cross-posted from: https://lemm.ee/post/23155648

> Here is the script. > > > #!/usr/bin/env bash > # Download and search youtube subs > # deps yt-dlp ,awk, perl, any one or more of either ugrep, ripgrep, grep > # usage "script youtube_url" > > > main() { > url="$@" > check_if_url > get_video_id > search_for_downloaded_matching_files > set_download_boolean_flag > download_subs > read_and_format_transcript_file > echo_description_file > user_search > } > > > # Iterate over the array and add items to the new array if they match the regex > check_if_url() { > local regex='^https://[^[:space:]]+$' > if ! [[ $url =~ $regex ]]; then > echo "Invalid input. Valid input is a url matching regex ${regex}" > exit 1 > fi > } > > > get_video_id() { > video_id=$(echo "$url" | sed -n 's/.*v=\([^&]*\).*/\1/p') > } > > > search_for_downloaded_matching_files() { > # Find newest created files matching the video_id > transcript_file="$( /usr/bin/ls -t --time=creation "$PWD"/*${video_id}*\.vtt 2>/dev/null | head -n 1 )" > description_file="$( /usr/bin/ls -t --time=creation "$PWD"/*${video_id}*\.description 2>/dev/null | head -n 1 )" > } > > > set_download_boolean_flag() { > if [ -n "$transcript_file" ] && [ -n "$description_file" ]; then > download=0 # FALSE > else > download=1 # TRUE > fi > } > > > download_subs() { > if [ "$download" -eq 1 ]; then > yt-dlp --restrict-filenames --write-auto-sub --skip-download "${url}" > yt-dlp --restrict-filenames --sub-langs=eng --write-subs --skip-download "${url}" > yt-dlp --restrict-filenames --write-description --skip-download "${url}" > # Search files again since they were just downloaded > search_for_downloaded_matching_files > fi > } > > > read_and_format_transcript_file() { > perl_removed_dupes="$(perl -0777 -pe 's/^\d\d.*\n.*\n.*<\/c>//gm' <"${transcript_file}")" > local prefix="https://www.youtube.com/watch?v=${video_id}&t=" > local suffix="s" > formated_transcript_file="$(awk -v pre="$prefix" -v suf="$suffix" ' > /^([0-9]{2}:){2}[0-9]{2}\.[0-9]{3}/ { > split($1, a, /[:.]/); > $1 = pre (int(a[1]*3600 + a[2]*60 + a[3]) - 3) suf; > sub(/ --> [0-9]{2}:[0-9]{2}:[0-9]{2}\.[0-9]{3}/, ""); > sub(/ align:start position:0%$/, ""); > print; > next; > } > { > sub(/ align:start position:0%$/, ""); > print; > } > ' <<<"${perl_removed_dupes}")" > #CRLF for ugrep to avoid ?bug? where before lines are not all outputted > formated_transcript_file_CRLF=$(printf '%b' "$formated_transcript_file" | sed 's/$/\r/') > } > > > echo_description_file() { > cat "${description_file}" > } > > > user_search() { > echo -e "\n\n" > read -rp "Enter regex (read as raw input): " search_term > > : ${app_count:=0} > > if command -v ug >/dev/null 2>&1; then > echo -e "\n\n\n\n" > echo "Ugrep output" > ug --pretty=never -B2 -A1 -i -Z+-~1 -e "${search_term}" --andnot "^https?:\/\/" <<<"$formated_transcript_file_CRLF" > ((app_count++)) > fi > > if command -v rg >/dev/null 2>&1; then > echo -e "\n\n\n\n" > echo "Ripgrep output" > rg -iP -B2 -A7 "^(?!https?:\/\/).*\K${search_term}" <<<"$formated_transcript_file" > ((app_count++)) > fi > > if [ "$app_count" -eq 0 ]; then > echo -e "\n\n\n\n" > echo "Grep output" > grep -iP -B2 -A1 "${search_term}" <<<"$formated_transcript_file" > echo -e "\n\n" > echo "Consider installing ripgrep and ugrep for better search" > ((app_count++)) > fi > } > > > main "$@" > > > >

Here is the script. ```

#!/usr/bin/env bash

Download and search youtube subs

deps yt-dlp ,awk, perl, any one or more of either ugrep, ripgrep, grep

usage "script youtube_url"

main() { url="$@" check_if_url get_video_id search_for_downloaded_matching_files set_download_boolean_flag download_subs read_and_format_transcript_file echo_description_file user_search }

Iterate over the array and add items to the new array if they match the regex

check_if_url() { local regex='^https://[[:space:]]+$' if ! [[ $url =~ $regex ]]; then echo "Invalid input. Valid input is a url matching regex ${regex}" exit 1 fi }

get_video_id() { video_id=$(echo "$url" | sed -n 's/.v=\([^&]\).*/\1/p') }

search_for_downloaded_matching_files() { # Find newest created files matching the video_id transcript_file="$( /usr/bin/ls -t --time=creation "$PWD"/${video_id}\.vtt 2>/dev/null | head -n 1 )" description_file="$( /usr/bin/ls -t --time=creation "$PWD"/${video_id}\.description 2>/dev/null | head -n 1 )" }

set_download_boolean_flag() { if [ -n "$transcript_file" ] && [ -n "$description_file" ]; then download=0 # FALSE else download=1 # TRUE fi }

download_subs() { if [ "$download" -eq 1 ]; then yt-dlp --restrict-filenames --write-auto-sub --skip-download "${url}" yt-dlp --restrict-filenames --sub-langs=eng --write-subs --skip-download "${url}" yt-dlp --restrict-filenames --write-description --skip-download "${url}" # Search files again since they were just downloaded search_for_downloaded_matching_files fi }

read_and_format_transcript_file() { perl_removed_dupes="$(perl -0777 -pe 's/^\d\d.\n.\n.*<\/c>//gm' <"${transcript_file}")" local prefix="https://www.youtube.com/watch?v=${video_id}&t=" local suffix="s" formated_transcript_file="$(awk -v pre="$prefix" -v suf="$suffix" ' /^([0-9]{2}:){2}[0-9]{2}\.[0-9]{3}/ { split($1, a, /[:.]/); $1 = pre (int(a[1]*3600 + a[2]*60 + a[3]) - 3) suf; sub(/ --> [0-9]{2}:[0-9]{2}:[0-9]{2}\.[0-9]{3}/, ""); sub(/ align:start position:0%$/, ""); print; next; } { sub(/ align:start position:0%$/, ""); print; } ' <<<"${perl_removed_dupes}")" #CRLF for ugrep to avoid ?bug? where before lines are not all outputted formated_transcript_file_CRLF=$(printf '%b' "$formated_transcript_file" | sed 's/$/\r/') }

echo_description_file() { cat "${description_file}" }

user_search() { echo -e "\n\n" read -rp "Enter regex (read as raw input): " search_term

: ${app_count:=0}

if command -v ug >/dev/null 2>&1; then echo -e "\n\n\n\n" echo "Ugrep output" ug --pretty=never -B2 -A1 -i -Z+-~1 -e "${search_term}" --andnot "^https?:\/\/" <<<"$formated_transcript_file_CRLF" ((app_count++)) fi

if command -v rg >/dev/null 2>&1; then echo -e "\n\n\n\n" echo "Ripgrep output" rg -iP -B2 -A7 "^(?!https?:\/\/).*\K${search_term}" <<<"$formated_transcript_file" ((app_count++)) fi

if [ "$app_count" -eq 0 ]; then echo -e "\n\n\n\n" echo "Grep output" grep -iP -B2 -A1 "${search_term}" <<<"$formated_transcript_file" echo -e "\n\n" echo "Consider installing ripgrep and ugrep for better search" ((app_count++)) fi }

main "$@"

```

I made a script that downloads from youtube super fast using a custom aria2 build.

Aria2 https://github.com/P3TERX/Aria2-Pro-Core/releases

ffmpeg build https://github.com/yt-dlp/FFmpeg-Builds/releases

I choose ffmpeg-master-latest-linux64-gpl.tar.xz

