mad/hosts/hexload.sh
kittykat 83d17967d6
# 2025.02.25 - [mad + allhosts] Re-engineer BadHtml scan to only scan the first 10kb of downloaded partials
# 2025.02.24 - [pixeldrain] Update "The file is IP limited" response handling retry
# 2025.02.22 - [blackcloud_onion] Add bcloud.onion download handling (url fixing)
# 2025.02.21 - [anonfile] Update cdn link parsing to handle new subdomains
# 2025.02.21 - [anonfile] Add download limit reached response handling
# 2025.02.21 - [anonfile] Update file info retrieval (head no longer responds)
# 2025.02.21 - [sendspace] Add sendspace.com as download host
# 2025.02.21 - [oshi / up_oshi] Revert /nossl/ changes for oshi.at (clearnet)
2025-02-26 12:00:57 +00:00

413 lines
18 KiB
Bash

#! Name: hexload.sh
#! Author: kittykat
#! Version: 2024.09.13
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='hex'
HostNick='hexload'
HostFuncPrefix='hex'
HostUrls='hexload.com, hexupload.net'
HostDomainRegex='^(http|https)://(.*\.)?(hexload\.com|hexupload\.net)'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
hex_DownloadFile() {
local remote_url=${1}
local file_url=${1}
local filecnt=${2}
warnAndRetryUnknownError=false
exitDownloadError=false
exitDownloadNotAvailable=false
fileAlreadyDone=false
hexUseDownload="download1"
hexDownload2RetryCnt=0
file_id=$(grep -oP '[^\/]*$' <<< "$file_url")
download_inflight_path="${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 hex_FetchFileInfo $finalAttempt && check_file_extension && hex_GetFile "${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 ----------------- #
#!
hex_FetchFileInfo() {
finalAttempt=$1
hexmaxfetchfileretries=20
bNoNewTorIdent=false
echo -e "${GREEN}# Fetching download url… ${NC}[.] timeout, [-] blocked ip, [*] wait time${NC}"
local bDonePrint=true
for ((j=1; j<=$hexmaxfetchfileretries; j++)); do
if [[ "${bDonePrint}" == "false" ]]; then
printf " ."
fi
bDonePrint=false
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
if [[ "$bNoNewTorIdent" == "true" ]]; then
bNoNewTorIdent=false
else
tor_identity="${RANDOM}"
fi
if grep -Eq "pjscloud.sh" <<< "$LoadPlugins" && [[ "$PJSCloud_hexload" == "true" ]]; then
if [[ "$hexUseDownload" == "download2" ]]; then
form_data="op=download1&id=${file_id}&rand=&usr_login=&fname=&ajax=1&method_free=1&dataType=json"
response=$(pjscloud_tor_request "https://hexload.com/download" "$form_data")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "hex_dwnpage$j" "form_data: ${form_data}"$'\n'"${response}"
fi
else
form_data="op=download1&id=${file_id}&rand=&usr_login=&fname=&ajax=1&method_free=1&dataType=json"
response=$(tor_curl_request --insecure -s --data "$form_data" "https://hexload.com/download")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "hex_dwnpage$j" "form_data: ${form_data}"$'\n'"${response}"
fi
fi
else
if [[ "$hexUseDownload" == "download2" ]]; then
form_data="op=download1&id=${file_id}&rand=&usr_login=&fname=&ajax=1&method_free=1&dataType=json"
response=$(tor_curl_request --insecure -s --data "$form_data" "https://hexload.com/download")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "hex_dwnpage$j" "form_data: ${form_data}"$'\n'"${response}"
fi
else
form_data="op=download2&id=${file_id}&rand=&usr_login=&fname=&ajax=1&method_free=1&dataType=json"
response=$(tor_curl_request --insecure -s --data "$form_data" "https://hexload.com/download")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "hex_dwnpage$j" "form_data: ${form_data}"$'\n'"${response}"
fi
fi
fi
filename=$(echo "$response" | grep -oPi '(?<="file_name":")[^"]+(?=")' | base64 --decode)
download_url=$(echo "$response" | grep -oPi '(?<="link":")[^"]+(?=")' | base64 --decode)
download_url=$(urlencode_spaces "$download_url")
if grep -Eqi "Sorry, you have been blocked" <<< "$response"; then
if ((j == hexmaxfetchfileretries)) ; then
printf "\\n"
echo -e "${YELLOW}| Too many failed attempts${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
printf " -"
bDonePrint=true
continue
fi
fi
if grep -Eqi '<span id="countdown">Wait <span class="seconds">' <<< "$response"; then
hexDownload2RetryCnt=$((hexDownload2RetryCnt + 1))
if ((hexDownload2RetryCnt >=3)); then
printf "\\n"
echo -e "${RED}| Abort: Wait to download button loop detected (x3). File is probably gone.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
wait_time=$(grep -oP '(?<=<span id="countdown">Wait <span class="seconds">).*?(?=</span> seconds.*$)' <<< "$response")
