Scraping resilience, metadata tooling, and repository hygiene

Consolidates mosaic and session hardening (login retry, skip processed scans, no retry on 404, started_at), progress reporting (Markdown tables, by-year rollup, rolling-window rate/ETA), and metadata workflow scripts (run_metadata_scan.sh, scan_progress_report.py, export_machine_metadata.py). Adds mosaic reconstruction sample JPEGs referenced by the report. Updates .gitignore for backup/ and .claude/; sample_random_scans helper is documented for branch testing/sample-runs only (see README).
This commit is contained in:
2026-05-14 19:52:53 -04:00
parent 752c278dff
commit 6390f5d529
23 changed files with 788 additions and 188 deletions
+218
View File
@@ -0,0 +1,218 @@
#!/usr/bin/env python3
"""
Report metadata-scan progress and projected completion times for all machines.
Usage:
python scripts/scan_progress_report.py [--archive ARCHIVE_DIR] [--recent N] [--mermaid] [--rate-chart]
Options:
--archive DIR Path to archives directory (default: archives)
--recent N Number of recent files used to compute current rate (default: 500)
--mermaid Also print a Mermaid Gantt chart
--rate-chart Also print a Mermaid XY chart of s/scan rate by hour
"""
import argparse
import glob
import os
import re
import sys
from collections import defaultdict
from datetime import datetime, timedelta
from pathlib import Path
# Canonical machine order and total scan counts (from README inventory, April 2026)
MACHINES = [
("BW1-4 [AMR-15]", 6121),
("BW1-6 [AMR-19]", 18198),
("BW1-7 [AMR-18]", 430),
("BW2-8 [AMR-25]", 8191),
("BW2-10 [AMR-22]", 16537),
("BW2-11 [AMR-23]", 26763),
("BW2-13 [AMR-24]", 13537),
("BW3-16 [AMR-16]", 7325),
("BW3-17 [AMR-20]", 471),
("BW3-19 [AMR-21]", 15186),
("BW3-20 [AMR-26]", 23052),
("BW3-21 [AMR-17]", 10115),
]
TOTAL_SCANS = sum(t for _, t in MACHINES)
def dir_name(label: str) -> str:
return re.sub(r"[^\w\-.]", "_", label).strip("_")
def get_timestamps(machine_dir: Path) -> list[float]:
files = glob.glob(str(machine_dir / "**" / "metadata.json"), recursive=True)
return sorted(os.path.getmtime(f) for f in files)
def print_rate_chart(all_timestamps: list[float]) -> None:
"""Print a Mermaid xychart-beta of average s/scan per hour."""
# One avg rate per hour
bins: dict[str, list[float]] = defaultdict(list)
start_hour: datetime | None = None
for i in range(1, len(all_timestamps)):
gap = all_timestamps[i] - all_timestamps[i - 1]
if gap < 300: # ignore inter-machine gaps
dt = datetime.fromtimestamp(all_timestamps[i])
hour_key = dt.strftime("%m-%d %Hh")
bins[hour_key].append(gap)
if start_hour is None:
start_hour = dt.replace(minute=0, second=0, microsecond=0)
# Drop the last (partial) hour
hours = sorted(bins.keys())
if hours:
hours = hours[:-1]
if not hours or start_hour is None:
print("(not enough data for rate chart)")
return
values = [f"{sum(bins[h])/len(bins[h]):.2f}" for h in hours]
y_max = max(float(v) for v in values)
y_ceil = int(y_max) + 3
n = len(hours)
# Numeric x-axis: Mermaid auto-picks readable tick positions
start_label = start_hour.strftime("%b %d %H:%M")
print("```mermaid")
print("xychart-beta")
print(f' title "Metadata scan rate (s/scan) — hourly, starting {start_label}"')
print(f' x-axis "Hours elapsed" 0 --> {n}')
print(f' y-axis "s / scan" 0 --> {y_ceil}')
print(f" line [{', '.join(values)}]")
print("```")
def fmt_dt(dt: datetime) -> str:
return dt.strftime("%a %b %d %H:%M")
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--archive", default="archives", help="Archives directory")
parser.add_argument("--recent", type=int, default=500,
help="Files used to compute recent rate (default: 500)")
parser.add_argument("--mermaid", action="store_true", help="Print Mermaid Gantt chart")
