177 lines
6.4 KiB
Python
177 lines
6.4 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
直接通过Python requests将审校结果写回单元挑战多维表格
|
||
"""
|
||
import json, requests, sys, os
|
||
|
||
APP_TOKEN = "CMHSbUUjka3TrUsaxxEc297ongf"
|
||
APP_ID = "cli_a931175d41799cc7"
|
||
APP_SECRET = "Iw2vEfbjT6GtV0GhbxbZqfQ4nAPtbR14"
|
||
BASE = "https://open.feishu.cn/open-apis/bitable/v1"
|
||
|
||
TABLES = {
|
||
"听力-P1-图片选择题": "tbliZAhcc9C43B23",
|
||
"听力-P2-表格填空题": "tblzTLNH7f13uWQN",
|
||
"听力-P4-短对话选择题": "tblVmeDtBDKsAEfz",
|
||
"听力-P5-信息匹配题": "tblDssVmhGzc3UKd",
|
||
"听力-P6-听力选图": "tbloiMcD0sBtGSTq",
|
||
"听力-P7-听力拖拽": "tbly9SvPEa44k3yX",
|
||
}
|
||
|
||
KNOWN_ABILITY_LABELS = {
|
||
"显性事实理解｜关键词识别", "显性事实理解｜单句信息点抓取",
|
||
"显性细节理解｜数字/时间/地点", "多特征整合", "语用推断",
|
||
"干扰抑制｜多信息筛选", "多句保持｜信息整合",
|
||
"语用推断｜否定与纠错", "听觉抓取关键信息",
|
||
"问题意图识别", "关键细节听辨", "图像语义对齐",
|
||
"近义改写", "否定与纠错",
|
||
}
|
||
|
||
def get_token():
|
||
r = requests.post("https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal",
|
||
json={"app_id": APP_ID, "app_secret": APP_SECRET})
|
||
return r.json()["tenant_access_token"]
|
||
|
||
def fetch_records(token, table_id):
|
||
all_items = []
|
||
page_token = None
|
||
while True:
|
||
url = f"{BASE}/apps/{APP_TOKEN}/tables/{table_id}/records?page_size=200"
|
||
if page_token:
|
||
url += f"&page_token={page_token}"
|
||
r = requests.get(url, headers={"Authorization": f"Bearer {token}"})
|
||
data = r.json()
|
||
if data.get("code") != 0:
|
||
print(f" Fetch error: {data}", file=sys.stderr)
|
||
break
|
||
all_items.extend(data["data"]["items"])
|
||
if not data["data"].get("has_more"):
|
||
break
|
||
page_token = data["data"].get("page_token")
|
||
return all_items
|
||
|
||
def write_record(token, table_id, record_id, result_text):
|
||
r = requests.put(
|
||
f"{BASE}/apps/{APP_TOKEN}/tables/{table_id}/records/{record_id}",
|
||
headers={
|
||
"Authorization": f"Bearer {token}",
|
||
"Content-Type": "application/json"
|
||
},
|
||
json={"fields": {"审校结果": result_text}}
|
||
)
|
||
data = r.json()
|
||
return data.get("code") == 0
|
||
|
||
def audit_record(rec):
|
||
issues = []
|
||
fields = rec.get("fields", {})
|
||
jd_raw = fields.get("jsonData")
|
||
qs_id = fields.get("题目集合 ID", "")
|
||
|
||
if not jd_raw:
|
||
return None, False
|
||
|
||
try:
|
||
parsed = json.loads(jd_raw)
|
||
except:
|
||
return "❌ jsonData JSON解析失败", True
|
||
|
||
first = parsed.get("first", {})
|
||
second = parsed.get("second", {})
|
||
qtype = first.get("type", "unknown")
|
||
f_qsid = first.get("questionSetID", "")
|
||
s_qsid = second.get("questionSetID", "")
|
||
|
||
if qs_id and f_qsid and f_qsid != qs_id:
|
||
issues.append(f" ❌ first questionSetID({f_qsid})与字段({qs_id})不一致")
|
||
if qs_id and s_qsid and s_qsid != qs_id:
