output directory $dst_dir does not exist."; exit -1; }

#########################################
###            MAIN ENTRY             ###
#########################################

PAGE_SIZE=30

# params: jsonobject key
decode_json() {

statement=`cat << EOF
import json,sys
if sys.version_info<(3,0,0):
  reload(sys)
  sys.setdefaultencoding("utf8")
try:
    print(json.dumps(json.load(sys.stdin)[sys.argv[1]],ensure_ascii=False))
except KeyError as e:
    print('')
EOF`

    echo `cat|python -c "$statement" "$1"`
}

# param track_id
fetch_track_by_id() {
    result=`curl -s "http://mobile.ximalaya.com/v1/track/baseInfo?device=iPhone&trackId=$1"|grep title`
    if [ -n "$result" ];then
        uid=`echo $result|decode_json uid|sed 's/\"//g'`
        title=`echo $result|decode_json title|sed 's/\"//g'`
        url64=`echo $result|decode_json playUrl64|sed 's/\"//g'|sed 's/\\\//g'`

        if [ -n "$url64" ];then
            title=`echo $title|sed 's/\.//g'|sed 's/\///g'`
            wget "$url64" -O "$dst_dir/$title.mp3"
        else
            error "Failed to fetch the track, may be a paid resource."
        fi
    else
        error "The trackId $1 does not exist."
    fi
}

# param track_id track_id
fetch_track_by_ids() {
    for id in $@; do
        fetch_track_by_id $id
    done
}

# param: album_id page_num
fetch_tracks_by_page() {
    local album_id=$1
    local page_num=$2
    local page_size=$PAGE_SIZE
    local content=`curl -s "https://www.ximalaya.com/revision/album/v1/getTracksList?albumId=$album_id&pageNum=$page_num&pageSize=$page_size"`

statement=`cat << EOF
import json,sys
items = json.loads(sys.argv[1])['data']['tracks']
for item in items:
    print(item['trackId'])

EOF`

    track_ids=`python -c "$statement" "$content"`
    fetch_track_by_ids $track_ids
}

# param: album_id
fetch_album_track_count() {
    local album_id=$1
    local content=`curl -s "https://www.ximalaya.com/revision/album/v1/getTracksList?albumId=$album_id&pageNum=0&pageSize=1"`

statement=`cat << EOF
import json,sys
count = json.loads(sys.argv[1])['data']['trackTotalCount']
print(count)

EOF`
    echo `python -c "$statement" "$content"`
}

# param: album_id page_num1 page_num2
fetch_tracks_by_pages() {
    local album_id=$1
    shift
    for page in $@; do
        fetch_tracks_by_page $album_id $page
    done
}

# main
[ $# -lt 2 ] && usage

album_id=$1
type=$2

# remove the first two parameters
shift
shift

if [ "$type" == "all" ];then
    count=`fetch_album_track_count $album_id`
    page_count=$((count/$PAGE_SIZE))
    info "Total count is $count"
    for (( i = 0; i <= $page_count+1; i++ )); do
        fetch_tracks_by_page $album_id $i
    done
elif [ "$type" == "page" ];then
    fetch_tracks_by_pages $album_id $@
elif [ "$type" == "track" ];then
    fetch_track_by_ids $@
else
    usage
fi