"""논산시 Phase 1 — 사이트맵 → 엑셀 (D~K + 병합·정렬·스타일).

매뉴얼: D:\\01.프로젝트\\DB수집\\사이트맵_수집_매뉴얼.md
사이트맵 구조: div.sitemap.type1 > [div.s_1th > a (D)] + [div.inner > div.s_2th > a (E) + ul > li > a (F) + (ul.s_4th_ul > li > a (G))]*
"""
import shutil
import warnings
from copy import copy
from urllib.parse import urljoin

import openpyxl
import requests
from bs4 import BeautifulSoup
from openpyxl.styles import Alignment, Font

warnings.filterwarnings('ignore')

INSTITUTION = '논산시'
BASE = 'https://nonsan.go.kr'
SITEMAP_URL = 'https://nonsan.go.kr/kor/html/sub07/0701.html'
SHEET_NAME = '04_논산시'
TEMPLATE = r'D:\01.프로젝트\DB수집\자료_취합_예시.xlsx'
OUTPUT = r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\충청남도\4.논산시\충청남도_논산시.xlsx'

UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
H = {'User-Agent': UA}


def extract_href(a):
    if a is None:
        return ''
    href = (a.get('href') or '').strip()
    if not href or href.startswith('#') or href.lower().startswith('javascript:'):
        return ''
    return href


def abs_url(href):
    if not href:
        return ''
    href = href.strip()
    if href.startswith(('javascript:', '#')):
        return ''
    if href.startswith(('http://', 'https://')):
        return href
    return urljoin(BASE + '/', href)


def is_external(url):
    return url.startswith(('http://', 'https://')) and 'nonsan.go.kr' not in url


def walk_ul(ul, depth, base_path, out):
    """Recursive walk for nested ul > li > a (s_4th_ul handling)."""
    for li in ul.find_all('li', recursive=False):
        a = li.find('a', recursive=False)
        if not a:
            continue
        text = a.get_text(strip=True).replace('\xa0', '').strip()
        href = extract_href(a)
        path = base_path[:depth] + [(text, href)]
        nested = li.find('ul', recursive=False)
        if nested:
            out.append({'path': list(path), 'href': href})
            walk_ul(nested, depth + 1, path, out)
        else:
            out.append({'path': list(path), 'href': href})


def main():
    print('[1] 사이트맵 가져오기')
    r = requests.get(SITEMAP_URL, headers=H, timeout=20, verify=False)
    r.encoding = r.apparent_encoding
    soup = BeautifulSoup(r.text, 'html.parser')

    sitemap = soup.select_one('div.sitemap.type1') or soup.select_one('div.sitemap')
    if sitemap is None:
        raise RuntimeError('div.sitemap.type1 영역을 찾지 못했습니다.')

    raw_rows = []
    # Iterate child elements in document order:
    # div.s_1th = 대분류 (D)
    # div.inner = 중분류 + 소분류 그룹
    current_D = ''
    for child in sitemap.find_all(['div'], recursive=False):
        cls = child.get('class', [])
        if 's_1th' in cls:
            a = child.find('a')
            current_D = a.get_text(strip=True) if a else ''
        elif 'inner' in cls:
            # div.s_2th > a → 중분류 (E)
            s2 = child.find('div', class_='s_2th')
            mid_a = s2.find('a') if s2 else None
            mid_name = mid_a.get_text(strip=True) if mid_a else ''
            mid_href = extract_href(mid_a) if mid_a else ''
            # Each direct ul under .inner is a separate group of leaf items (F)
            uls = child.find_all('ul', recursive=False)
            if not uls:
                raw_rows.append({'D': current_D, 'E': mid_name, 'href': mid_href,
                                 'F': '', 'G': '', 'H': '', 'I': '', 'J': ''})
                continue
            for ul in uls:
                tmp = []
                walk_ul(ul, 0, [], tmp)
                for item in tmp:
                    p = item['path']
                    row = {'D': current_D, 'E': mid_name, 'href': item['href'],
                           'F': '', 'G': '', 'H': '', 'I': '', 'J': ''}
                    for di, (t, _) in enumerate(p):
                        col = 'FGHIJ'[di] if di < 5 else 'J'
                        row[col] = t
                    raw_rows.append(row)

    print(f'[2] 원본 행: {len(raw_rows)}')

    # 부모-자식 URL 중복 제거
    final_rows = []
    i = 0
    removed = 0
    while i < len(raw_rows):
        row = raw_rows[i]
        if (i + 1 < len(raw_rows)
                and row.get('G', '') == ''
                and raw_rows[i + 1].get('D') == row.get('D')
                and raw_rows[i + 1].get('E') == row.get('E')
                and raw_rows[i + 1].get('F') == row.get('F')
                and raw_rows[i + 1].get('G', '') != ''
                and raw_rows[i + 1].get('href') == row.get('href')):
            removed += 1
            i += 1
            continue
        final_rows.append(row)
        i += 1
    print(f'[3] 부모-자식 URL 중복 삭제: {removed}개 → 최종 {len(final_rows)}행')

    print('[4] 엑셀 템플릿 복사')
    shutil.copy(TEMPLATE, OUTPUT)
    wb = openpyxl.load_workbook(OUTPUT)
    ws = wb.active
    ws.title = SHEET_NAME

