378 lines
17 KiB
Bash
Executable file
378 lines
17 KiB
Bash
Executable file
#! Name: kraken.sh
|
||
#! Author: kittykat
|
||
#! Version: 2024.09.22
|
||
#! Desc: Add support for downloading and processing of urls for a new host
|
||
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
|
||
#!
|
||
#!
|
||
#! ------------ REQUIRED SECTION ---------------
|
||
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
|
||
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
|
||
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
|
||
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
|
||
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
|
||
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
|
||
#! HostDomainRegex: The regex used to verify matching urls
|
||
HostCode='kraken'
|
||
HostNick='kraken'
|
||
HostFuncPrefix='kraken'
|
||
HostUrls='krakenfiles.com'
|
||
HostDomainRegex='^(http|https)://(.*\.)?krakenfiles\.com'
|
||
#!
|
||
#! !! DO NOT UPDATE OR REMOVE !!
|
||
#! This merges the Required HostAndDomainRegexes into mad.sh
|
||
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
|
||
#!
|
||
#!
|
||
#! ------------ (1) Host Main Download Function --------------- #
|
||
#!
|
||
#! @REQUIRED: Host Main Download function
|
||
#! Must be named specifically as such:
|
||
#! <HostFuncPrefix>_DownloadFile()
|
||
kraken_DownloadFile() {
|
||
local remote_url=${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 kraken_FetchFileInfo "" $((i+1)) $finalAttempt && kraken_GetFile "${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 ----------------- #
|
||
#!
|
||
kraken_FetchFileInfo() {
|
||
fileCnt=$1
|
||
retryCnt=$2
|
||
finalAttempt=$3
|
||
if grep -Eqi 'krakenfiles.com/download/' <<< "${remote_url}" ; then
|
||
fixed_url=${remote_url/krakenfiles.com\/download\//krakenfiles.com\/view\/}
|
||
else
|
||
fixed_url=${remote_url}
|
||
fi
|
||
if ! grep -Eqi '/file.html' <<< "${fixed_url}" ; then
|
||
fixed_url=${fixed_url}'/file.html'
|
||
fi
|
||
krak_id=${fixed_url%%\/file.htm*}
|
||
krak_id=${krak_id##*\/}
|
||
krak_id=${krak_id//[^a-zA-Z0-9]/}
|
||
echo -e "${GREEN}# Fetching file info…${NC}"
|
||
local num_attempt=$1
|
||
mkdir -p "${WorkDir}/.temp"
|
||
local max_attempts=${CircuitRetries}
|
||
local iter=0 instance_no="$fileCnt" time_out=5 instances="$2" kraken_cookie_jar="" tor_identity="" PAGE="" kraken_token="" kraken_action=""
|
||
mkdir -p "${WorkDir}/.temp"
|
||
for ((i=1; i<=5; i++)); do
|
||
printf " ."
|
||
kraken_cookie_jar=$(mktemp "${WorkDir}/.temp/kraken_cookies""${instance_no}"".XXXXXX")
|
||
tor_identity="${RANDOM}"
|
||
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${kraken_cookie_jar}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
|
||
PAGE=$(tor_curl_request --insecure --max-time "$ConnectTimeout" -s -L -c "${kraken_cookie_jar}" "${fixed_url}")
|
||
if [ "${DebugAllEnabled}" == "true" ] ; then
|
||
debugHtml "${krak_id}" "kraken_token${num_attempt}_$i" "url: ${fixed_url}"$'\n'"krakenid: ${krak_id}"$'\n'"${PAGE}"
|
||
fi
|
||
if grep -Eqi 'sendFormCaptcha()' <<< "${PAGE}"; then
|
||
rm -f "$kraken_cookie_jar";
|
||
printf "\n"
|
||
echo -e "${RED}| Captcha required (Recaptcha)${NC}"
|
||
exitDownloadError=true
|
||
failedRetryDownload "${remote_url}" "Captcha required (Recaptcha)" ""
|
||
return 1
|
||
fi
|
||
if ! grep -Eqi 'name="token" value="' <<< "${PAGE}"; then
|
||
