Ben_Kosytorz
271fb3bf68
- git mv of all existing files into version-python/ (history preserved) - version-rust/: minimal cargo scaffold (edition 2024), no deps yet - root AGENTS.md documents the transition rules and artifact/schema contract - main is untouched; the python layout there stays as-is
39 lines
1.1 KiB
Bash
Executable File
39 lines
1.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
THREAD_ID="${THREAD_ID:-1455993943471820842}"
|
|
OUT_DIR="${OUT_DIR:-$PWD/thread}"
|
|
HTML="$OUT_DIR/export.html"
|
|
URLS="$OUT_DIR/urls.txt" # aria2c input file: one URL per line
|
|
|
|
# Token from env, otherwise prompt (input hidden)
|
|
if [[ -z "${DISCORD_TOKEN:-}" ]]; then
|
|
read -rsp "Discord token: " DISCORD_TOKEN
|
|
echo
|
|
fi
|
|
|
|
mkdir -p "$OUT_DIR"
|
|
|
|
# 1. Export the thread to HTML
|
|
docker run --rm --user "$(id -u):$(id -g)" \
|
|
-v "$OUT_DIR:/out" \
|
|
tyrrrz/discordchatexporter:stable export \
|
|
-t "$DISCORD_TOKEN" -c "$THREAD_ID" -f HtmlDark -o /out/export.html
|
|
|
|
unset DISCORD_TOKEN
|
|
|
|
# 2. Find base64 strings starting with "https://", then decode them
|
|
grep -oP 'aHR0cHM6Ly[89][A-Za-z0-9+/_-]*' "$HTML" \
|
|
| sort -u \
|
|
| while read -r s; do
|
|
s=$(printf '%s' "$s" | tr '_-' '/+' | tr -d '=')
|
|
while (( ${#s} % 4 )); do s="$s="; done
|
|
printf '%s' "$s" | base64 -d 2>/dev/null | tr -d '\r\n' || true
|
|
echo
|
|
done \
|
|
| grep -E '^https://[[:graph:]]+$' \
|
|
| awk '!seen[$0]++' > "$URLS"
|
|
|
|
echo "Found $(wc -l < "$URLS") URLs -> $URLS"
|
|
echo "Download with: aria2c -i \"$URLS\" -d \"$OUT_DIR/downloads\""
|