登记 chinese-poetry / ck12 / phet，并让 source schema、lint 与 INDEX 能按学科和抓取进度消费。 Co-authored-by: Cursor <cursoragent@cursor.com>
这个提交包含在：
231
tools/fetch_source.py
普通文件
231
tools/fetch_source.py
普通文件
@@ -0,0 +1,231 @@
|
||||
#!/usr/bin/env python3
|
||||
"""fetch_source.py — 按 sources/*.yaml 自动抓取 L2 原始数据到本地 staging。
|
||||
|
||||
只处理**可自动化**的 fetch_method：
|
||||
- curl : 逐 item 下载单文件（item.url，或 source.url_template 渲染 {item_id}）
|
||||
- git-clone : 浅克隆一次仓库，再按 item.src_path 打包成 .tar.gz
|
||||
|
||||
manual-download / manual-export / generated 会被跳过（需人工介入）。
|
||||
|
||||
用法：
|
||||
# 看有哪些可自动抓取（不下载）
|
||||
python tools/fetch_source.py --list
|
||||
|
||||
# 试跑：只打印将要下载的 URL / 目标路径
|
||||
python tools/fetch_source.py --source phet --dry-run
|
||||
|
||||
# 实际下载到 .staging/，并回填 sha256/size/fetch_date/status=fetched
|
||||
python tools/fetch_source.py --source phet --apply
|
||||
python tools/fetch_source.py --source chinese-poetry --apply
|
||||
python tools/fetch_source.py --subject physics --apply # 按学科批量
|
||||
python tools/fetch_source.py --all-auto --apply # 所有可自动化来源
|
||||
|
||||
下载产物落在 <repo>/.staging/{source_id}/...（已 gitignore），随后用
|
||||
python tools/oss_sync.py --raw-root .staging --apply
|
||||
上传到 OSS 并对齐 oss_key。
|
||||
|
||||
注意：回填 YAML 走 yaml_patch（行级替换），**保留文件内注释**。
|
||||
"""
|
||||
import os, sys, glob, hashlib, datetime, argparse, subprocess, shutil, tarfile, urllib.request
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||||
from yaml_patch import patch_item_fields, patch_source_fields
|
||||
|
||||
REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
STAGING = os.path.join(REPO, ".staging")
|
||||
CACHE = os.path.join(REPO, ".cache", "repos")
|
||||
AUTO_METHODS = {"curl", "git-clone"}
|
||||
UA = "edu-content-fetcher/1.0 (+https://git.aibeaver.cn/fengjunchen/edu-content)"
|
||||
|
||||
|
||||
def sha256_file(p):
|
||||
h = hashlib.sha256()
|
||||
with open(p, "rb") as f:
|
||||
for chunk in iter(lambda: f.read(1 << 20), b""):
|
||||
h.update(chunk)
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
def load_sources():
|
||||
import yaml
|
||||
out = []
|
||||
for path in sorted(glob.glob(os.path.join(REPO, "sources", "**", "*.yaml"), recursive=True)):
|
||||
try:
|
||||
doc = yaml.safe_load(open(path, encoding="utf-8"))
|
||||
except Exception as e:
|
||||
print(f"WARN: {path} 解析失败: {e}")
|
||||
continue
|
||||
for s in (doc or {}).get("sources", []) or []:
|
||||
out.append((path, s))
|
||||
return out
|
||||
|
||||
|
||||
def item_url(source, item):
|
||||
if item.get("url"):
|
||||
return item["url"]
|
||||
tpl = source.get("url_template")
|
||||
if tpl:
|
||||
return tpl.replace("{item_id}", item["id"])
|
||||
return None
|
||||
|
||||
|
||||
def fetch_curl(source, item, dest_dir, dry_run):
|
||||
url = item_url(source, item)
|
||||
if not url:
|
||||
return None, "无 url / url_template，跳过"
|
||||
fname = os.path.basename(item.get("oss_key") or "") or f"{item['id']}"
|
||||
dest = os.path.join(dest_dir, fname)
|
||||
if dry_run:
|
||||
return dest, f"[dry-run] {url} -> {dest}"
|
||||
os.makedirs(dest_dir, exist_ok=True)
|
||||
req = urllib.request.Request(url, headers={"User-Agent": UA})
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=120) as r, open(dest, "wb") as f:
|
||||
shutil.copyfileobj(r, f)
|
||||
except Exception as e:
|
||||
return None, f"下载失败: {type(e).__name__}: {e}"
|
||||
return dest, f"ok {os.path.getsize(dest)}B"
|
||||
|
||||
|
||||
def ensure_clone(source, dry_run):
|
||||
"""浅克隆到 .cache/repos/{id}，返回本地路径。"""
|
||||
url = source.get("url")
|
||||
if not url:
|
||||
return None, "source.url 为空，无法 clone"
|
||||
local = os.path.join(CACHE, source["id"])
|
||||
if os.path.isdir(os.path.join(local, ".git")):
|
||||
return local, "复用已有克隆"
|
||||
if dry_run:
|
||||
return local, f"[dry-run] git clone --depth 1 {url} {local}"
|
||||
os.makedirs(os.path.dirname(local), exist_ok=True)
|
||||
r = subprocess.run(["git", "clone", "--depth", "1", url, local],
|
||||
capture_output=True, text=True, timeout=1800)
|
||||
if r.returncode != 0:
|
||||
return None, f"clone 失败: {(r.stderr or '').strip()[:200]}"
|
||||
return local, "克隆完成"
|
||||
|
||||
|
||||
def fetch_git_item(source, item, repo_dir, dest_dir, dry_run):
|
||||
"""按 item.src_path 从克隆仓库取内容。
|
||||
|
||||
