yipng05-max/-skills/pdf-bib-import

#!/usr/bin/env python3
"""
extract_bib.py — 从 PDF 目录批量提取题录，输出 bib_data.json
用法：python3 extract_bib.py <pdf_dir>
"""
import os, sys, json, subprocess, re
def run(cmd):
    return subprocess.run(cmd, capture_output=True, text=True).stdout.strip()
def extract_pdf_meta(path):
    info = run(["/opt/homebrew/bin/pdfinfo", path])
    meta = {}
    for line in info.splitlines():
        if ":" in line:
            k, _, v = line.partition(":")
            meta[k.strip()] = v.strip()
    text = run(["/opt/homebrew/bin/pdftotext", "-l", "2", path, "-"])
    return meta, text
def guess_fields(meta, text):
    """从 pdfinfo + 前两页文字中猜测题录字段，返回 dict。"""
    lines = [l.strip() for l in text.splitlines() if l.strip()]
    return {
        "论文题目": meta.get("Title", ""),
        "作者":     meta.get("Author", ""),
        "发表年份": None,
        "期刊名称": "",
        "卷期页码": "",
        "DOI":      "",
        "摘要":     "",
        "_raw_text_preview": "\n".join(lines[:40]),  # 供人工核查
    }
def main():
    pdf_dir = sys.argv[1] if len(sys.argv) > 1 else "."
    results = []
    for fname in sorted(os.listdir(pdf_dir)):
        if not fname.lower().endswith(".pdf"):
            continue
        fpath = os.path.join(pdf_dir, fname)
        meta, text = extract_pdf_meta(fpath)
        rec = guess_fields(meta, text)
        rec["_filename"] = fname
        results.append(rec)
        print(f"  ✓ {fname}")
    out = "/tmp/bib_data.json"
    with open(out, "w", encoding="utf-8") as f:
        json.dump(results, f, ensure_ascii=False, indent=2)
    print(f"\n已写出 {len(results)} 条记录 → {out}")
    print("请检查 bib_data.json，补全缺失字段后再执行 Step 3 导入。")
if __name__ == "__main__":
    main()

python3 /tmp/extract_bib.py "/path/to/pdf_folder"

lark-cli base +base-create --name "论文题录数据库"
# 记录返回的 base_token

lark-cli base +table-list --base-token <BASE_TOKEN>
lark-cli base +table-update --base-token <BASE_TOKEN> --table-id <TABLE_ID> --json '{"name":"论文题录"}'

# 查看现有字段（记录各字段 id）
lark-cli base +field-list --base-token <BASE_TOKEN> --table-id <TABLE_ID>
 
# 将默认文本字段重命名为"论文题目"
lark-cli base +field-update --base-token <BASE_TOKEN> --table-id <TABLE_ID> \
  --field-id <TEXT_FIELD_ID> --json '{"type":"text","name":"论文题目","style":{"type":"plain"}}'
 
# 删除多余默认字段（日期、附件、单选）
lark-cli base +field-delete --base-token <BASE_TOKEN> --table-id <TABLE_ID> --field-id <ID> --yes
 
# 创建其余字段（串行执行）
cd /tmp
for field in \
  '{"type":"text","name":"作者","style":{"type":"plain"}}' \
  '{"type":"number","name":"发表年份"}' \
  '{"type":"text","name":"期刊名称","style":{"type":"plain"}}' \
  '{"type":"text","name":"卷期页码","style":{"type":"plain"}}' \
  '{"type":"text","name":"DOI","style":{"type":"plain"}}' \
  '{"type":"text","name":"摘要","style":{"type":"plain"}}'; do
  echo "$field" > field.json
  lark-cli base +field-create --base-token <BASE_TOKEN> --table-id <TABLE_ID> --json @field.json
  sleep 0.3
done

cat << 'PYEOF' > /tmp/import_to_lark.py
#!/usr/bin/env python3
"""
import_to_lark.py — 从 bib_data.json 批量写入飞书 Base
用法：python3 import_to_lark.py <BASE_TOKEN> <TABLE_ID> [bib_data.json]
"""
import json, sys, subprocess, time, os
 
def upsert(base_token, table_id, record):
    tmp = "/tmp/_rec.json"
    # 去除空值字段（避免写入空字符串覆盖）
    payload = {k: v for k, v in record.items()
               if not k.startswith("_") and v not in (None, "", 0)}
    # 年份是数字，0 代表未知，保持过滤
    with open(tmp, "w", encoding="utf-8") as f:
        json.dump(payload, f, ensure_ascii=False)
    result = subprocess.run(
        ["lark-cli", "base", "+record-upsert",
         "--base-token", base_token,
         "--table-id", table_id,
         "--json", "@_rec.json"],
        capture_output=True, text=True, cwd="/tmp"
    )
    return json.loads(result.stdout)
 
def main():
    base_token = sys.argv[1]
    table_id   = sys.argv[2]
    data_file  = sys.argv[3] if len(sys.argv) > 3 else "/tmp/bib_data.json"
 
    with open(data_file, encoding="utf-8") as f:
        records = json.load(f)
 
    ok, fail = 0, 0
    for i, rec in enumerate(records, 1):
        title = rec.get("论文题目", rec.get("_filename", f"record-{i}"))
        resp = upsert(base_token, table_id, rec)
        if resp.get("ok"):
            ok += 1
            print(f"  [{i}/{len(records)}] ✓ {title[:60]}")
        else:
            fail += 1
            print(f"  [{i}/{len(records)}] ✗ {title[:60]}: {resp}")
        time.sleep(0.5)   # 避免写入冲突
 
    print(f"\n完成：{ok} 成功 / {fail} 失败")
 
if __name__ == "__main__":
    main()
PYEOF
 
python3 /tmp/import_to_lark.py <BASE_TOKEN> <TABLE_ID> /tmp/bib_data.json