Buckets:

download
raw
3.53 kB
#!/usr/bin/env python3
"""Snapshot the repository's public counts into ``data/github.json``.
The site shows stars, forks and contributors in three places. It reads them from
the GitHub API in the visitor's browser, which is the right source but not a
reliable one: the unauthenticated API allows 60 requests an hour per address, and
a visitor who is over that limit, offline, or behind something that blocks the
call used to see zeros — or, in the hero, nothing at all.
This writes the last known-good figures to a file the site ships, so the counts
render before the network answers and stay rendered if it never does. The live
lookup still wins whenever it succeeds; this is only the floor.
python scripts/gen_github_data.py # write data/github.json
python scripts/gen_github_data.py --stdout # print, write nothing
Unlike ``gen_site_data.py`` this one needs the network, so it is deliberately a
separate script: ``gen_site_data.py --check`` stays offline and deterministic.
Re-run this when the numbers are worth refreshing; nothing breaks if it is stale.
"""
from __future__ import annotations
import argparse
import json
import re
import sys
import urllib.request
from datetime import datetime, timezone
from pathlib import Path
REPO = Path(__file__).resolve().parent.parent
OUT = REPO / "data" / "github.json"
SLUG = "ctrl-gaurav/effGen"
API = "https://api.github.com"
def _get(url: str):
request = urllib.request.Request(
url, headers={"Accept": "application/vnd.github+json", "User-Agent": "effgen-site-build"}
)
with urllib.request.urlopen(request, timeout=30) as response:
return json.loads(response.read()), dict(response.headers)
def contributors_count() -> int:
"""Total contributors, read off the pagination header.
Asking for one per page makes the last page number the total, which avoids
walking every page just to count them.
"""
_, headers = _get(f"{API}/repos/{SLUG}/contributors?per_page=1&anon=false")
link = headers.get("Link", "")
match = re.search(r'[?&]page=(\d+)>;\s*rel="last"', link)
if match:
return int(match.group(1))
# No Link header means a single page; count what came back.
people, _ = _get(f"{API}/repos/{SLUG}/contributors?per_page=100&anon=false")
return len(people)
def main() -> int:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--stdout", action="store_true", help="print, write nothing")
args = parser.parse_args()
repo, _ = _get(f"{API}/repos/{SLUG}")
data = {
"_comment": (
"Generated by scripts/gen_github_data.py. The last known-good repository "
"counts, shipped so the site renders them without the network. The live "
"GitHub API still wins when it answers."
),
"derived_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
"slug": repo["full_name"],
"stars": repo["stargazers_count"],
"forks": repo["forks_count"],
"watchers": repo["subscribers_count"],
"open_issues": repo["open_issues_count"],
"contributors": contributors_count(),
}
text = json.dumps(data, indent=2) + "\n"
if args.stdout:
sys.stdout.write(text)
return 0
OUT.write_text(text)
print(f"{OUT.relative_to(REPO)}: {data['stars']} stars · {data['forks']} forks · "
f"{data['contributors']} contributors")
return 0
if __name__ == "__main__":
raise SystemExit(main())

Xet Storage Details

Size:
3.53 kB
·
Xet hash:
16099df6566f446ea142330e170808bc79aceaf6c30dfe200d779b293312ef02

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.