Thema: Crawler IMDB-ID by Release-Name / Dirname xrel.to srrdb.com

Huhu,

hab heute meine beiden Funktionen zum Abgreifen der IMDB-ID von srrdb und xrel überarbeitet. Wer sich auskennt, erkennt, dass ich in jeder Funktion mehrere Möglichkeiten zum Abgreifen der IMDB-ID ausprogrammiert habe. Im Test von 1000 Releases, konnten 951 Stk. abgegriffen werden. Die 49 Stück waren weder auf XREL noch SRRDB gelistet oder es gab dafür keine IMDB-ID was mit imdb.com abgeglichen wurde und demnach korrekt ist.

Code:

agent="Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.742.122 Safari/534.30"
proxy=""

getimdb_srrdb() {
    release="${1}"
    if [ -z "${imdb_id}" ]; then
        echo -e ":: Check srrdb.com"
        echo -e ":: #1"
        imdb_id_temp=`curl -sS ${proxy} -A "${agent}" -L "https://www.srrdb.com/api/imdb/${release}" | python -mjson.tool | egrep -i '"imdb":' | grep -m1 -oE "[0-9]{1,15}"`
        if [ -n "${imdb_id_temp}" ]; then
            imdb_id="tt${imdb_id_temp}"
        fi
        
        if [ -z "${imdb_id}" ]; then
            echo -e ":: #2"
            nfo_filename_temp=`curl -sS ${proxy} -A "${agent}" -L "https://www.srrdb.com/api/nfo/${release}" | python -mjson.tool | egrep '"http' | cut -d\" -f2`
            if [ -n "${nfo_filename_temp}" ]; then
                imdb_id=`curl -sS ${proxy} -A "${agent}" -L "${nfo_filename_temp}" | grep -m1 -oE "tt[0-9]{1,15}"`
            fi
            
            if [ -z "${imdb_id}" ]; then
                echo -e ":: #3"
                nfo_filename_temp=`curl -sS ${proxy} -A "${agent}" -L "https://www.srrdb.com/release/details/${release}" | grep "storedFile" |  grep "icon-nfo" | sed 's/href="/\n/g' | grep "download" | cut -d\" -f1`
                if [ -n "${nfo_filename_temp}" ]; then
                    curl -sS ${proxy} -A "${agent}" -L "https://www.srrdb.com${nfo_filename_temp}" > file.nfo
                    imdb_id=`tr '[\000-\011\013-\037\177-\377]' '.' < file.nfo | grep -m1 -oE "tt[0-9]{1,15}" | head -n1`
                fi
            fi
        fi
    fi
}


getimdb_xrel() {
    release="${1}"
    if [ -z "${imdb_id}" ]; then
        echo -e ":: Check xrel.to"
        echo -e ":: #1"
        xrel_temp=`curl -sS ${proxy} -A "${agent}" -L "https://api.xrel.to/v2/search/releases.json?scene=true&p2p=true&q=${release}"`
        
        if [ -n "${xrel_temp}" ]; then
            echo "${xrel_temp}" > ${myhome}/asset/releases_json/${release}.json
            
            imdb_id=`cat "${myhome}/asset/releases_json/${release}.json" | grep -m1 -oE "tt[0-9]{7,15}"`
            
            if [ -z "${imdb_id}" ]; then
                echo -e ":: #2"
                id_imdb_temp=`cat "${myhome}/asset/releases_json/${release}.json" | grep "link_href" | cut -d\" -f4 | head -n1`
                if [ -n "${id_imdb_temp}" ]; then
                    imdb_id=`curl -sS ${proxy} -A "${agent}" -L "${id_imdb_temp}" | grep -m1 -oE "tt[0-9]{1,15}"`
                fi
            fi
        else
            echo -e ":: Fehler... keine Info von XREL erhalten. Probiers gleich nochmal"
            sleep 2s
            getimdb_xrel
        fi
        sleep 5s
    fi
}

Aufruf

Code:

getimdb_xrel "${release-dirname}"
getimdb_srrdb "${release-dirname}"

Ausgabe

Code:

echo "$imdb_id"

Pakete

Code:

apt install curl python