#!    Name: tempsh.sh
#!  Author: kittykat
#! Version: 2024.10.11
#!    Desc: Add support for downloading and processing of urls for a new host
#!   Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.."  will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#!   * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='tmpsh'
HostNick='temp.sh'
HostFuncPrefix='tmpsh'
HostUrls='temp.sh'
HostDomainRegex='^(http|https)://(.*\.)?temp\.sh'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
tmpsh_DownloadFile() {
	local remote_url=${1}
	local file_url=${1}
    local filecnt=${2}
    warnAndRetryUnknownError=false
    exitDownloadError=false
    exitDownloadNotAvailable=false
	fileAlreadyDone=false
	download_inflight_path="${WorkDir}/.inflight/"
	mkdir -p "$download_inflight_path"
	completed_location="${WorkDir}/downloads/"
	tor_identity="${RANDOM}"
	finalAttempt="false"
	for ((z=0; z<=$MaxUrlRetries; z++)); do
	    if [[ $z -eq  $MaxUrlRetries ]] ; then
            finalAttempt="true"
	    fi  
        CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
        trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
        if tmpsh_FetchFileInfo $finalAttempt && tmpsh_GetFile "${filecnt}" $((z+1)) $finalAttempt ; then
            return 0
        elif [[ $z -lt $MaxUrlRetries ]]; then
            if [[ "${fileAlreadyDone}" == "true" ]] ; then
                break
            fi
            if [[ "${warnAndRetryUnknownError}" == "true" ]] ; then
                if [[ "${DebugAllEnabled}" == "true" ]] ; then
                    debugHtml "${remote_url##*/}" "error" "Retry due to an unknown issue: attempt #$((z+1)) of ${MaxUrlRetries}"
                fi
            fi
            if [[ "${exitDownloadError}" == "true" || "${exitDownloadNotAvailable}" == "true" ]] ; then
                if [[ "${DebugAllEnabled}" == "true" ]] ; then
                    debugHtml "${remote_url##*/}" "error" "Exit due to unrecoverable issue"
                fi
                rm -f "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
                break
            fi
            echo -e "\n${YELLOW}A recoverable error occurred, retry attempt $((z+1))/${MaxUrlRetries}${NC}"
            sleep 3
        fi
    done
    rm -f "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
}
#!
#! ------------- (2) Fetch File Info Function ----------------- #
#!
tmpsh_FetchFileInfo() {
    finalAttempt=$1
    maxfetchretries=4
    download_url="$remote_url"
    echo -e "${GREEN}# Fetching file info…${NC}"
    for ((j=1; j<=$maxfetchretries; j++)); do
        printf " ."
        CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
        trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
        GetRandomUA
        file_header=$(tor_curl_request --insecure -s -D - -o /dev/null -X POST \
            -H "Connection: keep-alive" \
            -w 'EffectiveUrl=%{url_effective}' \
            "$download_url")
        if [[ "${DebugAllEnabled}" == "true" ]] ; then
            debugHtml "${remote_url##*/}" "tmpsh_posthead" "download_url: ${download_url}"$'\n'"${file_header}"
        fi
		if [[ -z $file_header ]] ; then
		    if [[ $j == $maxfetchretries ]] ; then
                printf "\\n"
                echo -e "${RED}| Failed to extract file info [1]${NC}"
                warnAndRetryUnknownError=true
                if [[ "${finalAttempt}" == "true" ]] ; then
            		failedRetryDownload "${remote_url}" "Failed to extract file info [1]" ""
            	fi
                return 1
            else
                tor_identity="${RANDOM}"
                continue
            fi
		fi
        if grep -Eqi 'HTTP.* 404|Not found|No such file|File was deleted' <<< "$file_header"; then
            printf "\\n"
            echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
            exitDownloadError=true
            removedDownload "${remote_url}"
            return 1
        fi
        if grep -Eqi 'HTTP.* 403|Forbidden|Maximum download limit reached' <<< "$file_header"; then
            printf "\\n"
            echo -e "${RED}| The file is not available. Maximum download limit reached or it was removed.${NC}"
            exitDownloadError=true
            removedDownload "${remote_url}"
            return 1
        fi
        if grep -Eqi 'HTTP.* 200' <<< "$file_header"; then
            printf "\\n"
            echo -e "${GREEN}| File info found.${NC}"
            if [[ "$filename_override" == "" ]] ; then
                filename=$(grep -oPi '(?<=filename=").*(?=")' <<< "$file_header")
                if [[ -z $filename ]]; then                    
                    filename="${download_url##*/}"    
                fi
                if [[ -z "$filename" ]]; then
                    if [[ $j == $maxfetchretries ]] ; then
                        printf "\\n"
                        echo -e "${RED}| Failed to extract file name${NC}"
                        warnAndRetryUnknownError=true
                        if [[ "${finalAttempt}" == "true" ]] ; then
                    		failedRetryDownload "${remote_url}" "Failed to extract file name" ""
                    	fi
                        return 1
                    else
                        continue
                    fi
                fi
            fi
            file_size_bytes=$(grep -oPi '(?<=content-length: ).*?(?=$)' <<< "$file_header")
            file_size_bytes=${file_size_bytes//[$'\t\r\n']}
        else
            err=$(grep -oPi '(?<=HTTP/.* ).*?(?=$)' <<< "$file_header")
	        if [[ $j == $maxfetchretries ]] ; then
                printf "\\n"
                echo -e "${RED}| Failed to get file info. (Code: $err)${NC}"
                warnAndRetryUnknownError=true
                if [[ "${finalAttempt}" == "true" ]] ; then
            		failedRetryDownload "${remote_url}" "Failed to get file info. (Code: $err)" ""
            	fi
                return 1
            else
                tor_identity="${RANDOM}"
                continue
            fi
        fi
        if [[ -z "$file_size_bytes" ]]; then
            if [[ $j == $maxfetchretries ]] ; then
                printf "\\n"
                echo -e "${RED}| Failed to extract file size.${NC}"
                warnAndRetryUnknownError=true
                if [[ "${finalAttempt}" == "true" ]] ; then
            		failedRetryDownload "${remote_url}" "Failed to extract file size." ""
            	fi
                return 1
            else
                tor_identity="${RANDOM}"
                continue
            fi
        fi
        printf "\\n"
        break
    done
    touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
	if [[ ! "$filename_override" == "" ]] ; then
		filename="$filename_override"
	fi
    filename=$(sanitize_file_or_folder_name "${filename}")
    printf "\\n"
    echo -e "${YELLOW}| File name:${NC}\t\"${filename}\""
    if [[ -z $file_size_bytes ]] ; then
        if [[ "${finalAttempt}" == "true" ]] ; then
    		failedRetryDownload "${remote_url}" "Filesize not found!" ""
    	fi
    	echo -e "${YELLOW}| Filesize not found… retry${NC}"
        return 1
    else
        file_size_readable="$(numfmt --to=iec --from=auto --format "%.2f" <<< "$file_size_bytes")"
    fi
    echo -e "${YELLOW}| File size:${NC}\t${file_size_readable}"
    file_path="${download_inflight_path}${filename}"
	flockDownload="${WorkDir}/.flocks/${filename//[^a-zA-Z0-9\.\_\-]/}.flock"
    if CheckFileSize "${remote_url}" "${file_size_bytes}" ; then
        return 1
    fi
    if CheckDownloadExists "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_path" "$completed_location" ; then
        return 1
    fi
	echo "${remote_url//[^a-zA-Z0-9]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
tmpsh_GetFile() {
    echo -e "${GREEN}# Downloading…${NC}"
    echo -e "${YELLOW}| File path:${NC}\t./.inflight/${filename}\n"
    fileCnt=$1
    retryCnt=$2
    finalAttempt=$3
	flockDownload="${WorkDir}/.flocks/${filename//[^a-zA-Z0-9\.\_\-]/}.flock"
    for ((j=1; j<=$MaxDownloadRetries; j++)); do
        pd_presize=0
        if [[ -f "$file_path" ]] ; then
            pd_presize=$(stat --format="%s" "$file_path" | tr -d '[:space:]')
        fi
        GetRandomUA
        tor_identity="${RANDOM}"
	    CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
        trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
        if [[ "${UseTorCurlImpersonate}" == "true" ]]; then
            if [[ "${RateMonitorEnabled}" == "true" ]]; then
                tor_curl_request --insecure -X POST \
        		    --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval \
                    "$download_url" --continue-at - --output "$file_path"
            else
                tor_curl_request --insecure -X POST \
                    "$download_url" --continue-at - --output "$file_path"
            fi
        else
            if [[ "${RateMonitorEnabled}" == "true" ]]; then
                tor_curl_request --insecure -X POST \
                    --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval \
		            -H "User-Agent: $RandomUA" \
                    -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8" \
                    -H "Accept-Language: en-US,en;q=0.5" \
                    -H "Accept-Encoding: gzip, deflate, br" \
                    -H "Connection: keep-alive" \
                    -H "Upgrade-Insecure-Requests: 1" \
                    -H "Sec-Fetch-Dest: document" \
                    -H "Sec-Fetch-Mode: navigate" \
                    -H "Sec-Fetch-Site: same-origin" \
                    -H "Sec-Fetch-User: ?1" \
