mad/hosts/uploadhive.sh
kittykat eeb8054960
# 2025.01.14 - [gagneux / up_gagneux] Add fichier.gagneux.info as upload / download host
# 2025.01.14 - [uwabaki] Add uwabaki.party as download host
# 2025.01.14 - [fileblade] Additional retries and handling for blocked Tor ips (until alternative)
# 2025.01.13 - [ocr_captcha] Create imagemagick OCR function for testing without tesseract
# 2025.01.13 - [anonfile, dailyuploads] Update ocr call to use tesseract function
# 2025.01.13 - [up_anonfile] Modify to use new upload url
# 2025.01.12 - [ateasystems] Update 404 Not found response
# 2025.01.11 - [mad] Update direct head response handling
# 2025.01.11 - [ranoz] Add 404 Not found handling on head
# 2025.01.09 - [ranoz] Add handling of "NEXT_NOT_FOUND" response
# 2025.01.09 - [fileblade] Fix cdn url parsing
# 2025.01.08 - [up_pixeldrain] Fix success response from pixeldrain
# 2025.01.08 - [ramsgaard / up_ramsgaard] Add data.ramsgaard.me as upload / download host
# 2025.01.08 - [euromussels / up_euromussels] Add uploads.euromussels.eu as upload / download host
# 2025.01.07 - [up_fileland] Add fileland.io as upload host
# 2025.01.07 - [up_fireget] Add fireget.com as upload host
# 2025.01.06 - [uploadhive] Update the removed / gone response detection
# 2025.01.06 - [fileblade] Add "user does not allow free downloads over 100MB" response (and warnings)
# 2025.01.06 - [desiupload] Add desiupload as download host
# 2025.01.05 - [isupload] Fix filename detection
2025-01-16 07:54:05 +00:00

428 lines
19 KiB
Bash

#! Name: uploadhive.sh
#! Author: kittykat
#! Version: 2025.01.06
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='uhive'
HostNick='uploadhive'
HostFuncPrefix='uhive'
HostUrls='uploadhive.com'
HostDomainRegex='^(http|https)://(.*\.)?uploadhive\.com'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
uhive_DownloadFile() {
local remote_url=${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 uhive_FetchFileInfo $finalAttempt && uhive_GetFile "${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 ----------------- #
#!
uhive_FetchFileInfo() {
finalAttempt=$1
maxfetchretries=5
echo -e "${GREEN}# Fetching download link…${NC}"
for ((j=1; j<=$maxfetchretries; j++)); do
mkdir -p "${WorkDir}/.temp"
printf " ."
tor_identity="${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=$(tor_curl_request --insecure -L -s "$remote_url")
if [ "${DebugAllEnabled}" == "true" ] ; then
debugHtml "${remote_url##*/}" "uhive_dwnpage$j" "${response}"
fi
if [[ -z $response ]] ; then
if [ $j == $maxfetchretries ] ; then
printf "\\n"
echo -e "${RED}| Failed to extract post link.${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi "File Not Found|could not be found|file was removed|404 Not Found" <<< "$response"; then
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi 'input type="hidden" name="id" value="' <<< "$response"; then
printf "\\n"
echo -e "${GREEN}| Post link found.${NC}"
post_op=$(grep -oP '(?<=input type="hidden" name="op" value=").*(?=">)' <<< "$response")
post_id=$(grep -oP '(?<=input type="hidden" name="id" value=").*(?=">)' <<< "$response")
post_rand=$(grep -oP '(?<=input type="hidden" name="rand" value=").*(?=">)' <<< "$response")
post_referer=$(grep -oP '(?<=input type="hidden" name="referer" value=").*(?=">)' <<< "$response")
break
fi
if [ $j == $maxfetchretries ] ; then
printf "\\n"
echo -e "${RED}| Failed to extract post link (unknown).${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
fi
done
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; tput cnorm; exit" 0 1 2 3 6 15
form_data="op=${post_op}&id=${post_id}&rand=${post_rand}&referer=${post_referer}&method_free=&method_premium="
response=$(tor_curl_request --insecure -L -s -X POST --data "$form_data" "$remote_url")
if [ "${DebugAllEnabled}" == "true" ] ; then
debugHtml "${remote_url##*/}" "uhive_post" "${response}"
fi
if [[ -z $response ]] ; then
echo -e "${RED}| Failed to extract download link [1]${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "Failed to extract download link [1]" ""
fi
return 1
fi
if grep -Eqi "There is no such file." <<< "$response"; then
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi 'Error happened when generating Download Link' <<< "$response"; then