if grep -Eqi 'a page that either has been deleted or never existed' <<< "${PAGE}"; then
|
||
rm -f "$kraken_cookie_jar";
|
||
printf "\n"
|
||
echo -e "${RED}| The file has been deleted or does not exist.${NC}"
|
||
exitDownloadError=true
|
||
removedDownload "${remote_url}"
|
||
return 1
|
||
fi
|
||
if grep -Eqi 'class="alert-danger"' <<< "${PAGE}"; then
|
||
rm -f "$kraken_cookie_jar";
|
||
req_msg=$(grep -oP '(?<=class="alert-danger").*(?=</span>)' <<< "$PAGE")
|
||
req_msg=$(grep -oP '">\K[^>]+' <<< "$req_msg")
|
||
printf "\n"
|
||
echo -e "${RED}| ${req_msg}.${NC}"
|
||
exitDownloadError=true
|
||
failedRetryDownload "${remote_url}" "$req_msg" ""
|
||
return 1
|
||
fi
|
||
if grep -Eqi '521: Web server is down' <<< "${PAGE}"; then
|
||
rm -f "$kraken_cookie_jar";
|
||
printf "\n"
|
||
echo -e "${RED}| 521: Web server is down. Try again later${NC}"
|
||
exitDownloadError=true
|
||
failedRetryDownload "${remote_url}" "521: Web server is down. Try again later" ""
|
||
return 1
|
||
fi
|
||
if grep -Eqi 'Oops! Why you’re here?' <<< "${PAGE}"; then
|
||
rm -f "$kraken_cookie_jar";
|
||
req_msg=$(grep -oP '(?<=nk-error-text">).*(?=</)' <<< "$PAGE")
|
||
printf "\n"
|
||
echo -e "${RED}| ${req_msg}.${NC}"
|
||
exitDownloadError=true
|
||
failedRetryDownload "${remote_url}" "$req_msg" ""
|
||
return 1
|
||
fi
|
||
else
|
||
kraken_token=$(grep -oP 'name="token" value="\K[^"]+' <<< "${PAGE}")
|
||
kraken_action=$(grep -oP 'form action="\K[^"]+' <<< "${PAGE}")
|
||
kraken_action="https://krakenfiles.com/download/${kraken_action##*/}"
|
||
if [[ $kraken_token ]]; then
|
||
if [[ -s kraken_token ]] || [[ -s kraken_action ]] ; then
|
||
continue
|
||
fi
|
||
printf "\n"
|
||
echo -e "${GREEN}| Kraken token found.${NC}"
|
||
break
|
||
fi
|
||
fi
|
||
done
|
||
echo -e "\n# Attempting to get download url"
|
||
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
|
||
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${kraken_cookie_jar}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
|
||
down_request=$(tor_curl_request --insecure -L -s -b "${kraken_cookie_jar}" -c "${kraken_cookie_jar}" -F "token=${kraken_token}" "${kraken_action}")
|
||
if [ "${DebugAllEnabled}" == "true" ] ; then
|
||
debugHtml "${krak_id}" "kraken_url${num_attempt}_1" "action: ${kraken_action}, token: ${kraken_token}"$'\n'"${down_request}"
|
||
fi
|
||
if ! grep -Eqi '"status":"ok"' <<< "${down_request}"; then
|
||
echo -e "${RED}| Failed to get download url${NC}"
|
||
rm -f "$kraken_cookie_jar";
|
||
return 1
|
||
else
|
||
kraken_url=$(grep -oP '"url":"\K[^"]+' <<< "${down_request}")
|
||
download_url=${kraken_url//\\/}
|
||
download_url=${download_url//\/\//\/}
|
||
download_url=$(urlencode_literal_grouped_case_urlendingonly "$download_url")
|
||
echo -e "${GREEN}| Download url found.${NC}"
|
||
fi
|
||
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
|
||
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${kraken_cookie_jar}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
|
||
file_header=$(tor_curl_request --insecure --head -L -s -b "${kraken_cookie_jar}" -c "${kraken_cookie_jar}" --referer "$kraken_action" "$download_url")
|
||
if [ "${DebugAllEnabled}" == "true" ] ; then
|
||
debugHtml "${krak_id}" "kraken_head$j" "download_url: ${download_url}"$'\n'"${file_header}"
|
||
fi
|
||
rm -f "$kraken_cookie_jar";
|
||
if [ ! -z "$file_header" ] ; then
|
||
if grep -Eqi '404 Not Found' <<< "${file_header}" ; then
