mad/hosts/pixeldrain.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

442 lines
21 KiB
Bash

#! Name: pixeldrain.sh
#! Author: kittykat
#! Version: 2025.02.24
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='pd'
HostNick='pixeldrain'
HostFuncPrefix='pd'
HostUrls='pixeldrain.com'
HostDomainRegex='^(http|https)://(.*\.)?pixeldrain\.com'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
pd_DownloadFile() {
local remote_url=${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 pd_FetchFileInfo $finalAttempt && pd_GetFile "${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/${remote_url//[^a-zA-Z0-9]/}"
}
#!
#! ------------- (2) Fetch File Info Function ----------------- #
#!
pd_FetchFileInfo() {
echo -e "${GREEN}# Fetching file info…${NC}"
finalAttempt=$1
vwtoken=""
if grep -Eqi '\?' <<< "${remote_url}" ; then
fixed_url=${remote_url%%\?*}
else
fixed_url=${remote_url}
fi
fileid=${fixed_url##*/}
pdpreviews=0
pdpostviews=0
for ((i=1; i<=5; i++)); do
tor_identity="${RANDOM}"
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
response=$(tor_curl_request --insecure -L -s "https://pixeldrain.com/u/$fileid")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "pd_fetch$i" "$response"
fi
if [[ ! -z "$response" ]] ; then
if grep -q -Eq '"views":' <<< "$response"; then
pdpreviews=$(grep -o -P '(?<="views":).+?(?=,")' <<< "$response")
fi
if grep -i -Eq "You have reached the maximum number of open download connections" <<< "$response"; then
if ((i >= 5)) ; then
printf "\\n"
echo -e "${YELLOW}| Bad node. Reached the maximum number of open download connections…${NC}"
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
printf " ."
continue
fi
fi
if grep -Eqi '404, File Not Found' <<< "$response"; then
if ((i > 1)) ; then
printf "\\n"
fi
echo -e "${RED}| The file has expired or was removed.${NC}"
removedDownload "${remote_url}"
exitDownloadNotAvailable=true
return 1
fi
if grep -Eqi "window.viewer_data" <<< "$response"; then
if ! grep -q -Eqi '"abuse_type":""' <<< "$response"; then
if ((i > 1)) ; then
printf "\\n"
fi
echo -e "${RED}| The file has been reported for abuse and removed.${NC}"
removedDownload "${remote_url}"
exitDownloadNotAvailable=true
return 1
fi
if grep -Eqi "file_rate_limited_captcha_required" <<< "$response"; then
if ((i > 1)) ; then
printf "\\n"
fi
if grep -Eq "pjscloud.sh" <<< "$LoadPlugins" && [[ "$PJSCloud_pixeldrain" == "true" ]]; then
if ! grep -Eq "pjscloud.sh" <<< "$LoadPlugins" ; then
echo -e "${RED}| Pixeldrain viewpump requires pjscloud.sh plugin.${NC}"
failedRetryDownload "${remote_url}" "Captcha Rate Limited (needs view pumping). Requires pjscloud.sh plugin."
return 1
fi
echo -e "| Current views: $pdpreviews"
echo -e "${YELLOW}| The file is rate limited with captcha. Pumping views (will take a minute):${NC}"
cnt_successful_pumps=0
printf " "
for ((k=1; k<=40; k++)); do
if ((k % 3 == 1)); then
printf "${BLUE}_.${NC}"
elif ((k % 3 == 2)); then
printf "${BLUE}~\"${NC}"
else
printf "${NC}(\`${NC}"
fi
pdpostviews=""
tor_identity="${RANDOM}"
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $jsonRequest; echo ""; tput cnorm; exit" 0 1 2 3 6 15
resp_pump=$(pjscloud_tor_request "https://pixeldrain.com/u/$fileid")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "pd_pump$k" "preViews: $pdpreviews"$'\n'"postViews: $pdpostviews"$'\n'"$resp_pump"
fi
if grep -q -Eq 'Error: Forbidden' <<< "$resp_pump"; then
continue
fi
if grep -q -Eq 'statusCode":404|"error":"Not Found"' <<< "$resp_pump"; then
continue
fi
if grep -Eqi 'Views' <<< "$resp_pump"; then
pdpostviews=$(grep -oPi '(?s)Views\K.*?(?=Downloads)' <<< "${resp_pump//[$'\t\r\n']/}")
else
continue
fi
printf "${GREEN} [+]${NC}"
pumpDownload "${remote_url##*/}" "$pdpreviews" "$pdpostviews"
cnt_successful_pumps=$((cnt_successful_pumps + 1))
if ((cnt_successful_pumps >= 1)) ; then
break
fi
done
printf "\\n"
echo -e "| Final views: $pdpostviews (+1)"
echo -e "| Waiting a few seconds to allow pd views to update…"
sleepRandomSecs 45 120
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
return 1
fi
continue
else
echo -e "${RED}| Failed: The file is rate limited with captcha… (needs view pumping)${NC}"
exitDownloadNotAvailable=true
failedRetryDownload "${remote_url}" "Captcha Rate Limited (needs view pumping)" ""
return 1
fi
elif grep -i -Eq "ip_download_limited_captcha_required" <<< "$response"; then
if ((i >= 5)) ; then
printf "\\n"
echo -e "${RED}| Failed: The file is IP limited… (used max bandwidth/48hr, try again later)${NC}"
exitDownloadNotAvailable=true
failedRetryDownload "${remote_url}" "Captcha IP Limited (used max bandwidth/48hr, try again later)" ""
return 1
else
printf " ."
