mad/hosts/innocent.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

254 lines
11 KiB
Bash

#! Name: innocent.sh
#! Author: kittykat
#! Version: 2024.11.29
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='inno'
HostNick='innocent.onion'
HostFuncPrefix='inno'
HostUrls='innocent5z4fg2kdd4y6q4emu5nfybfiyr2mbp7s5pwllf6sqqhqdwyd.onion'
HostDomainRegex='^(http|https)://(.*\.)?innocent5z4fg2kdd4y6q4emu5nfybfiyr2mbp7s5pwllf6sqqhqdwyd\.onion/'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
inno_DownloadFile() {
local remote_url=${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="${WorkDir}/downloads/"
if grep -Eqi 'uploaded=' <<< "$remote_url" ; then
download_url="${remote_url/?uploaded=/dl\/}"
else
download_url="$remote_url"
fi
download_url="${download_url/https:/http:}"
tor_identity="${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 inno_FetchFileInfo $finalAttempt && inno_GetFile "${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/${remote_url//[^a-zA-Z0-9]/}"
}
#!
#! ------------- (2) Fetch File Info Function ----------------- #
#!
inno_FetchFileInfo() {
echo -e "${GREEN}# Fetching file info…${NC}"
download_url=$(urlencode_literal_grouped_case_urlendingonly "$download_url")
maxretries=3
for ((j=1; j<=$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: attempt #$j"
file_header=$(tor_curl_request_extended --insecure --head -L -s "$download_url")
elif ((j % 2 == 0)); then
printf "| Retrieving Head (Get): attempt #$j"
file_header=$(tor_curl_request --insecure -m 16 -s -D - -o /dev/null \
-H "Connection: keep-alive" \
-w 'EffectiveUrl=%{url_effective}' \
"$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 --insecure --head -L -s "$download_url")
fi
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "inno_head$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...${NC}"
continue
fi
fi
if [[ "$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"
elif [[ -z $filename ]] ; then
filename=${download_url##*/}
fi
filename=$(sanitize_file_or_folder_name "${filename}")
if [[ -z "$filename" ]]; then
echo -e "${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/${filename//[^a-zA-Z0-9\.\_\-]/}.flock"
if CheckFileSize "${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]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
inno_GetFile() {
echo -e "${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" "$file_path" | tr -d '[:space:]')
fi
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
if [[ ! -z "$file_size_bytes" ]] ; then
tor_curl_request_extended --insecure "$download_url" --continue-at - --output "$file_path"
else
echo -e "${BLUE}| No Resume Fetch${NC}"
tor_curl_request_extended --insecure "$download_url" --output "$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" "$((received_file_size - pd_presize))" ; then
containsHtml=false
else
containsHtml=true
fi
if [[ "${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
fi
break
done
rm -f "$flockDownload";
ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!