# -*- coding: utf-8 -*-
"""取证脚本：拉取 5 个目标仓库的元数据 / README / 文件树。
只读 GitHub 公开 API，产物落本目录 api/ 下。运行一次即留痕（含取证时间）。
"""
import json, os, sys, time, urllib.request, urllib.error

sys.stdout.reconfigure(encoding="utf-8", errors="replace")

HERE = os.path.dirname(os.path.abspath(__file__))
OUT = os.path.join(HERE, "api")
os.makedirs(OUT, exist_ok=True)

REPOS = [
    ("easel", "ZJU-REAL/Easel"),
    ("wendao", "wendaoai/wendao-content-workbench"),
    ("opencreator", "krillinai/OpenCreator"),
    ("postiz", "gitroomhq/postiz-app"),
    ("postsider", "lumizone/postsider"),
]

HDRS = {"User-Agent": "wb-research/1.0", "Accept": "application/vnd.github+json"}


def get(url):
    req = urllib.request.Request(url, headers=HDRS)
    with urllib.request.urlopen(req, timeout=40) as r:
        return json.loads(r.read().decode("utf-8"))


def save(name, obj):
    p = os.path.join(OUT, name)
    with open(p, "w", encoding="utf-8") as f:
        json.dump(obj, f, ensure_ascii=False, indent=1)
    return p


meta_all = {}
for slug, full in REPOS:
    rec = {"full_name": full, "fetched_at": time.strftime("%Y-%m-%dT%H:%M:%S")}
    try:
        m = get("https://api.github.com/repos/" + full)
        save(slug + ".repo.json", m)
        rec["meta"] = {k: m.get(k) for k in [
            "full_name", "description", "language", "stargazers_count",
            "forks_count", "open_issues_count", "default_branch",
            "created_at", "pushed_at", "size", "homepage", "archived", "fork"]}
        rec["meta"]["license"] = (m.get("license") or {}).get("spdx_id")
        rec["meta"]["topics"] = m.get("topics")
        branch = m.get("default_branch") or "main"

        try:
            rdm = get("https://api.github.com/repos/%s/readme" % full)
            save(slug + ".readme.json", rdm)
            import base64
            txt = base64.b64decode(rdm.get("content", "")).decode("utf-8", "replace")
            with open(os.path.join(OUT, slug + ".README.md"), "w", encoding="utf-8") as f:
                f.write(txt)
            rec["readme_path"] = rdm.get("path")
            rec["readme_bytes"] = len(txt.encode("utf-8"))
        except urllib.error.HTTPError as e:
            rec["readme_error"] = "HTTP %s" % e.code

        try:
            tr = get("https://api.github.com/repos/%s/git/trees/%s?recursive=1" % (full, branch))
            save(slug + ".tree.json", tr)
            paths = [t["path"] for t in tr.get("tree", []) if t.get("type") == "blob"]
            rec["tree_total_blobs"] = len(paths)
            rec["tree_truncated"] = tr.get("truncated")
            tops = sorted({p.split("/")[0] for p in paths})
            rec["tree_top_level"] = tops
        except urllib.error.HTTPError as e:
            rec["tree_error"] = "HTTP %s" % e.code
    except urllib.error.HTTPError as e:
        rec["error"] = "HTTP %s %s" % (e.code, e.reason)
    except Exception as e:
        rec["error"] = repr(e)
    meta_all[slug] = rec
    print("[%s] %s" % (slug, json.dumps(rec, ensure_ascii=False)[:600]))
    time.sleep(0.6)

save("_summary.json", meta_all)
print("\nDONE -> " + OUT)