mad/hosts/isupload.sh
kittykat d62376f7a8
# 2025.02.18 - [uploadhive] Add handling of the new /cgi-bin/dl.cgi/ url tickets (WIP)
#               (unfortunately, this is tied to the requesting ip, so downloads get "Wrong IP")
# 2025.02.18 - [up_oshi] Add Manage url as comment on uploads
# 2025.02.18 - [up_oshi / oshi] use /nossl/ url and http
# 2025.02.17 - [gofile] Add a random sleep if 429 response detected (too many requests)
# 2025.02.17 - [*ALL] Audit and update all single bracket operations
# 2025.02.17 - [filehaus] Fix downloading from fh
# 2025.02.15 - [uploadbay] Update urls regex for acceptable alternate
# 2025.02.15 - [up_sendnow] Add send.now as upload host
# 2025.02.15 - [sendnow] Fix handling of filenames with special characters in url
2025-02-19 13:41:07 +00:00

492 lines
22 KiB
Bash

#! Name: isupload.sh
#! Author: kittykat
#! Version: 2025.01.30
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='isup'
HostNick='isupload'
HostFuncPrefix='isup'
HostUrls='isupload.com'
HostDomainRegex='^(http|https)://(.*\.)?isupload\.com'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
isup_DownloadFile() {
local remote_url=${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 isup_FetchFileInfo $finalAttempt && isup_GetFile "${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 ----------------- #
#!
isup_FetchFileInfo() {
finalAttempt=$1
maxfetchretries=5
isup_cookie_jar=""
echo -e "${GREEN}# Fetching download link…${NC}"
for ((i=1; i<=$maxfetchretries; i++)); do
mkdir -p "${WorkDir}/.temp"
isup_cookie_jar=$(mktemp "${WorkDir}/.temp/isup_cookies""${instance_no}"".XXXXXX")
printf " ."
tor_identity="${RANDOM}"
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f "${isup_cookie_jar}"; echo ""; tput cnorm; exit" 0 1 2 3 6 15
response=$(tor_curl_request_extended --insecure -L -s -b "${isup_cookie_jar}" -c "${isup_cookie_jar}" "$remote_url")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "isup_dwnpage$i" "${response}"
fi
if [[ -z $response ]] ; then
rm -f "${isup_cookie_jar}";
if [[ $i == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download link.${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi "Sorry, you are banned" <<< "$response"; then
rm -f "${isup_cookie_jar}";
if [[ $i == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download link.${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi "404 Not Found|File was removed|There is no such file|File was deleted|File not found" <<< "$response"; then
rm -f "${isup_cookie_jar}";
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi 'input type="hidden" name="op" value="' <<< "$response"; then
printf "\\n"
echo -e "${GREEN}| Post link found.${NC}"
post_action="${remote_url//https:/http:}"
post_op=$(grep -oPi '(?<=input type="hidden" name="op" value=").*(?=">)' <<< "$response")
post_id=$(grep -oPi '(?<=input type="hidden" name="id" value=").*(?=">)' <<< "$response")
post_rand=$(grep -oPi '(?<=input type="hidden" name="rand" value=").*(?=">)' <<< "$response")
post_referer=$(grep -oPi '(?<=input type="hidden" name="referer" value=").*(?=">)' <<< "$response")
post_action=$(urlencode_literal_grouped_case_urlendingonly "${post_action}")
fi
if [[ -z "$post_action" ]] || [[ -z "$post_op" ]] || [[ -z "$post_id" ]] ; then
rm -f "${isup_cookie_jar}";
if [[ $i == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download link [2].${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "Failed to extract download link [2]" ""
fi
return 1
else
continue
fi
else
break
fi
done
echo -e "${GREEN}# Fetching download url…${NC}"
for ((i=1; i<=$maxfetchretries; i++)); do
printf " _"
download_url=""
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; echo ""; rm -f $isup_cookie_jar; tput cnorm; exit" 0 1 2 3 6 15
form_data="op=$post_op&id=$post_id&rand=$post_rand&referer=$post_referer&method_free=&method_premium="
response=$(tor_curl_request_extended --insecure -L -s -X POST \
-b "${isup_cookie_jar}" -c "${isup_cookie_jar}" \
--data "$form_data" "$post_action")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "isup_post" "post_action: ${post_action}"$'\n'"form_data: ${form_data}"$'\n'"${response}"
fi
if [[ -z $response ]] ; then
if [[ $i == $maxfetchretries ]] ; then
rm -f "${isup_cookie_jar}";
printf "\\n"
echo -e "${RED}| Failed to extract download link [3].${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
tor_identity="${RANDOM}"
continue
fi
fi
if grep -Eqi '404 Not Found|No such file with this filename|File was deleted|File not found' <<< "$response"; then
rm -f "${isup_cookie_jar}";
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi 'Just a moment...' <<< "$response"; then
if [[ $i == $maxfetchretries ]] ; then
rm -f "${isup_cookie_jar}";
printf "\\n"
echo -e "${RED}| Failed to extract download link [3].${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
tor_identity="${RANDOM}"
continue
fi
fi
if grep -Eqi '<nobr>Filename: <b>' <<< "$response"; then
filename=$(grep -oP -m 1 '(?<=<nobr>Filename: <b>).*?(?=<\/b><\/nobr><br>.*$)' <<< "$response")
fi
if ! grep -Eqi '<a href="http://isupload.com/cgi-bin/dl.cgi/' <<< "$response"; then
printf "\\n"
