ELO scraper: discover the embed link and retry transient failures

Read the current OneDrive link from the stat-check.com/elo iframe on
each run, falling back to EMBED_URL if the page can't be read or its
link 404s. Retry 429/5xx and network errors up to three times with
backoff, after a one-off 503 from the Badger token endpoint failed a run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-09-22 16:40:45 -05:00
co-authored by Claude Opus 5.5
parent a8cb306f88
commit a6eea9c0ac
4 changed files with 71 additions and 9 deletions
@@ -4,8 +4,10 @@ import html
import json
import re
import sys
import time
import zipfile
from pathlib import Path
from urllib.error import HTTPError, URLError
from urllib.request import Request, urlopen
from xml.etree.ElementTree import iterparse
@@ -16,6 +18,27 @@ NS = {
"pkgrel": "http://schemas.openxmlformats.org/package/2006/relationships",
}
# Seconds to wait before each retry of a transient failure.
RETRY_DELAYS = (5, 15, 45)
def fetch(req: Request) -> bytes:
"""Read a URL, retrying 429/5xx responses and network errors."""
for attempt, delay in enumerate((*RETRY_DELAYS, None), start=1):
try:
with urlopen(req, timeout=60) as resp:
return resp.read()
except HTTPError as e:
if delay is None or not (e.code == 429 or e.code >= 500):
raise
reason = f"HTTP {e.code}"
except (URLError, TimeoutError, ConnectionError) as e:
if delay is None:
raise
reason = str(e)
print(f" {req.full_url.split('?')[0]}: {reason}; retry {attempt} in {delay}s", file=sys.stderr)
time.sleep(delay)
def metadata_download_url(capture_path: Path) -> str:
capture = json.loads(capture_path.read_text())
@@ -29,8 +52,7 @@ def metadata_download_url(capture_path: Path) -> str:
def download(url: str, output: Path) -> None:
req = Request(url, headers={"User-Agent": "Mozilla/5.0"})
with urlopen(req, timeout=60) as resp:
output.write_bytes(resp.read())
output.write_bytes(fetch(req))
def shared_strings(zf: zipfile.ZipFile) -> list[str]: