태그로 박혀있는 검색 가능한 메인 페이지.
JS 검색은 이미 렌더링된 링크를 보이기/숨기기만 하므로,
구글 크롤러는 JS 실행 여부와 무관하게 모든 링크를 그대로 읽을 수 있다.
"""
total = sum(len(v) for v in category_entries.values())
cat_buttons = "\n".join(
f' '
for c, entries in sorted(category_entries.items())
)
list_items = []
for category, entries in sorted(category_entries.items()):
label = CATEGORY_LABELS.get(category, category)
for e in sorted(entries, key=lambda x: x["filename"]):
title = html.escape(e["title"] or e["filename"])
desc = html.escape(e["description"]) if e["description"] else ""
href = f"./{category}/{e['filename']}"
searchtext = html.escape(f"{label} {e['filename']} {e['title']} {e['keywords']}".lower())
desc_html = f'{desc}
' if desc else ""
list_items.append(
f' '
f'{label}{title}'
f'{desc_html}'
)
list_html = "\n".join(list_items)
return f"""
TopEduPrep 학습지 전체 모음 ({total}개) | study.topeduprep.uk
TopEduPrep 학습지 전체 모음
총 {total}개 학습지 · 과목/시험별로 검색하고 바로 풀어보세요.
{cat_buttons}
"""
def build_sitemap_xml(urls_with_dates: list) -> str:
items = "\n".join(
f"""
{loc}
{lastmod}
"""
for loc, lastmod in urls_with_dates
)
return f'''
{items}
'''
def build_sitemap_index(sitemap_files: list) -> str:
items = "\n".join(
f"""
{BASE_URL}/{name}
"""
for name in sitemap_files
)
return f'''
{items}
'''
def main():
input_dir = Path(INPUT_DIR)
output_dir = Path(OUTPUT_DIR)
output_dir.mkdir(parents=True, exist_ok=True)
html_files = sorted(input_dir.glob("*.html"))
if not html_files:
print(f"⚠ {INPUT_DIR} 안에 .html 파일이 없습니다. INPUT_DIR 설정을 확인하세요.")
return
category_entries = {} # category -> [ {filename, title, description}, ... ]
today = datetime.now().strftime("%Y-%m-%d")
for filepath in html_files:
original_name = filepath.name
html_text = filepath.read_text(encoding="utf-8", errors="ignore")
title, keywords, description = extract_meta(html_text)
category = classify(original_name, title, keywords)
new_name = strip_date_prefix(original_name)
file_date = parse_date_from_filename(original_name) or today
category_dir = output_dir / category
category_dir.mkdir(parents=True, exist_ok=True)
new_path = category_dir / new_name
# 같은 이름 파일이 이미 있으면 번호를 붙여 충돌 방지
counter = 2
while new_path.exists():
stem, ext = os.path.splitext(new_name)
new_path = category_dir / f"{stem}-{counter}{ext}"
counter += 1
canonical_url = f"{BASE_URL}/{category}/{new_path.name}"
html_text = inject_canonical(html_text, canonical_url)
new_path.write_text(html_text, encoding="utf-8")
category_entries.setdefault(category, []).append({
"filename": new_path.name,
"title": title,
"description": description,
"keywords": keywords,
"date": file_date,
})
print(f"[{category}] {original_name} -> {category}/{new_path.name}")
# ---- 카테고리별 index.html 생성 ----
for category, entries in category_entries.items():
index_html = build_index_page(category, entries)
(output_dir / category / "index.html").write_text(index_html, encoding="utf-8")
# ---- 검색 가능한 전체 학습지 인덱스 페이지 (study.topeduprep.uk 루트용) ----
search_index = build_search_index_page(category_entries)
(output_dir / "index.html").write_text(search_index, encoding="utf-8")
# ---- 카테고리별 sitemap.xml (+ index 페이지 url 포함) ----
sitemap_files = []
for category, entries in category_entries.items():
urls = [(f"{BASE_URL}/{category}/", today)]
urls += [
(f"{BASE_URL}/{category}/{e['filename']}", e["date"])
for e in entries
]
sitemap_name = f"sitemap-{category}.xml"
sitemap_xml = build_sitemap_xml(urls)
(output_dir / sitemap_name).write_text(sitemap_xml, encoding="utf-8")
sitemap_files.append(sitemap_name)
# ---- 루트(검색 인덱스) 페이지용 sitemap ----
root_sitemap_xml = build_sitemap_xml([(f"{BASE_URL}/", today)])
(output_dir / "sitemap-home.xml").write_text(root_sitemap_xml, encoding="utf-8")
sitemap_files.insert(0, "sitemap-home.xml")
# ---- sitemap_index.xml ----
sitemap_index_xml = build_sitemap_index(sitemap_files)
(output_dir / "sitemap_index.xml").write_text(sitemap_index_xml, encoding="utf-8")
# ---- robots.txt ----
robots_txt = f"""User-agent: *
Allow: /
Sitemap: {BASE_URL}/sitemap_index.xml
"""
(output_dir / "robots.txt").write_text(robots_txt, encoding="utf-8")
print("\n=== 완료 ===")
for category, entries in sorted(category_entries.items()):
print(f" {CATEGORY_LABELS.get(category, category)} ({category}): {len(entries)}개")
print(f"\n결과물 위치: {output_dir.resolve()}")
print("GSC에는 sitemap_index.xml 의 URL을 제출하세요.")
print(f"예: {BASE_URL}/sitemap_index.xml")
if __name__ == "__main__":
main()