fix: ダンジョン・レイド・討滅戦全209ページのヘッダー・サイドバー構造を大元テンプレート(Seesaaニュートラルグレーiframe共通化)に完全統一

This commit is contained in:
armonica committed 2026-10-29 16:19:58 +09:00
1 parent a653dcb5a6
commit 6d752556d7
217 files changed
+5958 -2770

No files matched your search

+39
View File
@@ -0,0 +1,39 @@
import os
import sys
sys.stdout.reconfigure(encoding='utf-8')
categories = {}
for root, dirs, files in os.walk('.'):
if '.git' in root or 'node_modules' in root:
continue
for f in files:
if f.endswith('.html'):
path = os.path.join(root, f).replace('\\', '/')
if path in ['./common/header.html', './common/sidebar.html']:
continue
with open(path, 'r', encoding='utf-8', errors='ignore') as fp:
content = fp.read()
has_iframe = 'wiki-header-frame' in content or 'wiki-sidebar-frame' in content
has_container = 'wiki-header-container' in content or 'wiki-sidebar-container' in content
dir_name = os.path.dirname(path)
if dir_name not in categories:
categories[dir_name] = {'iframe': 0, 'container': 0, 'other': 0, 'total': 0, 'container_files': [], 'other_files': []}
categories[dir_name]['total'] += 1
if has_iframe:
categories[dir_name]['iframe'] += 1
elif has_container:
categories[dir_name]['container'] += 1
categories[dir_name]['container_files'].append(os.path.basename(path))
else:
categories[dir_name]['other'] += 1
categories[dir_name]['other_files'].append(os.path.basename(path))
print(f"{'Directory':<30} | {'Total':<5} | {'iframe':<6} | {'container':<9} | {'other':<5}")
print('-'*65)
for d, counts in sorted(categories.items()):
print(f"{d:<30} | {counts['total']:<5} | {counts['iframe']:<6} | {counts['container']:<9} | {counts['other']:<5}")
+43
View File
@@ -0,0 +1,43 @@
import os
import re
import sys
sys.stdout.reconfigure(encoding='utf-8')
with open('tools/test_extract.py', 'r', encoding='utf-8') as fp:
code = fp.read()
# extract_content 関数定義部分をそのまま利用
exec(code[:code.find("test_files = [")])
unknown_files = []
success_count = 0
with open('tools/list_non_conforming_pages.py', 'r', encoding='utf-8') as fp:
lines = fp.readlines()
for root, dirs, files in os.walk('.'):
if '.git' in root or 'node_modules' in root:
continue
for f in files:
if f.endswith('.html'):
path = os.path.join(root, f).replace('\\', '/')
if path in ['./common/header.html', './common/sidebar.html', './common/templates/dungeon_raid_template.html']:
continue
with open(path, 'r', encoding='utf-8', errors='ignore') as fp:
content = fp.read()
has_iframe_header = 'wiki-header-frame' in content
has_iframe_sidebar = 'wiki-sidebar-frame' in content
if not (has_iframe_header and has_iframe_sidebar):
t, d, c, pattern = extract_content(content)
if pattern == "UNKNOWN" or not c:
unknown_files.append(path)
else:
success_count += 1
print(f"抽出成功ファイル数: {success_count} / {success_count + len(unknown_files)}")
print(f"抽出失敗ファイル数: {len(unknown_files)}")
if unknown_files:
print("失敗ファイル一覧:")
for uf in unknown_files:
print(uf)
+41
View File
@@ -0,0 +1,41 @@
import os
import sys
sys.stdout.reconfigure(encoding='utf-8')
iframe_pages = []
container_pages = []
other_pages = []
for root, dirs, files in os.walk('.'):
if '.git' in root or 'node_modules' in root:
continue
for f in files:
if f.endswith('.html'):
path = os.path.join(root, f).replace('\\', '/')
# 除外:common/header.html, common/sidebar.html など共通パーツ自身
if path in ['./common/header.html', './common/sidebar.html']:
continue
with open(path, 'r', encoding='utf-8', errors='ignore') as fp:
content = fp.read()
has_iframe = 'wiki-header-frame' in content or 'wiki-sidebar-frame' in content
has_container = 'wiki-header-container' in content or 'wiki-sidebar-container' in content
if has_iframe:
iframe_pages.append(path)
elif has_container:
container_pages.append(path)
else:
other_pages.append(path)
print(f"iframe形式のページ数: {len(iframe_pages)}")
print(f"container形式のページ数: {len(container_pages)}")
print(f"その他のページ数: {len(other_pages)}")
print("\n--- container形式のサンプル (最大20件) ---")
for p in container_pages[:20]:
print(p)
print("\n--- その他のサンプル (全件) ---")
for p in other_pages:
print(p)
+163
View File
@@ -0,0 +1,163 @@
import os
import re
import sys
sys.stdout.reconfigure(encoding='utf-8')
def extract_content(html):