``` #!/usr/bin/env bash #set -x

if [[ -z $@ ]]; then echo "specify download url" exit fi

dir_dl="$PWD" url="$@"

ffmpeg_dir="$HOME/.local/bin.notpath/" download_archive_dir="$HOME/Videos/yt-dlp/" download_archive_filename=".yt-dlp-archived-done.txt"

mkdir -p "$download_archive_dir"

youtube_match_regex='^.(youtube[.]com|youtu[.]be|youtube-nocookie[.]com).$'

if [[ "$1" =~ $youtube_match_regex ]]; then url="$(echo "$@" | perl -pe 's/((?:http:|https:)?\/\/(?:www\.|)(?:youtube\.com|m\.youtube\.com|youtu\.|#youtube-nocookie\.com).(?:c(?:hannel)?\/|u(?:ser)?\/|v=|v%3D|v\/|(?:a|p)\/(?:a|u)\/\d.\/|watch\?|vi(?:=|\/)|\/#embed\/|oembed\?|be\/|e\/)([^&amp;?%#\/\n]+))./$1/gm')" yt-dlp \ --check-formats \ --clean-info-json \ --download-archive "$download_archive_dir$download_archive_filename" \ --embed-chapters \ --embed-info-json \ --embed-metadata \ --embed-thumbnail \ --external-downloader aria2c \ --downloader-args \ "aria2c: \ --allow-piece-length-change=true \ --check-certificate=false \ --console-log-level=notice \ --content-disposition-default-utf8=true \ --continue=true \ --disk-cache=8192 \ --download-result=full \ --enable-mmap \ --file-allocation=falloc \ --lowest-speed-limit=100K \ --max-concurrent-downloads=16 \ --max-connection-per-server=64 \ --max-mmap-limit=8192M \ --max-resume-failure-tries=5 \ --max-file-not-found=2 \ --max-tries=3 \ --min-split-size=64K \ --no-file-allocation-limit=8192M \ --piece-length=64k \ --realtime-chunk-checksum=false \ --retry-on-400=true \ --retry-on-403=true \ --retry-on-406=true \ --retry-on-unknown=true \ --retry-wait=1 \ --split=32 \ --stream-piece-selector=geom \ --summary-interval=0 " \ --ffmpeg-location "$ffmpeg_dir" \ --output "$dir_dl"'/%(channel)s/%(title)s_%(channel)s_%(upload_date>%Y-%m-%d)s_%(duration>%H-%M-%S)s_%(resolution)s.%(ext)s' \ --prefer-free-formats \ --remux-video mkv \ --restrict-filenames \ --sponsorblock-remove "filler,interaction,intro,music_offtopic,outro,preview,selfpromo,sponsor" \ --sub-langs "en.*,live_chat" \ --write-auto-subs \ --write-description \ --write-info-json \ --write-playlist-metafiles \ --write-subs \ --write-thumbnail \ "$url" else yt-dlp \ --download-archive "$download_archive_dir$download_archive_filename" \ --embed-chapters \ --ffmpeg-location "$ffmpeg_dir" \ --http-chunk-size 10M \ --output "$dir_dl/%(title)s_%(duration>%H-%M-%S)s_%(upload_date>%Y-%m-%d)s_%(resolution)s_URL_(%(id)s).%(ext)s" \ --prefer-free-formats \ --restrict-filenames \ "$url" fi

```

I bought a 15.36TB SSD SAMSUNG PM1633A SAS MZ-ILS15TA DELL EMC MZ1LS15THMLS-000D4

I am trying to figure out what to buy in order to connect it to my desktop PC via PCIE. Is this a viable or recommended solution?

SFF-8643 to SFF-8639 cable

Dell LSI 9311-8i 8-port Internal 12G SAS PCle x8 Host Bus RAID Adapter 3YDX4