from __future__ import annotations
from html import escape
from pathlib import Path
from urllib.parse import quote
from openpyxl import load_workbook
INPUT = Path(
"docs/final-results/20260813-yifangbao-phone-legal-enrichment/"
"7月线索导入模板-0715-0812-电话法人已补全-可靠来源二次补查.xlsx"
)
OUTPUT = Path("docs/final-results/20260813-yifangbao-phone-legal-enrichment/index.html")
def text(value: object) -> str:
return str(value or "").strip()
def linkify(value: object) -> str:
url = text(value)
if not url:
return ""
return f'打开来源'
def status_badge(value: str) -> str:
klass = "ok" if value == "已补充" else "review" if value == "待复核" else "gap"
return f'{escape(value)}'
def main() -> None:
wb = load_workbook(INPUT, data_only=True)
ws = wb["企业补全汇总"]
rows = [list(row) for row in ws.iter_rows(min_row=2, values_only=True)]
unique_companies = len(rows)
final_phone = sum(1 for row in rows if text(row[3]))
added_phone = sum(1 for row in rows if text(row[4]))
legal_count = sum(1 for row in rows if text(row[5]))
legal_review = sum(1 for row in rows if text(row[6]) == "待复核")
enriched = sum(1 for row in rows if text(row[4]) or text(row[5]))
review_rows = sum(1 for row in rows if text(row[8]) == "medium" or "复核" in text(row[11]))
phone_gap_companies = sum(1 for row in rows if text(row[1]) and not text(row[3]))
second_round_names = {
"青岛天高智慧科技有限公司",
"中国农业银行股份有限公司潮州分行",
"成都鑫金大数据有限责任公司",
"中国银行股份有限公司福州闽都支行",
"张家港市大数据科技有限公司",
"广州市公用公交站场管理服务有限公司",
"中国电信股份有限公司牡丹江分公司",
}
second_round_companies = sum(1 for row in rows if text(row[1]) in second_round_names)
body = []
for row in rows:
legal_status = text(row[6])
body.append(
f"""
{escape(text(row[0]))}
{escape(text(row[1]))}
{escape(text(row[2]))}
{escape(text(row[3]))}
{escape(text(row[4]))}
{escape(text(row[5]))}
{status_badge(legal_status)}
{escape(text(row[7]))}
{escape(text(row[8]))}
{linkify(row[9])}
{escape(text(row[10]))}
{escape(text(row[11]))}
{escape(text(row[12]))}
"""
)
workbook_href = quote(INPUT.name)
html = f"""
7月线索电话与法人补全结果