mad/hosts/biteblob.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

377 lines
17 KiB
Bash

#! Name: biteblob.sh
#! Author: kittykat
#! Version: 2024.09.13
#! Desc: Add support for downloading and processing of urls for a new host
#! Usage: Copy this file into the ./${ScriptDir}/hosts/ folder
#!
#!
#! ------------ REQUIRED SECTION ---------------
#! @[UPDATE] HostAndDomainRegexes: This string is loaded into mad.sh and allows dynamic handling of new url data
#! Format: '/HostCode/HostNick/HostFuncPrefix:HostDomainRegex@'
#! HostCode: <aUniqueCodeForHost> (ie. 'fh' for filehaus -- cannot be used by other hosts)
#! HostNick: What is displayed throughout MAD output (ie. 'filehaus' -- "urls.txt has 10 filehaus.." will be displayed)
#! HostFuncPrefix: <aUniqueStringThatMustPrefixHostFunctions> (ie. 'fh' -- fh_DownloadFile(), fh_FetchFileInfo() .. )
#! * Note: Must begin with a letter a-z (functions beginning with numbers are no bueno)
#! HostDomainRegex: The regex used to verify matching urls
HostCode='bite'
HostNick='biteblob'
HostFuncPrefix='bite'
HostUrls='biteblob.com'
HostDomainRegex='^(http|https)://(.*\.)?biteblob\.(com|org)'
#!
#! !! DO NOT UPDATE OR REMOVE !!
#! This merges the Required HostAndDomainRegexes into mad.sh
ListHostAndDomainRegexes=${ListHostAndDomainRegexes}'/'${HostCode}'/'${HostNick}'/'${HostFuncPrefix}'/'${HostUrls}':'${HostDomainRegex}'@'
#!
#!
#! ------------ (1) Host Main Download Function --------------- #
#!
#! @REQUIRED: Host Main Download function
#! Must be named specifically as such:
#! <HostFuncPrefix>_DownloadFile()
bite_DownloadFile() {
local remote_url=${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 bite_FetchFileInfo $finalAttempt && bite_GetFile "${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 ----------------- #
#!
bite_FetchFileInfo() {
finalAttempt=$1
maxfetchretries=5
fixed_url=${remote_url}
if grep -Eqi "biteblob.org" <<< "$fixed_url"; then
fixed_url=${remote_url/biteblob.org/biteblob.com}
fi
if grep -Eqi "biteblob.com/Download/" <<< "$fixed_url"; then
fixed_url=${remote_url/biteblob.com\/Download/biteblob.com\/Information}
fi
download_url=${fixed_url/Information/Download}
echo -e "${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=$(tor_curl_request --insecure -L -s "${fixed_url}")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "bite_dwnpage$j" "url: $fixed_url"$'\n'"${response}"
fi
if [[ -z $response ]] ; then
if [[ $j == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download link${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if grep -Eqi 'Not Found|Invalid Request|Link Unauthorized|No download available|file was removed|file has been deleted' <<< "$response"; then
printf "\\n"
echo -e "${RED}| The file was not found. It could be deleted or expired.${NC}"
exitDownloadError=true
removedDownload "${remote_url}"
return 1
fi
if grep -Eqi '<button id="downloadButton"' <<< "$response"; then
printf "\\n"
echo -e "${GREEN}| Download link found${NC}"
if ! grep -Eqi 'https://biteblob.com/Download/' <<< $download_url ; then
download_loc=$(grep -oP '(?<=onclick="location.href='"'"').*(?='"'"')' <<< "$response")
download_url="https://biteblob.com${download_loc}"
fi
break
fi
if [[ $j == $maxfetchretries ]] ; then
printf "\\n"
echo -e "${RED}| Failed to extract download info (unknown).${NC}"
warnAndRetryUnknownError=true
if [[ "${finalAttempt}" == "true" ]] ; then
failedRetryDownload "${remote_url}" "" ""
fi
return 1
fi
done
echo -e "${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=$(tor_curl_request --insecure --head -L -s "$download_url")
if [[ "${DebugAllEnabled}" == "true" ]] ; then
debugHtml "${remote_url##*/}" "bite_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 "${remote_url}" "" ""
fi
return 1
else
continue
fi
fi
if [[ "$filename_override" == "" ]] ; then
if grep -Eqi 'filename=' <<< "${file_header}" ; then
filename=$(grep -oP 'filename=\K.*$' <<< "${file_header}")
filename=${filename##filename}
filename=${filename//\"/}
filename=${filename//[$'\t\r\n']}
filename=$(trim_string "${filename}")
fi
fi
file_size_bytes=$(grep -oPi '(?<=content-length: ).*' <<< "$file_header")
file_size_bytes=${file_size_bytes//[$'\t\r\n']}
printf "\\n"
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}")
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]/}" > $flockDownload
}
#!
#! ----------- (3) Fetch File / Download File Function --------------- #
#!
bite_GetFile() {
echo -e "${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
if [[ -z $file_size_bytes ]] ; then
echo -e "${BLUE}| No Resume Fetch${NC} (unknown filesize)"
tor_identity="${RANDOM}"
CLEANSTRING=${remote_url//[^a-zA-Z0-9]/}
trap "rm -f ${WorkDir}/.flocks/${CLEANSTRING}; rm -f $flockDownload; echo ""; tput cnorm; exit" 0 1 2 3 6 15
tor_curl_request --insecure --referer "$file_url" "$download_url" --output "$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
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" "$((received_file_size - pd_presize))" ; then
containsHtml=false
else
containsHtml=true
fi
if [[ "$containsHtml" == "true" ]]; then
if grep -Eqi 'was removed|no such file|was deleted|not found|banned' < "$file_path" ; then
printf "\\n"
echo -e "${RED}| The file was not found or has been removed.${NC}"
rm -f "${file_path}"
rm -f "$flockDownload";
removedDownload "${remote_url}" "The file was not found or has been removed."
exitDownloadNotAvailable=true
return 1
fi
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 --insecure --speed-limit $DownloadSpeedMin --speed-time $DownloadTimeoutInterval "$download_url" --continue-at - --output "$file_path"
else
tor_curl_request --insecure --referer "$file_url" "$download_url" --continue-at - --output "$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
fi
done
rm -f "$flockDownload";
ProcessCompletedDownload "$remote_url" "$MoveToFolder" "$filecnt" "$filename" "$file_size_bytes" "$completed_location" "$file_path"
return 0
}
#!
#! --------------- Host Extra Functions ------------------- #
#!