continue
fi
elif ! grep -q -Eqi '"availability":""' <<< "$response"; then
pd_message=$(grep -o -P '(?<="availability":").+?(?=")' <<< "$response")
if ((i > 1)) ; then
printf "\\n"
fi
echo -e "${YELLOW}| Unknown availability: $pd_message${NC}"
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
return 1
fi
fi
fi
if ((i > 1)) ; then
printf "\\n"
fi
echo -e "| Current views: $pdpreviews"
break
else
if ((i >= 5)) ; then
printf "\\n"
echo -e "${YELLOW}| No response…${NC}"
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
printf " ."
continue
fi
fi
done
filename=$(grep -oP '(?<="name":")[^"]+(?=")' <<< "$response")
touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
if [[ ! "$filename_override" == "" ]] ; then
filename="$filename_override"
fi
filename=$(sanitize_file_or_folder_name "${filename}")
if [[ "$filename_override" == "" ]] && [[ -z "$filename" ]] ; then
echo -e "${RED}| Failed to extract file name.${NC}"
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
fi
echo -e "${YELLOW}| File name:${NC}\t\"${filename}\""
for ((i=1; i<=6; i++)); do
pdheadurl="https://pixeldrain.com/api/file/${fileid}"
if [[ "${UsePixeldrainBypass}" == "true" ]]; then
pdheadurl="https://pd.cybar.xyz/$fileid"
fi
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
file_header=$(tor_curl_request --insecure --head -L -s --referer "$file_url" "$pdheadurl")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "pd_head$i" "url: ${pdheadurl}"$'\n'"${file_header}"
fi
if ! grep -Eqi 'HTTP/2 200|HTTP/1.1 200|200 OK' <<< $file_header ; then
if ((i < 6)); then
continue
else
echo -e "${YELLOW}| Filesize not found.${NC}"
return 1
fi
fi
if [[ "${UsePixeldrainBypass}" == "true" ]]; then
download_url=$(grep -oP '(?<=location: ).*$' <<< "$file_header")
download_url="${download_url//[$'\t\r\n']}"
else
download_url="https://pixeldrain.com/api/file/${fileid}"
fi
download_url=$(urlencode_literal_grouped_case_urlendingonly "$download_url")
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}"
break
done
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
if [[ "${UsePixeldrainBypass}" == "true" ]]; then
echo -e "| ${BLUE}PixelDrain bypass:${NC} Knight beds queen ${RED}]${NC}°${PINK}----${RED}[${NC} ♞♝ ${NC}|▀▄▀▄▀▄▀▄▀▄▀▄▀▄▀▄|${NC}"
fi
echo "${remote_url//[^a-zA-Z0-9]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
pd_GetFile() {
echo -e "${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
echo -e "Download Url: $download_url"
GetRandomUA
tor_identity="${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 \
--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 "$file_path"
fi
else
if [[ "${RateMonitorEnabled}" == "true" ]]; then
tor_curl_request --insecure \
-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: none' -H 'Sec-Fetch-User: ?1' \
--speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval \
--referer "$file_url" "$download_url" --continue-at - --output "$file_path"
else
tor_curl_request --insecure \
-H "User-Agent: $RandomUA" \
-H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8' \
-H 'Accept-Language: en-US,en;q=0.5' -H 'Accept-Encoding: gzip, deflate, br' \
-H 'Connection: keep-alive' -H 'Upgrade-Insecure-Requests: 1' -H 'Sec-Fetch-Dest: document' \
-H 'Sec-Fetch-Mode: navigate' -H 'Sec-Fetch-Site: none' -H 'Sec-Fetch-User: ?1' \
--referer "$file_url" "$download_url" --continue-at - --output "$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 ------------------- #
#!