# 1. titleの抽出
title_match = re.search(r'<title>(.*?)</title>', html, re.DOTALL | re.IGNORECASE)
title = title_match.group(1).strip() if title_match else "FF14 攻略Wiki"
# 2. meta descriptionの抽出
desc_match = re.search(r'<meta\s+name=["\']description["\']\s+content=["\'](.*?)["\']', html, re.DOTALL | re.IGNORECASE)
if not desc_match:
desc_match = re.search(r'<meta\s+content=["\'](.*?)["\']\s+name=["\']description["\']', html, re.DOTALL | re.IGNORECASE)
meta_desc = f' <meta name="description" content="{desc_match.group(1).strip()}">\n' if desc_match else ""
# 3. メインコンテンツの抽出
# パターンA: <main id="wiki-main"> ... </main>
main_match = re.search(r'<main\s+id=["\']wiki-main["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main#wiki-main"
# パターンB: <main class=["\']wiki-main["\']>(.*?)</main>
main_match = re.search(r'<main\s+class=["\']wiki-main["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main.wiki-main"
# パターンC: <main id=["\']wiki-main-container["\']>(.*?)</main>
main_match = re.search(r'<main\s+id=["\']wiki-main-container["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main#wiki-main-container"
# パターンD: <main id=["\']wiki-content["\']>(.*?)</main>
main_match = re.search(r'<main\s+id=["\']wiki-content["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
content = main_match.group(1).strip()
content = re.sub(r'<div\s+id=["\']wiki-breadcrumb["\']>\s*</div>', '', content)
return title, meta_desc, content.strip(), "main#wiki-content"
# パターンE: <div class=["\']wiki-content["\']>(.*?)</div>\s*</main>
main_match = re.search(r'<div\s+class=["\']wiki-content["\']>(.*?)</div>\s*</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "div.wiki-content"
return title, meta_desc, None, "UNKNOWN"
def build_html(filepath, html):
title, meta_desc, content, pattern = extract_content(html)
if not content:
raise ValueError(f"Failed to extract content from {filepath}")
# パンくずリストの整備
has_breadcrumbs = ('wiki-breadcrumbs' in content) or ('wiki-breadcrumb' in content)
is_index = os.path.basename(filepath) == 'index.html'
if not has_breadcrumbs and not is_index:
genre = "ダンジョン攻略" if "dungeons" in filepath else ("レイド攻略" if "raids" in filepath else "討滅戦攻略")
clean_title = re.sub(r'【.*?】', '', title).replace('完全攻略', '').replace('攻略', '').strip()
breadcrumb = f' <div class="wiki-breadcrumbs">\n <a href="../index.html">トップ</a> &gt; <a href="index.html">{genre}</a> &gt; <strong>{clean_title}</strong>\n </div>\n\n'
content = breadcrumb + content
else:
# id="wiki-breadcrumb" を class="wiki-breadcrumbs" に統一
content = re.sub(r'<div\s+id=["\']wiki-breadcrumb["\']>', '<div class="wiki-breadcrumbs">', content)
# 空のパンくずの場合は置換
if re.search(r'<div\s+class=["\']wiki-breadcrumbs["\']>\s*</div>', content):
genre = "ダンジョン攻略" if "dungeons" in filepath else ("レイド攻略" if "raids" in filepath else "討滅戦攻略")
clean_title = re.sub(r'【.*?】', '', title).replace('完全攻略', '').replace('攻略', '').strip()
new_bc = f'<div class="wiki-breadcrumbs">\n <a href="../index.html">トップ</a> &gt; <a href="index.html">{genre}</a> &gt; <strong>{clean_title}</strong>\n </div>'
content = re.sub(r'<div\s+class=["\']wiki-breadcrumbs["\']>\s*</div>', new_bc, content)
template = f'''<!DOCTYPE html>
<html lang="ja">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta http-equiv="Cache-Control" content="no-cache, no-store, must-revalidate">
<meta http-equiv="Pragma" content="no-cache">
<meta http-equiv="Expires" content="0">
<title>{title}</title>
{meta_desc} <link rel="stylesheet" href="../common/css/seesaa_neutral_gray.css">
</head>
<body>
<div id="wiki-wrapper">
<!-- 共通ヘッダー&グローバルナビ(iframe共通化) -->
<iframe src="../common/header.html" class="wiki-header-frame" frameborder="0" scrolling="no"></iframe>
<!-- 2カラムコンテンツ -->
<div id="wiki-container">
<!-- 共通左サイドバー(iframe共通化) -->
<div id="wiki-sidebar">
<iframe src="../common/sidebar.html" class="wiki-sidebar-frame" frameborder="0"></iframe>
</div>
<main id="wiki-main">
{content}
</main>
</div>
<!-- フッター -->
<footer id="wiki-footer">
<p>&copy; SQUARE ENIX CO., LTD. All Rights Reserved. | FINAL FANTASY XIV</p>
<p>FF14 攻略Wiki (Seesaa Wiki ニュートラルグレー テンプレート完全準拠)</p>
</footer>
</div>