parser.add_argument("--rate-chart", action="store_true", help="Print Mermaid XY rate-over-time chart")
args = parser.parse_args()
archive = Path(args.archive)
if not archive.is_dir():
sys.exit(f"Archive directory not found: {archive}")
now = datetime.now()
# --- Gather per-machine data ---
machine_data = [] # (label, total, done, first_ts, last_ts)
all_timestamps: list[float] = []
for label, total in MACHINES:
mdir = archive / dir_name(label)
if mdir.is_dir():
times = get_timestamps(mdir)
else:
times = []
done = len(times)
first_ts = datetime.fromtimestamp(times[0]) if times else None
last_ts = datetime.fromtimestamp(times[-1]) if times else None
machine_data.append((label, total, done, first_ts, last_ts, times))
all_timestamps.extend(times)
all_timestamps.sort()
total_done = sum(d for _, _, d, *_ in machine_data)
# --- Rate calculation ---
recent_times = all_timestamps[-args.recent:] if len(all_timestamps) >= 2 else all_timestamps
if len(recent_times) >= 2:
recent_rate = (recent_times[-1] - recent_times[0]) / len(recent_times)
else:
recent_rate = None
if len(all_timestamps) >= 2:
overall_rate = (all_timestamps[-1] - all_timestamps[0]) / len(all_timestamps)
else:
overall_rate = None
rate = recent_rate or overall_rate or 5.0 # fallback
# --- Print timetable ---
print(f"Metadata scan progress — {now.strftime('%Y-%m-%d %H:%M')}")
print(f"Overall rate : {overall_rate:.2f} s/scan" if overall_rate else "Overall rate : n/a")
print(f"Recent rate : {recent_rate:.2f} s/scan (last {args.recent} files)" if recent_rate else "Recent rate : n/a")
print(f"Rate used : {rate:.2f} s/scan")
print(f"Done : {total_done:,} / {TOTAL_SCANS:,} ({100*total_done/TOTAL_SCANS:.1f}%)")
print()
print(f"{'Machine':<20} {'Total':>7} {'Done':>7} {'Pct':>6} {'Completion'}")
print("-" * 68)
cursor = now
gantt_rows: list[tuple[str, datetime, datetime, str]] = [] # label, start, end, status
for label, total, done, first_ts, last_ts, times in machine_data:
pct = 100 * done / total if total else 0
complete = done >= total or (done > 0 and done / total >= 0.999)
if done == 0:
# Not started yet
start = cursor
finish = cursor + timedelta(seconds=total * rate)
status = "pending"
print(f"{label:<20} {total:>7,} {'':>7} {'':>5} {fmt_dt(finish)}")
elif complete:
# Complete — use actual timestamps
start = first_ts
finish = last_ts
status = "done"
print(f"{label:<20} {total:>7,} {done:>7,} {pct:>5.1f}% complete")
else:
# In progress
remaining = total - done
start = first_ts
finish = cursor + timedelta(seconds=remaining * rate)
status = "active"
print(f"{label:<20} {total:>7,} {done:>7,} {pct:>5.1f}% {fmt_dt(finish)} ← in progress")
gantt_rows.append((label, start or cursor, finish, status))
if status != "done":
cursor = finish
print("-" * 68)
print(f"{'All done':<20} {TOTAL_SCANS:>7,} {total_done:>7,} {100*total_done/TOTAL_SCANS:>5.1f}% {fmt_dt(cursor)}")
# --- Mermaid rate chart ---
if args.rate_chart:
print()
print_rate_chart(all_timestamps)
# --- Mermaid Gantt ---
if args.mermaid:
print()
print("```mermaid")
print("gantt")
print(" title Metadata scan progress — all 12 machines")
print(" dateFormat YYYY-MM-DD HH:mm")
print(" axisFormat %b %d")
print()
section = None
for label, start, finish, status in gantt_rows:
prefix = label.split()[0][:3] # BW1, BW2, BW3
if prefix != section:
section = prefix
print(f" section {section}")
safe = label.replace("[", "").replace("]", "").replace(" ", "-")
tag = f"done, " if status == "done" else ("active, " if status == "active" else "")
s = start.strftime("%Y-%m-%d %H:%M")
e = finish.strftime("%Y-%m-%d %H:%M")
print(f" {label} :{tag}{safe}, {s}, {e}")
print("```")
if __name__ == "__main__":
main()