feat: add reels-sync.sh, and dedupe reels-scrape.py against the whole archive

reels-sync.sh is the single-command version of the two-step pipeline:
scrape a profile's reels tab, then fetch and publish whatever's new,
with the same hand-paced settings gdl-cron.sh uses. Takes a bare
username or a full profile URL. Exits clean without touching
gdl-sync.py at all when a profile has nothing new.

Also fixes a real inefficiency in reels-scrape.py's dedup, found by
running the new script twice in a row: checking only the scraped
profile's own directories missed that a shortcode already existed
under its true owner elsewhere in the archive (reposts/collabs by
other tracked accounts), so 9 already-held reels got re-fetched for no
reason. Shortcodes are globally unique, so dedup now checks every
archived profile's listing -- all local requests to the viewer's own
API, never instagram.com, so this costs nothing on the budget that
actually matters. See TOOLING.md for the full story.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011qAds5qr7nZRq5R4yAuxUk

scripts/reels-sync.sh

@@ -0,0 +1,114 @@
+#!/bin/bash
+# The full reels pipeline for one profile: scrape by scrolling the real page,
+# then fetch and publish whatever's new. See TOOLING.md ("Reels: the API is
+# blocked, scrape by scrolling instead") for why this exists at all -- the
+# dedicated reels API is blocked, this drives the actual signed-in browser
+# session instead, and is slower by design.
+#
+# Usage: ./reels-sync.sh <username-or-profile-url>
+#   ./reels-sync.sh zindoriyam
+#   ./reels-sync.sh https://www.instagram.com/zindoriyam/
+#
+# Deliberately NOT wired into gdl-cron.sh or the timers -- see TOOLING.md.
+# Exits non-zero if either step does. Everything is logged.
+set -eu
+
+RAW="${1:?usage: reels-sync.sh <username-or-profile-url>}"
+
+GDL_HOME="${GDL_HOME:-$HOME/gdl}"
+GDL_PYTHON="${GDL_PYTHON:-$HOME/.local/share/pipx/venvs/gallery-dl/bin/python3}"
+INDEX="${GDL_INDEX:-https://instaarchive.ergosteur.com}"
+PUBLISH="${GDL_PUBLISH:-agentapi@10.20.28.200:/volume1/rslsync/sync/Instagram-archive/archives/}"
+
+# Same hand-paced pacing gdl-cron.sh uses -- see its comment for why. Override
+# per-run with GDL_SLEEP_REQUEST etc. if you ever need to, but raise them
+# rather than lower them.
+SLEEP_REQUEST="${GDL_SLEEP_REQUEST:-12 20}"
+SLEEP="${GDL_SLEEP:-5 10}"
+RATE="${GDL_RATE:-500K}"
+SCROLL_PAUSE="${GDL_SCROLL_PAUSE:-2.0 3.5}"
+MAX_IDLE_ROUNDS="${GDL_MAX_IDLE_ROUNDS:-3}"
+
+PATH="$HOME/.local/bin:$PATH"; export PATH
+
+if [ ! -x "$GDL_PYTHON" ]; then
+  echo "reels-scrape.py needs gallery-dl's own pipx venv python (websocket-client" >&2
+  echo "was injected there, not into the system python): $GDL_PYTHON not found" >&2
+  exit 2
+fi
+
+# Same username-from-URL parsing gdl-sync.py already does for --urls-file,
+# reused rather than re-implemented so the two never drift apart.
+PROFILE=$("$GDL_PYTHON" -c "
+import re, sys, importlib.util
+from pathlib import Path
+spec = importlib.util.spec_from_file_location('gdl_sync', Path('$GDL_HOME/gdl-sync.py'))
+gdl = importlib.util.module_from_spec(spec)
+sys.modules['gdl_sync'] = gdl
+spec.loader.exec_module(gdl)
+raw = '$RAW'
+m = gdl.RE_PROFILE_URL.match(raw)
+user = m.group('user') if m else raw.strip('/')
+if not user or '/' in user or ' ' in user:
+    print(f'cannot read a username from {raw!r}', file=sys.stderr)
+    sys.exit(1)
+print(user)
+")
+
+mkdir -p "$GDL_HOME/logs"
+LOG="$GDL_HOME/logs/reels-$PROFILE-$(date +%Y%m%d-%H%M%S)-$$.log"
+URLS_FILE="$GDL_HOME/$PROFILE-reels.txt"
+STAGING="$GDL_HOME/staging-reels-$PROFILE"
+
+echo "=== reels-sync $PROFILE $(date -Is) ===" | tee -a "$LOG"
+
+# The exit status has to survive the pipe into tee -- see gdl-cron.sh's
+# comment on PIPESTATUS for why this needs to be bash, not sh.
+set +e
+"$GDL_PYTHON" "$GDL_HOME/reels-scrape.py" \
+    --profile "$PROFILE" \
+    --index "$INDEX" \
+    --scroll-pause $SCROLL_PAUSE \
+    --max-idle-rounds "$MAX_IDLE_ROUNDS" \
+    --out "$URLS_FILE" 2>&1 | tee -a "$LOG"
+scrape_status=${PIPESTATUS[0]}
+set -e
+
+if [ "$scrape_status" -ne 0 ]; then
+  echo "=== exit $scrape_status (scrape failed) at $(date -Is) ===" | tee -a "$LOG"
+  exit "$scrape_status"
+fi
+
+if [ ! -s "$URLS_FILE" ]; then
+  echo "no new reels for $PROFILE; nothing to fetch" | tee -a "$LOG"
+  echo "=== exit 0 at $(date -Is) ===" | tee -a "$LOG"
+  exit 0
+fi
+
+# Staging is wiped every run on purpose -- same reasoning as gdl-cron.sh: what
+# we already hold is decided by the archive dedupe in reels-scrape.py, not by
+# what happens to be sitting in staging.
+rm -rf "$STAGING"
+
+set +e
+# shellcheck disable=SC2086
+"$GDL_HOME/gdl-sync.py" \
+    --publish "$PUBLISH" \
+    --staging "$STAGING" \
+    --post-urls-file "$URLS_FILE" \
+    --sleep-request $SLEEP_REQUEST \
+    --sleep $SLEEP \
+    --rate "$RATE" \
+    --execute 2>&1 | tee -a "$LOG"
+status=${PIPESTATUS[0]}
+set -e
+
+echo "=== exit $status at $(date -Is) ===" | tee -a "$LOG"
+
+# Keep the log directory from growing without bound -- scoped to this
+# script's own logs so it never touches gdl-cron.sh's rotation.
+ls -1t "$GDL_HOME/logs" | grep '^reels-' | tail -n +30 | while read -r old; do
+  rm -f "$GDL_HOME/logs/$old"
+done
+
+exit "$status"