目录 → 打包 .tar.gz；单文件 → 直接复制（除非 oss_key 显式要 .tar.gz）。
|
||||
否则会产出「名叫 KET.json 其实是 tar.gz」的坑数据。
|
||||
"""
|
||||
rel = item.get("src_path")
|
||||
if not rel:
|
||||
return None, "缺 src_path，跳过"
|
||||
src = os.path.join(repo_dir, rel)
|
||||
fname = os.path.basename(item.get("oss_key") or f"{item['id']}.tar.gz")
|
||||
dest = os.path.join(dest_dir, fname)
|
||||
want_tar = fname.endswith((".tar.gz", ".tgz"))
|
||||
if dry_run:
|
||||
action = "tar" if want_tar else "copy"
|
||||
return dest, f"[dry-run] {action} {rel} -> {dest}"
|
||||
if not os.path.exists(src):
|
||||
return None, f"仓库内路径不存在: {rel}"
|
||||
if os.path.isdir(src) and not want_tar:
|
||||
return None, f"src_path 是目录但 oss_key 不是 .tar.gz（{fname}），请修正 oss_key"
|
||||
os.makedirs(dest_dir, exist_ok=True)
|
||||
if want_tar:
|
||||
with tarfile.open(dest, "w:gz") as tf:
|
||||
tf.add(src, arcname=rel)
|
||||
else:
|
||||
shutil.copy2(src, dest)
|
||||
return dest, f"ok {os.path.getsize(dest)}B"
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--source", help="按 source id 抓取")
|
||||
ap.add_argument("--subject", help="按学科代码抓取（chinese/physics/science/...）")
|
||||
ap.add_argument("--all-auto", action="store_true", help="所有 fetch_method 可自动化的来源")
|
||||
ap.add_argument("--list", action="store_true", help="只列出可自动抓取的来源")
|
||||
ap.add_argument("--dry-run", action="store_true")
|
||||
ap.add_argument("--apply", action="store_true")
|
||||
ap.add_argument("--limit", type=int, default=0, help="每个 source 最多抓 N 个条目（调试用）")
|
||||
args = ap.parse_args()
|
||||
|
||||
all_sources = load_sources()
|
||||
|
||||
if args.list:
|
||||
print(f"{'source':22} {'method':12} {'items':>5} subjects")
|
||||
print("-" * 70)
|
||||
for path, s in all_sources:
|
||||
mark = "" if s.get("fetch_method") in AUTO_METHODS else " (需人工)"
|
||||
print(f"{s['id']:22} {str(s.get('fetch_method')):12} "
|
||||
f"{len(s.get('items') or []):5} {','.join(s.get('subjects') or [])}{mark}")
|
||||
return
|
||||
|
||||
# 选择目标
|
||||
targets = []
|
||||
for path, s in all_sources:
|
||||
if s.get("fetch_method") not in AUTO_METHODS:
|
||||
continue
|
||||
if args.source and s["id"] != args.source:
|
||||
continue
|
||||
if args.subject and args.subject not in (s.get("subjects") or []):
|
||||
continue
|
||||
if not (args.source or args.subject or args.all_auto):
|
||||
continue
|
||||
targets.append((path, s))
|
||||
|
||||
if not targets:
|
||||
print("没有匹配的可自动抓取来源。用 --list 查看，或检查 --source/--subject 拼写。")
|
||||
sys.exit(0 if (args.source or args.subject or args.all_auto) else 2)
|
||||
|
||||
dry = args.dry_run or not args.apply
|
||||
today = datetime.date.today().isoformat()
|
||||
total_ok = total_fail = 0
|
||||
|
||||
for path, s in targets:
|
||||
sid = s["id"]
|
||||
method = s["fetch_method"]
|
||||
items = s.get("items") or []
|
||||
if args.limit:
|
||||
items = items[:args.limit]
|
||||
print(f"\n=== {sid} ({method}) — {len(items)} 个条目 ===")
|
||||
if not items:
|
||||
print(" items 为空，无可抓取内容（该来源尚未登记具体条目）")
|
||||
continue
|
||||
|
||||
dest_dir = os.path.join(STAGING, sid)
|
||||
repo_dir = None
|
||||
if method == "git-clone":
|
||||
repo_dir, msg = ensure_clone(s, dry)
|
||||
print(f" clone: {msg}")
|
||||
if repo_dir is None:
|
||||
total_fail += len(items)
|
||||
continue
|
||||
|
||||
ok_here = 0
|
||||
for it in items:
|
||||
if method == "curl":
|
||||
dest, msg = fetch_curl(s, it, dest_dir, dry)
|
||||
else:
|
||||
dest, msg = fetch_git_item(s, it, repo_dir, dest_dir, dry)
|
||||
print(f" {it['id']:34} {msg}")
|
||||
if dest is None:
|
||||
total_fail += 1
|
||||
continue
|
||||
total_ok += 1
|
||||
ok_here += 1
|
||||
if not dry and os.path.isfile(dest):
|
||||
patch_item_fields(path, sid, it["id"], {
|
||||
"sha256": sha256_file(dest),
|
||||
"size": os.path.getsize(dest),
|
||||
"fetch_date": today,
|
||||
"status": "fetched",
|
||||
})
|
||||
if not dry and ok_here:
|
||||
patch_source_fields(path, sid, {"status": "fetched", "fetched_at": today})
|
||||
|
||||
print(f"\n合计：成功 {total_ok} | 失败/跳过 {total_fail}")
|
||||
if dry:
|
||||
print("[dry-run] 未实际下载。加 --apply 执行。")
|
||||
else:
|
||||
print(f"产物在 {STAGING}/，已回填 sha256/size 到 sources YAML（注释保留）。")
|
||||
print("下一步上传 OSS： python tools/oss_sync.py --raw-root .staging --apply")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
在新工单中引用
屏蔽一个用户