DB_JOB/작업파일/완료/광역_사이트맵/_fix_external.py

# -*- coding: utf-8 -*-
"""외부 URL인데 사이트 아님 정리 (충남/충북/제주, 검수완료 제외).
 - 외부도메인(기관 core 도메인이 host에 없음) & L!=사이트 인 행:
   · D/E/F/G 라벨 전부 빈칸 → 템플릿 잔재 → 삭제
   · 라벨 있음 → 진짜 외부링크 → L=사이트, M/N/O/P/Q 비움, S=외부링크
flatten→잔재제외+사이트적용→재작성→D/E/F 재병합→K하이퍼링크.
"""
import sys, glob, os, re, shutil, warnings
from copy import copy
from urllib.parse import urlsplit
from collections import Counter
import openpyxl
from openpyxl.styles import Alignment, Font
warnings.filterwarnings('ignore')

MAXCOL = 27
HEADER_MERGES = {'B1:R1', 'S1:W1', 'Y1:AA1'}
EXCLUDE = {'계룡시', '공주시', '금산군', '논산시', '보령시'}


def host_of(u):
    try:
        return urlsplit(u).netloc.lower()
    except Exception:
        return ''


def process(path, write):
    wb = openpyxl.load_workbook(path)
    ws = wb.active
    # flatten cat for label check + main domain
    fcat = {}
    for r in range(3, ws.max_row + 1):
        fcat[r] = {c: ws.cell(r, c).value for c in (4, 5, 6, 7)}
    for mr in ws.merged_cells.ranges:
        if mr.min_col in (4, 5, 6) and mr.min_row >= 3:
            top = ws.cell(mr.min_row, mr.min_col).value
            for rr in range(mr.min_row, mr.max_row + 1):
                if rr in fcat and fcat[rr].get(mr.min_col) in (None, ''):
                    fcat[rr][mr.min_col] = top
    hosts = Counter()
    for r in range(3, ws.max_row + 1):
        if ws.cell(r, 2).value:
            k = ws.cell(r, 11).value
            if isinstance(k, str) and k.startswith('http'):
                hosts[host_of(k)] += 1
    if not hosts:
        return (0, 0)
    core = re.sub(r'^www\.', '', hosts.most_common(1)[0][0]).split('.')[0]

    delete = set()
    sitemark = set()
    for r in range(3, ws.max_row + 1):
        if not ws.cell(r, 2).value:
            continue
        k = ws.cell(r, 11).value
        L = ws.cell(r, 12).value
        if isinstance(k, str) and k.startswith('http'):
            h = host_of(k)
            if core and core not in h and L != '사이트':
                haslabel = any(fcat[r].get(c) not in (None, '') for c in (4, 5, 6, 7))
                if haslabel:
                    sitemark.add(r)
                else:
                    delete.add(r)
    if not delete and not sitemark:
        return (0, 0)
    if not write:
        return (len(delete), len(sitemark))

    shutil.copy(path, path.replace('.xlsx', '_backup_외부정리전.xlsx'))
    # flatten
    for mr in list(ws.merged_cells.ranges):
        s = str(mr)
        if s in HEADER_MERGES:
            continue
        top = ws.cell(mr.min_row, mr.min_col).value
        ws.unmerge_cells(s)
        for rr in range(mr.min_row, mr.max_row + 1):
            for cc in range(mr.min_col, mr.max_col + 1):
                if ws.cell(rr, cc).value in (None, ''):
                    ws.cell(rr, cc).value = top
    out = []
    for r in range(3, ws.max_row + 1):
        if all(ws.cell(r, c).value in (None, '') for c in range(2, MAXCOL + 1)):
            continue
        if r in delete:
            continue
        vals = {c: ws.cell(r, c).value for c in range(1, MAXCOL + 1)}
        if r in sitemark:
            vals[12] = '사이트'      # L
            vals[13] = None          # M
            vals[14] = None          # N
            vals[15] = None          # O
            vals[16] = None          # P
            vals[17] = None          # Q
            vals[19] = '외부링크'    # S
        styles = {c: (copy(ws.cell(r, c).font), copy(ws.cell(r, c).fill),
                      copy(ws.cell(r, c).border), copy(ws.cell(r, c).alignment),
                      ws.cell(r, c).number_format, copy(ws.cell(r, c).protection))
                  for c in range(1, MAXCOL + 1)}
        out.append({'vals': vals, 'styles': styles})
    for r in range(3, ws.max_row + 1):
        for c in range(1, MAXCOL + 1):
            ws.cell(r, c).value = None
            ws.cell(r, c).hyperlink = None
    START = 3
    for i, orow in enumerate(out):
        rr = START + i
        for c in range(1, MAXCOL + 1):
            f, fl, bd, al, nf, pr = orow['styles'][c]
            cell = ws.cell(rr, c)
            cell.font = copy(f); cell.fill = copy(fl); cell.border = copy(bd)
            cell.alignment = copy(al); cell.number_format = nf; cell.protection = copy(pr)
            cell.value = orow['vals'].get(c)
        ws.cell(rr, 2).value = i + 1
    END = START + len(out) - 1
    for rr in range(END + 1, ws.max_row + 1):
        for c in range(1, MAXCOL + 1):
            ws.cell(rr, c).value = None
            ws.cell(rr, c).hyperlink = None
    center = Alignment(horizontal='center', vertical='center', wrap_text=True)
    left = Alignment(horizontal='left', vertical='center', wrap_text=False)

    def merge_runs(letter, idx, gc=()):
        cur = ws.cell(START, idx).value
        grp = tuple(ws.cell(START, g).value for g in gc)
        st = START; runs = []
        for rr in range(START + 1, END + 1):
            val = ws.cell(rr, idx).value
            g2 = tuple(ws.cell(rr, gg).value for gg in gc)
            if val == cur and g2 == grp:
                continue
            if cur not in (None, '') and rr - 1 > st:
                runs.append((st, rr - 1))
            cur, grp, st = val, g2, rr
        if cur not in (None, '') and END > st:
            runs.append((st, END))
        for s, e in runs:
            ws.merge_cells(f'{letter}{s}:{letter}{e}')
            ws.cell(s, idx).alignment = center
    merge_runs('F', 6, (4, 5))
    merge_runs('E', 5, (4,))
    merge_runs('D', 4)
    for rr in range(START, END + 1):
        for c in (4, 5, 6, 7):
            if ws.cell(rr, c).value is not None:
                ws.cell(rr, c).alignment = center
    for rr in range(1, END + 1):
        ws.row_dimensions[rr].height = 15
    for rr in range(START, END + 1):
        cell = ws.cell(rr, 11)
        u = cell.value
        if 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
    wb.save(path)
    return (len(delete), len(sitemark))


def main():
    write = '--write' in sys.argv
    regions = ['충청남도', '충청북도', '제주특별자치도']
    base = os.path.dirname(os.path.abspath(__file__))
    for region in regions:
        for path in sorted(glob.glob(os.path.join(base, region, '*', '*.xlsx'))):
            if 'backup' in path or '_r2' in path:
                continue
            nm = os.path.basename(path).replace('.xlsx', '')
            if nm in EXCLUDE:
                continue
            d, s = process(path, write)
            if d or s:
                tag = '저장' if write else 'dry'
                print(f'[{tag}] {nm}: 삭제(잔재) {d} / 사이트표시 {s}')


if __name__ == '__main__':
    main()