mad/hosts/nippy.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

393 lines
17 KiB
Bash

#! Name: nippy.sh
#! Author: kittykat
#! Version: 2024.11.28
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='nippy'
HostNick='nippy'
HostFuncPrefix='nippy'
HostUrls='nippyshare.com, nippydrive.com, nippybox.com, nippyfile.com, nippyspace.com'
HostDomainRegex='^(http|https)://(.*\.)?nippy(share|drive|box|file|space)\.(com|me)/'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
nippy_DownloadFile() {
local remote_url=${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 nippy_FetchFileInfo $finalAttempt && nippy_GetFile "${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 ----------------- #
#!
nippy_FetchFileInfo() {
finalAttempt=$1
maxfetchretries=5
nippy_cookie_jar=""
local nippyhost="nippyshare.com"
if grep -Eqi "nippyshare.com" <<< "$remote_url"; then
nippyhost="nippyshare.com"
elif grep -Eqi "nippyshare.me" <<< "$remote_url"; then
nippyhost="nippyshare.me"
elif grep -Eqi "nippydrive.com" <<< "$remote_url"; then
nippyhost="nippydrive.com"
elif grep -Eqi "nippybox.com" <<< "$remote_url"; then
nippyhost="nippybox.com"
elif grep -Eqi "nippyfile.com" <<< "$remote_url"; then
nippyhost="nippyfile.com"
elif grep -Eqi "nippyspace.com" <<< "$remote_url"; then
nippyhost="nippyspace.com"
elif grep -Eqi "yolobit.com" <<< "$remote_url"; then
nippyhost="yolobit.com"
elif grep -Eqi "nofile.org" <<< "$remote_url"; then
nippyhost="nofile.org"
elif grep -Eqi "shareonline.vg" <<< "$remote_url"; then
nippyhost="shareonline.vg"
elif grep -Eqi "dbree.me" <<< "$remote_url"; then
nippyhost="dbree.me"
elif grep -Eqi "dbree.org" <<< "$remote_url"; then
nippyhost="dbree.me"
fi
if grep -Eqi "dbree.org" <<< "$remote_url"; then
fixed_url=${remote_url/dbree.org/dbree.me}
else
fixed_url=${remote_url}
fi
echo -e "${GREEN}# Fetching download link…${NC}"
for ((i=1; i<=$maxfetchretries; i++)); do
mkdir -p "${WorkDir}/.temp"
nippy_cookie_jar=$(mktemp "${WorkDir}/.temp/nippy_cookies""${instance_no}"".XXXXXX")
printf " ."
tor_identity="${RANDOM}"
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${nippy_cookie_jar}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
response=$(tor_curl_request --insecure -L -s -b "${nippy_cookie_jar}" -c "${nippy_cookie_jar}" "$fixed_url")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "nippy_dwnpage$i" "fixed_url: ${fixed_url}"$'\n'"${response}"
fi
if [[ -z $response ]] ; then
rm -f "${nippy_cookie_jar}";
if [[ $i == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download link.${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi "There is no such file|File was deleted because" <<< "$response"; then
rm -f "${nippy_cookie_jar}";
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi "is temporarily unavailable|Please try back later" <<< "$response"; then
rm -f "${nippy_cookie_jar}";
if ((i == maxfetchretries)) ; then
printf "\\n"
echo -e "${RED}| Download is temporarily unavailable. Try again later.${NC}"
exitDownloadError=true
failedRetryDownload "${remote_url}" "Download is temporarily unavailable. Try again later."
return 1
else
continue
fi
fi
if grep -Eqi '<h2><a href='\''//'"${nippyhost}"'/d/' <<< "$response"; then
printf "\\n"
echo -e "${GREEN}| Download url found.${NC}"
download_url="https:"$(grep -oP '(?<=<h2><a href='\'').*(?='\'' class=)' <<< "$response")
break
fi
if ((i == maxfetchretries)) ; then
rm -f "${nippy_cookie_jar}";
printf "\\n"
echo -e "${RED}| Failed to extract download url (unknown).${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
rm -f "${nippy_cookie_jar}";
continue
fi
done
echo -e "${GREEN}# Fetching file info…${NC}"
filename=""
file_size_bytes=""
cdn_url=""
if [[ ! "$filename_override" == "" ]] ; then
filename="$filename_override"
fi
for ((j=1; j<=$maxfetchretries; j++)); do
printf " ."
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${nippy_cookie_jar}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
file_header=$(tor_curl_request --insecure -L --head -s \
-b "${nippy_cookie_jar}" -c "${nippy_cookie_jar}" \
"$download_url")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "nippy_head$j" "FileInfoUrl: ${download_url}"$'\n'"${file_header}"
fi
if [[ -z $file_header ]] ; then
if [[ $j == $maxfetchretries ]] ; then
rm -f "${nippy_cookie_jar}";
printf "\\n"
echo -e "${RED}| Failed to extract file info${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "Failed to extract file info" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi 'HTTP.* 404' <<< $file_header ; then
printf "\\n"
echo -e "${RED}| 404 Not Found (file removed)${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if ! grep -Eqi 'HTTP.* 200' <<< $file_header ; then
if [[ $j == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract file info${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "Failed to extract file info" ""
fi
return 1
else
continue
fi
fi
if [[ -z "$cdn_url" ]] ; then
cdn_url="https:"$(grep -oP '(?<=location: ).*$' <<< "$file_header")
cdn_url=${cdn_url//[$'\t\r\n']}
fi
if [[ -z $filename ]]; then
filename=$(grep -oPi '(?<=filename=").*(?=")' <<< "$file_header")
fi
if [[ -z $file_size_bytes ]] ; then
file_size_bytes=$(grep -oPi '(?<=content-length: ).*' <<< "$file_header")
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
fi
if [[ -z $filename ]] || [[ -z "$cdn_url" ]] || [[ -z "$file_size_bytes" ]] ; then
if [[ $j == $maxfetchretries ]] ; then
rm -f "${nippy_cookie_jar}";
printf "\\n"
echo -e "${RED}| Failed to extract file info.${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
break #Good to go here
done
download_url="$cdn_url"
touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
filename=$(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]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
nippy_GetFile() {
echo -e "${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" "$file_path" | tr -d '[:space:]')
fi
GetRandomUA
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f ${nippy_cookie_jar}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
if [[ "${RateMonitorEnabled}" == "true" ]]; then
tor_curl_request --insecure -L --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval \
"$download_url" --continue-at - --output "$file_path"
else
tor_curl_request --insecure -L "$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 "$flockDownload";
rm -f "${nippy_cookie_jar}";
ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!