Files
castarr/tools/fetch-crests.py
be-nj f6f6a2499f
All checks were successful
Build TV app / build (push) Successful in 2m49s
Stop the CI from re-fetching crests, cache their URLs instead
Fetching 56 images on every run earned nothing but rate limits, and the
CI artefact is a test build that does not need the badges — the shield
fallback covers it. The resolved image URLs are cached in
tools/crest-sources.json, which is plain text and safe to commit, so a
local run needs one request per club instead of two and can resume after
a rate limit. The artwork itself stays out of the repository.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-26 03:42:49 +02:00

68 lines
2.6 KiB
Python

#!/usr/bin/env python3
"""Downloads club crests into the APK's assets at build time.
The badges are trademarks: they are fetched into a generated, git-ignored
folder so the repository stays free of them while the app ships with them
and needs no network at runtime.
"""
import json
import os
import re
import sys
import time
import urllib.parse
import urllib.request
OUT = sys.argv[1] if len(sys.argv) > 1 else "app/src/main/assets/crests"
URLS = "tools/crest-sources.json"
SRC = "app/src/main/java/dev/castarr/tv/data/TeamFilters.kt"
SUMMARY = "https://de.wikipedia.org/api/rest_v1/page/summary/"
UA = {"User-Agent": "Castarr build script (private use)"}
os.makedirs(OUT, exist_ok=True)
# Image URLs are plain text and safe to commit; the artwork itself is not.
sources = {}
if os.path.exists(URLS):
sources = json.load(open(URLS, encoding="utf-8"))
kotlin = open(SRC, encoding="utf-8").read()
entries = re.findall(r'club\((.*?)\)\s*,\s*(?://.*)?$', kotlin, re.M | re.S)
clubs = []
for raw in re.findall(r'club\(\s*"([^"]+)",\s*"[^"]*",\s*"([^"]+)"[^\n]*', kotlin):
clubs.append(raw)
# an explicit article = "..." wins over the club name
overrides = dict(re.findall(r'club\(\s*"([^"]+)"[^\n]*article = "([^"]+)"', kotlin))
clubs = [(k, overrides.get(k, n)) for k, n in clubs]
fetched = skipped = failed = 0
for key, full_name in clubs:
target = os.path.join(OUT, f"{key}.png")
if os.path.exists(target) and os.path.getsize(target) > 0:
skipped += 1
continue
try:
thumb = sources.get(key)
if not thumb:
url = SUMMARY + urllib.parse.quote(full_name)
with urllib.request.urlopen(urllib.request.Request(url, headers=UA), timeout=20) as r:
thumb = json.load(r).get("thumbnail", {}).get("source")
if not thumb:
raise ValueError("no thumbnail")
sources[key] = thumb.split("?")[0]
thumb = sources[key]
with urllib.request.urlopen(urllib.request.Request(thumb, headers=UA), timeout=20) as r:
data = r.read()
with open(target, "wb") as f:
f.write(data)
fetched += 1
except Exception as exc: # noqa: BLE001 - best effort, shield is the fallback
print(f" {key}: {exc}", file=sys.stderr)
failed += 1
# Wikipedia rate-limits bursts; this runs rarely and caches.
time.sleep(1.2)
with open(URLS, "w", encoding="utf-8") as f:
json.dump(dict(sorted(sources.items())), f, indent=2, ensure_ascii=False)
f.write("\n")
print(f"crests: {fetched} geladen, {skipped} vorhanden, {failed} fehlgeschlagen")