|
||
echo -e "${RED}| The file has been removed (404).${NC}"
|
||
removedDownload "${remote_url}"
|
||
exitDownloadNotAvailable=true
|
||
return 1
|
||
fi
|
||
if grep -Eqi 'HTTP/2 522|HTTP/1.1 522' <<< $file_header ; then
|
||
echo -e "${RED}| The server returned an error (522).${NC} Try again later.${NC}"
|
||
failedRetryDownload "${remote_url}" "522: The requested resource could not be loaded because the server returned an error. Try again later." ""
|
||
exitDownloadNotAvailable=true
|
||
return 1
|
||
fi
|
||
if ! grep -Eqi 'HTTP/2 200|HTTP/1.1 200|200 OK' <<< $file_header ; then
|
||
echo -e "${RED}| Bad http response.${NC}"
|
||
if [ "${finalAttempt}" == "true" ] ; then
|
||
failedRetryDownload "${remote_url}" "" ""
|
||
fi
|
||
return 1
|
||
fi
|
||
if [ "$filename_override" == "" ] ; then
|
||
if grep -Eqi 'filename=' <<< "${file_header}" ; then
|
||
filename=$(grep -oP 'filename=\K.*$' <<< "${file_header}")
|
||
filename=${filename##filename}
|
||
filename=${filename//\"/}
|
||
filename=${filename//[$'\t\r\n']}
|
||
else
|
||
echo -e "${RED}| Failed to extract file name.${NC}"
|
||
if [ "${finalAttempt}" == "true" ] ; then
|
||
failedRetryDownload "${remote_url}" "" ""
|
||
fi
|
||
return 1
|
||
fi
|
||
fi
|
||
if ! grep -Eqi 'Content-Length' <<< "${file_header}" ; then
|
||
echo -e "${RED}| Failed to extract file size.${NC}"
|
||
if [ "${finalAttempt}" == "true" ] ; then
|
||
failedRetryDownload "${remote_url}" "" ""
|
||
fi
|
||
return 1
|
||
fi
|
||
else
|
||
echo -e "${RED}| No response. Try again later.${NC}"
|
||
if [ "${finalAttempt}" == "true" ] ; then
|
||
failedRetryDownload "${remote_url}" "" ""
|
||
fi
|
||
return 1
|
||
fi
|
||
touch ${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}
|
||
if [ ! "$filename_override" == "" ] ; then
|
||
filename="$filename_override"
|
||
fi
|
||
filename=$(sanitize_file_or_folder_name "${filename}")
|
||
file_size_bytes=$(grep -oPi '(?<=content-length: ).*' <<< "$file_header")
|
||
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
|
||
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}"
|
||
echo -e "${YELLOW}| File name:${NC}\t\"${filename}\""
|
||
flockDownload="${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]/}" > $flockDownload
|
||
}
|
||
#!
|
||
#! ----------- (3) Fetch File / Download File Function --------------- #
|
||
#!
|
||
kraken_GetFile() {
|
||
echo -e "${GREEN}# Downloading…"
|
||
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" "$file_path" | tr -d '[:space:]')
|
||
fi
|
||
GetRandomUA
|
||
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
|
||
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
|
||
if [ "${RateMonitorEnabled}" == "true" ] && [ ! -f "$file_path" ]; then
|
||
tor_curl_request --insecure --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval --referer "$kraken_action" "$download_url" --continue-at - --output "$file_path"
|
||
else
|
||
tor_curl_request --insecure --referer "$kraken_action" "$download_url" --continue-at - --output "$file_path"
|
||
fi
|
||
received_file_size=0
|
||
if [ -f "$file_path" ] ; then
|
||
received_file_size=$(stat --format="%s" "$file_path" | tr -d '[:space:]')
|
||
fi
|
||
if CheckNoHtml "$remote_url" "$filename" "$file_path" ; then
|
||
containsHtml=false
|
||
else
|
||
containsHtml=true
|
||
fi
|
||
downDelta=$(( 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 ------------------- #
|
||
#!
|