echo -e "${RED}| Failed to extract download link [4]${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
rm -f "${isup_cookie_jar}";
failedRetryDownload "${remote_url}" "Failed to extract download link [4]" ""
fi
return 1
else
printf "\\n"
echo -e "${GREEN}| Download url found.${NC}"
download_url=$(grep -oP -m 1 '(?<=a href="http://isupload.com/cgi-bin/dl.cgi/).*?(?=">.*$)' <<< "$response")
download_url="${download_url//[$'\t\r\n']}"
download_url='http://isupload.com/cgi-bin/dl.cgi/'$(urlencode_literal_grouped_case_urlendingonly "$download_url")
break
fi
done
rm -f "${isup_cookie_jar}";
echo -e "${GREEN}# Fetching file info…${NC}"
maxretries=3
for ((j=1; j<=$maxretries; j++)); do
mkdir -p "${WorkDir}/.temp"
if ((j > 1)); then
tput rc; tput el;
fi
tput sc
tor_identity="${RANDOM}"
if ((j % 1 == 0)); then
printf "| Retrieving Head (Get): attempt #$j"
file_header=$(tor_curl_request --insecure -m 8 -s -D - -o /dev/null \
-H "Connection: keep-alive" \
-w 'EffectiveUrl=%{url_effective}' \
"$download_url")
elif ((j % 2 == 0)); then
printf "| Retrieving Head: attempt #$j"
file_header=$(tor_curl_request --insecure --head -L -s "$download_url")
elif ((j % 3 == 0)); then
printf "| Retrieving Head (hack): attempt #$j"
rm -f "${WorkDir}/.temp/directhead"
file_header=$(tor_curl_request --insecure --head -H "Connection: keep-alive" -L -s -i "$download_url" |
tee "${WorkDir}/.temp/directhead" &
sleep 6
[ -s "${WorkDir}/.temp/directhead" ]
kill $! 2>/dev/null
)
if [[ ! -f "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}" ]]; then
touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
fi
rm -f "${WorkDir}/.temp/directhead"
else
printf "| Retrieving Head: attempt #$j"
file_header=$(tor_curl_request_extended --insecure --head -L -s "$download_url")
fi
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "isup_head$j" "download_url: ${download_url}"$'\n'"${file_header}"
fi
if [[ ! -z "$file_header" ]] ; then
if grep -Eqi '404 Not Found|' <<< "${file_header}" ; then
printf "\\n"
echo -e "${RED}| Not Found (404). The file has been removed.${NC}"
removedDownload "${remote_url}"
exitDownloadNotAvailable=true
return 1
fi
if ! grep -Eqi 'HTTP/.*200|HTTP/.*302' <<< "${file_header}" ; then
hResponse=$(grep -oPi 'HTTP/.* \K.*$' <<< "${file_header}")
if ((j>=$maxretries)); then
printf "\\n"
echo -e "${RED}| Unexpected header response ($hResponse).${NC}"
return 1
else
printf "\\n"
echo -e "${YELLOW}| Unexpected header response ($hResponse). Retrying...${NC}"
continue
fi
else
break
fi
if [[ "$filename_override" == "" ]] ; then
filename=${download_url##*/}
fi
if grep -Eqi 'Content-Length:' <<< "${file_header}" ; then
file_size_bytes=$(grep -oPi '(?<=content-length: ).*?(?=$)' <<< "$file_header")
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
break
fi
else
if ((j>=$maxretries)); then
printf "\\n"
echo -e "${RED}| No response. Try again later.${NC}"
failedRetryDownload "${remote_url}" "" ""
exitDownloadNotAvailable=true
return 1
else
continue
fi
fi
done
printf "\\n"
touch "${WorkDir}/.flocks/${remote_url//[^a-zA-Z0-9]/}"
if [[ ! "$filename_override" == "" ]] ; then
filename="$filename_override"
fi
filename=$(sanitize_file_or_folder_name "${filename}")
if [[ -z "$filename" ]]; then
printf "\\n"
echo -e "${RED}| Unexpected or no header response.${NC}"
return 1
fi
if [[ -z $file_size_bytes ]] ; then
file_size_readable="${RED}Unknown filesize…${NC}"
else
file_size_readable="$(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/${filename//[^a-zA-Z0-9\.\_\-]/}.flock"
if CheckDownloadExists "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_path" "$completed_location" ; then
return 1
fi
echo "${remote_url//[^a-zA-Z0-9]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
isup_GetFile() {
echo -e "${GREEN}# Downloading…\t${BLUE}(No Resume)${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
if [[ -z $file_size_bytes ]] ; then
echo -e "${BLUE}| No Resume Fetch${NC} (unknown filesize)"
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
tor_curl_request_extended --insecure -L "$download_url" --output "$file_path"
rc=$?
if ((rc != 0 )) ; then
printf "${RED}Download Failed (bad exit status).${NC}"
if [[ -f ${file_path} ]]; then
printf "${YELLOW} Partial removed...${NC}"
printf "\n\n"
rm -f "${file_path}"
else
printf "\n\n"
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
fi
if CheckNoHtml "$remote_url" "$filename" "$file_path" ; then
containsHtml=false
else
containsHtml=true
fi
if [[ "$containsHtml" == "true" ]]; then
echo -e "${YELLOW}Download Failed (contains html)${NC} partial removed..."
rm -f "${file_path}"
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
break
else
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_extended --insecure -L --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval "$download_url" --continue-at - --output "$file_path"
else
tor_curl_request_extended --insecure -L "$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" "$file_path" ; then
containsHtml=false
else
containsHtml=true
fi
downDelta=$(( 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
fi
done
rm -f "$flockDownload";
ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!