|
||
issues.append(f" ❌ second questionSetID({s_qsid})与字段({qs_id})不一致")
|
||
if f_qsid == "000001":
|
||
issues.append(f" ❌ questionSetID为000001(占位数据)")
|
||
if qs_id and not qs_id.replace("-","").isdigit() and qs_id != "000001":
|
||
issues.append(f" ❌ 题目集合 ID异常: '{qs_id}'")
|
||
|
||
for bname, block in [("first", first), ("second", second)]:
|
||
qs = block.get("questionSet", [])
|
||
if not isinstance(qs, list) or len(qs) == 0:
|
||
continue
|
||
|
||
for i, q in enumerate(qs):
|
||
expl = q.get("explanation", "")
|
||
if not expl or expl.strip() == "":
|
||
issues.append(f" ❌ {bname}[{i}]: explanation为空")
|
||
elif len(expl) < 20:
|
||
issues.append(f" 🟡 {bname}[{i}]: explanation过短({len(expl)}字)")
|
||
|
||
ability = q.get("ability", [])
|
||
if not ability:
|
||
issues.append(f" ❌ {bname}[{i}]: ability为空")
|
||
else:
|
||
found_bad_sep = False
|
||
for a in ability:
|
||
if isinstance(a, str) and "¥¥" in a:
|
||
if not found_bad_sep:
|
||
issues.append(f" ❌ {bname}[{i}]: ability用¥¥分隔(应为逗号)")
|
||
found_bad_sep = True
|
||
|
||
text1 = None
|
||
text2 = None
|
||
for k in ["题目1 完整配置", "题目1", "题目完整配置"]:
|
||
if fields.get(k):
|
||
text1 = fields[k]
|
||
break
|
||
for k in ["题目2 完整配置", "题目2"]:
|
||
if fields.get(k):
|
||
text2 = fields[k]
|
||
break
|
||
|
||
if not text1:
|
||
issues.append(f" ❌ 题目1文本字段为空")
|
||
if second and second.get("questionSet") and not text2:
|
||
issues.append(f" 🟡 题目2文本字段为空(但jsonData有second)")
|
||
|
||
if not issues:
|
||
return f"✅ 审校通过\n题型：{qtype} | 题组：first={len(first.get('questionSet',[]))}题 second={len(second.get('questionSet',[]))}题", False
|
||
else:
|
||
return f"❌ 审校发现问题（{len(issues)}项）\n题型：{qtype} | 题组：first={len(first.get('questionSet',[]))}题 second={len(second.get('questionSet',[]))}题\n" + "\n".join(issues), True
|
||
|
||
def main():
|
||
token = get_token()
|
||
print(f"Token获取成功")
|
||
|
||
total_err = total_ok = total_skip = 0
|
||
|
||
for tname, tid in TABLES.items():
|
||
print(f"\n--- {tname} ---")
|
||
records = fetch_records(token, tid)
|
||
|
||
for rec in records:
|
||
rid = rec["record_id"]
|
||
fields = rec.get("fields", {})
|
||
ds = fields.get("dataStatus")
|
||
|
||
if ds != "0" or not fields.get("jsonData"):
|
||
total_skip += 1
|
||
continue
|
||
|
||
result_text, has_err = audit_record(rec)
|
||
if result_text is None:
|
||
total_skip += 1
|
||
continue
|
||
|
||
if write_record(token, tid, rid, result_text):
|
||
tag = "🔴" if has_err else "✅"
|
||
print(f" {tag} {rid} ✓")
|
||
if has_err:
|
||
total_err += 1
|
||
else:
|
||
total_ok += 1
|
||
else:
|
||
print(f" ❌ {rid} 写入失败")
|
||
|
||
print(f"\n{'='*40}")
|
||
print(f"✅通过={total_ok}, 🔴问题={total_err}, ⏭️跳过={total_skip}")
|
||
|
||
if __name__ == "__main__":
|
||
main()
|