                    "$download_url" --continue-at - --output "$file_path"
            else
                tor_curl_request --insecure -X POST \
		            -H "User-Agent: $RandomUA" \
                    -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8" \
                    -H "Accept-Language: en-US,en;q=0.5" \
                    -H "Accept-Encoding: gzip, deflate, br" \
                    -H "Connection: keep-alive" \
                    -H "Upgrade-Insecure-Requests: 1" \
                    -H "Sec-Fetch-Dest: document" \
                    -H "Sec-Fetch-Mode: navigate" \
                    -H "Sec-Fetch-Site: same-origin" \
                    -H "Sec-Fetch-User: ?1" \
                    "$download_url" --continue-at - --output "$file_path"
            fi
        fi
        received_file_size=0
        if [[ -f "$file_path" ]] ; then
            received_file_size=$(stat --format="%s" "$file_path" | tr -d '[:space:]')
        fi
        if CheckNoHtml "$remote_url" "$filename" "$file_path" "$((received_file_size - pd_presize))" ; then
            containsHtml=false
        else
            containsHtml=true
        fi
        downDelta=$(( received_file_size - pd_presize ))
        if [[ "${received_file_size}" -ne "${file_size_bytes}" ]] || [[ "$containsHtml" == "true" ]]; then	        
            if [[ "${AutoRepairBadPartials}" == "true" ]] && (( downDelta > 0 && downDelta < 1024 )) ; then
                if [[ -f "${file_path}" ]] ; then
                    if ((pd_presize > 0)); then
                        echo -e "${YELLOW}Bad node / HTML found:${NC} reverting to previous file..."
                        truncateDownload "$remote_url" "$filename" "$pd_presize" "$received_file_size"
                        truncate -s $pd_presize "${file_path}"
                    else
                        echo -e "${YELLOW}Bad node / HTML found:${NC} tainted partial removed..."
                        rm -f "${file_path}"
                    fi
                fi
                if  ((j >= $MaxDownloadRetries)) ; then
                    rm -f "$flockDownload";
                    if [[ "${finalAttempt}" == "true" ]] ; then
                		droppedSizeBadDownload "${remote_url}" "${filename}" "${received_file_size}"
                	fi
                    return 1
	            else
	                continue
	            fi
            elif [[ "${AutoRepairBadPartials}" == "true" ]] && [[ "$containsHtml" == "true" ]] ; then
                if [[ -f "${file_path}" ]] ; then
                    if ((pd_presize > 0)); then
                        echo -e "${YELLOW}Bad node / HTML found:${NC} reverting to previous file..."
                        truncateDownload "$remote_url" "$filename" "$pd_presize" "$received_file_size"
                        truncate -s $pd_presize "${file_path}"
                    else
                        echo -e "${YELLOW}Bad node / HTML found:${NC} tainted partial removed..."
                        rm -f "${file_path}"
                    fi
                fi
                if  ((j >= $MaxDownloadRetries)) ; then
                    rm -f "$flockDownload";
                    if [[ "${finalAttempt}" == "true" ]] ; then
                		droppedSizeBadDownload "${remote_url}" "${filename}" "${received_file_size}"
                	fi
                    return 1
	            else
	                continue
	            fi
            elif (( downDelta > 0 && downDelta < 1024 )) || [[ "$containsHtml" == "true" ]] ; then
                if [[ -f "$file_path" ]] ; then
                    rm -rf "$file_path"
                fi
                echo -e "\n${YELLOW}Bad node / HTML found:${NC} tainted partial removed..."
                if  ((j >= $MaxDownloadRetries)) ; then
                    rm -f "$flockDownload";
                    if [[ "${finalAttempt}" == "true" ]] ; then
                		droppedSizeBadDownload "${remote_url}" "${filename}" "${received_file_size}"
                	fi
                    return 1
	            else
	                continue
	            fi
            fi
            if [[ "${received_file_size}" -ne "${file_size_bytes}" ]]; then
                echo -e "\n${RED}Download failed, file is incomplete.${NC}"
                if  ((j >= $MaxDownloadRetries)) ; then
                    rm -f "$flockDownload";
                    if [[ "${finalAttempt}" == "true" ]] ; then
                		droppedSizeBadDownload "${remote_url}" "${filename}" "${received_file_size}"
                	fi
                    return 1
	            else
	                continue
	            fi
            fi
		else
		    break
        fi
    done
    rm -f "$flockDownload";
    ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
	return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!