if [[ "$hexUseDownload" == "download1" ]] && grep -Eqi 'name="op" value="download2">' <<< "$response"; then
printf "\\n"
echo -e "${YELLOW}| File uses download2.. switching.${NC}"
hexUseDownload="download2"
fi
bNoNewTorIdent=true
j=0 #Restart
continue
fi
if grep -Eqi '>You have to wait' <<< "$response"; then
if ((j == hexmaxfetchfileretries)) ; then
req_msg=$(grep -oP '(?<=>You have to wait ).*?(?= till next download.*$)' <<< "$response")
req_msg=$(sanitize_html_tags "${req_msg}")
printf "\\n"
echo -e "${YELLOW}| Failed: ${req_msg}.${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "${req_msg}" ""
fi
return 1
elif [[ "$hexUseDownload" == "download1" ]] && grep -Eqi 'name="op" value="download2">' <<< "$response"; then
printf "\\n"
echo -e "${YELLOW}| File uses download2.. switching.${NC}"
hexUseDownload="download2"
bNoNewTorIdent=true
j=0 #Restart
continue
else
printf " *"
bDonePrint=true
continue
fi
fi
if grep -Eqi "No such file|The file you were looking for could not be found" <<< "$response"; then
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi 'class="alert alert-success"' <<< "$response"; then
req_msg=$(grep -oPi '<strong>Whoo!</strong> \K.*$' <<< "${response}")
req_msg=$(sanitize_html_tags "${req_msg}")
printf "\\n"
echo -e "${RED}| Error: ${req_msg}${NC}"
exitDownloadError=true
failedRetryDownload "${remote_url}" "$req_msg" ""
return 1
fi
if [[ "$hexUseDownload" == "download1" ]] && grep -Eqi 'name="op" value="download2">' <<< "$response"; then
printf "\\n"
echo -e "${YELLOW}| File uses download2.. switching.${NC}"
hexUseDownload="download2"
bNoNewTorIdent=true
j=0 #Restart
continue
fi
if [[ -z "$download_url" ]]; then
if ((j == hexmaxfetchfileretries)) ; then
printf "\\n"
echo -e "${RED}| Failed to extract CDN URL${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "Failed to extract CDN URL" ""
fi
return 1
else
continue
fi
fi
if [[ "$filename_override" == "" ]] && [[ -z "$filename" ]] ; then
if ((j == hexmaxfetchfileretries)) ; then
printf "\\n"
echo -e "${RED}| Failed to extract file name${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "ailed to extract file name" ""
fi
return 1
else
continue
fi
fi
break #Good to go here
done
touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
if [[ ! "$filename_override" == "" ]] ; then
filename="$filename_override"
fi
filename=$(sanitize_file_or_folder_name "${filename}")
printf "\\n"
echo -e "${GREEN}| Fetching file info…${NC}"
hexmaxfetchfileretries=4
for ((j=1; j<=$hexmaxfetchfileretries; 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
tor_identity="${RANDOM}"
file_header=$(tor_curl_request --insecure --head -L -s --referer "$file_url" "$download_url")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "hex_head$j" "download_url: ${download_url}"$'\n'"${file_header}"
fi
if ! grep -Eqi 'HTTP/2 200|HTTP/1.1 200|200 OK' <<< $file_header ; then
if ((j < hexmaxfetchfileretries)); then
continue
else
printf "\\n"
echo -e "${RED}| Bad header response…${NC}"
exitDownloadError=true
failedDownload "${remote_url}" "Bad header response (not 200)" ""
return 1
fi
fi
file_size_bytes=$(grep -oPi '(?<=content-length: ).*' <<< "$file_header")
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
if [[ -z $file_size_bytes ]] ; then
if ((j < hexmaxfetchfileretries)); then
printf "\\n"
echo -e "${YELLOW}| Filesize not found… retry${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "Filesize not found" ""
fi
return 1
else
continue
fi
else
file_size_readable="$(numfmt --to=iec --from=auto --format "%.2f" <<< "$file_size_bytes")"
break
fi
done
printf "\\n"
echo -e "${YELLOW}| File name:${NC}\t\"${filename}\""
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]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
hex_GetFile() {
echo -e "${GREEN}# Downloading…"
echo -e "${YELLOW}| File path:${NC}\t./.inflight/${file_path##*/}\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 $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
if [[ "${RateMonitorEnabled}" == "true" ]]; then
tor_curl_request --insecure --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval --referer "$file_url" "$download_url" --continue-at - --output "$file_path"
else
tor_curl_request --insecure --referer "$file_url" "$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" "$file_path" "$((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 ------------------- #
#!