err=$(grep -oP '(?<=Error happened when generating Download Link.<br>).*(?=</font>.*$)' <<< "$response")
echo -e "${RED}| Error happened when generating Download Link.${NC}"
echo -e "(error: $(sanitize_html_tags "${err}"))"
exitDownloadError=true
failedRetryDownload "${remote_url}" "Error happened when generating Download Link" $(sanitize_html_tags "${err}")
return 1
fi
if grep -Eqi '<span id="direct_link"' <<< "$response"; then
echo -e "${GREEN}| Download link found.${NC}"
download_url=$(grep -oP '(?<=<a href=").*(?=.*uploadhive.com/files/).*(?=">)' <<< "$response")
filename=${download_url##*/}
else
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "The file was not found. It could be deleted or expired" ""
fi
return 1
fi
if [[ -z $download_url ]] ; then
echo -e "${RED}| Failed to extract download link [2]${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "Failed to extract download link [2]" ""
fi
return 1
fi
echo -e "${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
file_header=$(tor_curl_request --insecure --head -s -L --referer "$remote_url" "$download_url")
if [ "${DebugAllEnabled}" == "true" ] ; then
debugHtml "${remote_url##*/}" "uhive_head$j" "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.${NC}"
warnAndRetryUnknownError=true
if [ "${finalAttempt}" == "true" ] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if ! grep -Eqi 'HTTP/2 200|HTTP/1.1 200|200 OK' <<< $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 "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
file_size_bytes=$(grep -oPi '(?<=content-length: ).*' <<< "$file_header")
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
if [[ -z "$file_size_bytes" ]]; then
if [ $j == $maxfetchretries ] ; then
printf "\\n"
echo -e "${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
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]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
uhive_GetFile() {
echo -e "${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" "$file_path" | tr -d '[:space:]')
fi
GetRandomUA
tor_identity="${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 -L -G --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval "$download_url" --continue-at - --output "$file_path"
else
tor_curl_request --insecure -L -G "$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 "$flockDownload";
if grep -Eqi '^.*--7_\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming 7z)...${NC}"
origext="7z"
mv "$file_path" "${file_path%\--7_*}.$origext"
filename="${filename%\--7_*}.$origext"
file_path="${file_path%\--7_*}.$origext"
elif grep -Eqi '^.*--z_\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming zip)...${NC}"
origext="zip"
mv "$file_path" "${file_path%\--z_*}.$origext"
filename="${filename%\--z_*}.$origext"
file_path="${file_path%\--z_*}.$origext"
elif grep -Eqi '^.*_-p.*--r_\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming mp rar)...${NC}"
origext="rar"
partnum="${filename##*_-p}"
partnum="${partnum%--r_*}"
newfilepath="${file_path%_-p*}.part${partnum}.$origext"
mv "$file_path" "$newfilepath"
filename="${newfilepath##*/}"
file_path="${newfilepath}"
elif grep -Eqi '^.*--r_\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming rar)...${NC}"
origext="rar"
mv "$file_path" "${file_path%--r_*}.$origext"
filename="${filename%--r_*}.$origext"
file_path="${file_path%--r_*}.$origext"
elif grep -Eqi '^.*--t_\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming tar)...${NC}"
origext="tar"
mv "$file_path" "${file_path%--t_*}.$origext"
filename="${filename%--t_*}.$origext"
file_path="${file_path%--t_*}.$origext"
elif grep -Eqi '^.*_-7--..._\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming)...${NC}"
origext=${filename##*--}
origext=${origext%_*}
newfilepath="${file_path%--*}.$origext"
newfilepath="${newfilepath//_-7/.7z}"
mv "$file_path" "$newfilepath"
filename="${newfilepath##*/}"
file_path="${newfilepath}"
elif grep -Eqi '^.*--..._\....$' <<< "$filename" ; then
echo -e ""
echo -e "${BLUE}| Found mad upload random extension file (renaming)...${NC}"
origext=${filename##*--}
origext=${origext%_*}
mv "$file_path" "${file_path%--*}.$origext"
filename="${filename%--*}.$origext"
file_path="${file_path%--*}.$origext"
fi
ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!