    HEADER = {'B1:R1', 'S1:W1', 'Y1:AA1'}
    for rng in [str(m) for m in ws.merged_cells.ranges if str(m) not in HEADER]:
        ws.unmerge_cells(rng)
    for row in ws.iter_rows(min_row=3, max_row=ws.max_row, min_col=1, max_col=ws.max_column):
        for cell in row:
            cell.value = None

    START = 3
    template_r = 3
    cur_max = ws.max_row
    for idx, item in enumerate(final_rows, start=START):
        if idx > cur_max:
            for c in range(1, ws.max_column + 1):
                srcc = ws.cell(template_r, c)
                tgt = ws.cell(idx, c)
                if srcc.has_style:
                    tgt.font = copy(srcc.font)
                    tgt.fill = copy(srcc.fill)
                    tgt.border = copy(srcc.border)
                    tgt.alignment = copy(srcc.alignment)
                    tgt.number_format = srcc.number_format
                    tgt.protection = copy(srcc.protection)
        url = abs_url(item.get('href', ''))
        ws.cell(idx, 2).value = idx - 2
        ws.cell(idx, 3).value = INSTITUTION
        ws.cell(idx, 4).value = item.get('D', '')
        ws.cell(idx, 5).value = item.get('E', '')
        ws.cell(idx, 6).value = item.get('F', '')
        ws.cell(idx, 7).value = item.get('G', '')
        ws.cell(idx, 8).value = item.get('H', '')
        ws.cell(idx, 9).value = item.get('I', '')
        ws.cell(idx, 10).value = item.get('J', '')
        ws.cell(idx, 11).value = url
        if is_external(url):
            ws.cell(idx, 19).value = '외부링크'

    END = START + len(final_rows) - 1
    print(f'[5] 데이터 기입: {START}~{END}')

    center = Alignment(horizontal='center', vertical='center', wrap_text=True)
    left = Alignment(horizontal='left', vertical='center', wrap_text=False)

    def merge_runs(col_letter, col_idx, group_cols=()):
        runs = []
        cur_val = ws.cell(START, col_idx).value
        cur_grp = tuple(ws.cell(START, g).value for g in group_cols)
        run_start = START
        for r in range(START + 1, END + 1):
            v = ws.cell(r, col_idx).value
            g = tuple(ws.cell(r, gg).value for gg in group_cols)
            if v == cur_val and g == cur_grp:
                continue
            if cur_val not in (None, '') and r - 1 > run_start:
                runs.append((run_start, r - 1))
            cur_val, cur_grp, run_start = v, g, r
        if cur_val not in (None, '') and END > run_start:
            runs.append((run_start, END))
        for s, e in runs:
            ws.merge_cells(f'{col_letter}{s}:{col_letter}{e}')
            ws.cell(s, col_idx).alignment = center
        return len(runs)

    n_d = merge_runs('D', 4)
    n_e = merge_runs('E', 5, group_cols=(4,))
    n_f = merge_runs('F', 6, group_cols=(4, 5))
    for r in range(START, END + 1):
        for c in (4, 5, 6, 7):
            if ws.cell(r, c).value is not None:
                ws.cell(r, c).alignment = center
    print(f'[6] 병합 — D:{n_d} E:{n_e} F:{n_f}')

    for r in range(1, END + 1):
        ws.row_dimensions[r].height = 15

    link_n = 0
    for r in range(START, END + 1):
        cell = ws.cell(r, 11)
        u = cell.value
        if u and isinstance(u, str) and u.startswith(('http://', 'https://')):
            cell.hyperlink = u
            old = cell.font
            cell.font = Font(name=old.name or '맑은 고딕', size=old.size or 11,
                             bold=old.bold, italic=old.italic,
                             color='0000FF', underline='single')
            cell.alignment = left
            link_n += 1
    print(f'[7] 행 높이 15 + K 하이퍼링크 {link_n}개 (좌측 정렬)')

    wb.save(OUTPUT)
    print(f'[8] 저장: {OUTPUT}')

    print('\n=== 통계 ===')
    from collections import Counter
    cnt = Counter(item.get('D') for item in final_rows)
    print('대분류별 행수:')
    for k, v in cnt.items():
        print(f'  {k}: {v}')
    ext_n = sum(1 for it in final_rows if is_external(abs_url(it.get('href', ''))))
    print(f'외부링크: {ext_n}')


if __name__ == '__main__':
    main()