<script src="../common/js/wiki_common.js"></script>
</body>
</html>
'''
return template
def normalize_text(text):
lines = text.splitlines()
cleaned = []
prev_blank = False
for line in lines:
stripped = line.rstrip()
is_blank = (len(stripped) == 0)
if is_blank and prev_blank:
continue
cleaned.append(stripped)
prev_blank = is_blank
res = '\r\n'.join(cleaned)
if not res.endswith('\r\n'):
res += '\r\n'
return res
def process_file(filepath):
with open(filepath, 'r', encoding='utf-8', errors='ignore') as fp:
html = fp.read()
new_html = build_html(filepath, html)
normalized = normalize_text(new_html)
with open(filepath, 'wb') as fp:
fp.write(b'\xef\xbb\xbf')
fp.write(normalized.encode('utf-8'))
def main():
target_dirs = ['dungeons', 'raids', 'trials']
processed_files = []
for d in target_dirs:
for f in os.listdir(d):
if f.endswith('.html'):
path = os.path.join(d, f).replace('\\', '/')
with open(path, 'r', encoding='utf-8', errors='ignore') as fp:
content = fp.read()
has_iframe_header = 'wiki-header-frame' in content
has_iframe_sidebar = 'wiki-sidebar-frame' in content
if not (has_iframe_header and has_iframe_sidebar):
process_file(path)
processed_files.append(path)
print(f"変換完了ファイル総数: {len(processed_files)}")
if __name__ == '__main__':
main()
+28
View File
@@ -0,0 +1,28 @@
import os
import sys
sys.stdout.reconfigure(encoding='utf-8')
non_conforming = []
for root, dirs, files in os.walk('.'):
if '.git' in root or 'node_modules' in root:
continue
for f in files:
if f.endswith('.html'):
path = os.path.join(root, f).replace('\\', '/')
if path in ['./common/header.html', './common/sidebar.html', './common/templates/dungeon_raid_template.html']:
continue
with open(path, 'r', encoding='utf-8', errors='ignore') as fp:
content = fp.read()
# 正しいiframe形式か判定: wiki-header-frame と wiki-sidebar-frame が両方あるか
has_iframe_header = 'wiki-header-frame' in content
has_iframe_sidebar = 'wiki-sidebar-frame' in content
if not (has_iframe_header and has_iframe_sidebar):
non_conforming.append(path)
print(f"非準拠ファイル総数: {len(non_conforming)}")
for p in non_conforming:
print(p)
+87
View File
@@ -0,0 +1,87 @@
import os
import re
import sys
sys.stdout.reconfigure(encoding='utf-8')
with open('tools/test_extract.py', 'r', encoding='utf-8') as fp:
code = fp.read()
exec(code[:code.find("test_files = [")])
def build_html(filepath, html):
title, meta_desc, content, pattern = extract_content(html)
# パンくずの確認と補完
has_breadcrumbs = 'wiki-breadcrumbs' in content or 'wiki-breadcrumb' in content
if not has_breadcrumbs:
genre = "ダンジョン攻略" if "dungeons" in filepath else ("レイド攻略" if "raids" in filepath else "討滅戦攻略")
clean_title = re.sub(r'【.*?】', '', title).replace('完全攻略', '').replace('攻略', '').strip()
breadcrumb = f' <div class="wiki-breadcrumbs">\n <a href="../index.html">トップ</a> &gt; <a href="index.html">{genre}</a> &gt; <strong>{clean_title}</strong>\n </div>\n\n'
content = breadcrumb + content
else:
# id="wiki-breadcrumb" を class="wiki-breadcrumbs" に統一
content = re.sub(r'<div\s+id=["\']wiki-breadcrumb["\']>', '<div class="wiki-breadcrumbs">', content)
# 空のパンくずの場合は置換
if '<div class="wiki-breadcrumbs"></div>' in content or '<div class="wiki-breadcrumbs">\s*</div>' in content:
genre = "ダンジョン攻略" if "dungeons" in filepath else ("レイド攻略" if "raids" in filepath else "討滅戦攻略")
clean_title = re.sub(r'【.*?】', '', title).replace('完全攻略', '').replace('攻略', '').strip()
new_bc = f'<div class="wiki-breadcrumbs">\n <a href="../index.html">トップ</a> &gt; <a href="index.html">{genre}</a> &gt; <strong>{clean_title}</strong>\n </div>'
content = re.sub(r'<div class="wiki-breadcrumbs">\s*</div>', new_bc, content)
template = f'''<!DOCTYPE html>
<html lang="ja">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta http-equiv="Cache-Control" content="no-cache, no-store, must-revalidate">
<meta http-equiv="Pragma" content="no-cache">
<meta http-equiv="Expires" content="0">
<title>{title}</title>
{meta_desc} <link rel="stylesheet" href="../common/css/seesaa_neutral_gray.css">
</head>
<body>
<div id="wiki-wrapper">
<!-- 共通ヘッダー&グローバルナビ(iframe共通化) -->
<iframe src="../common/header.html" class="wiki-header-frame" frameborder="0" scrolling="no"></iframe>
<!-- 2カラムコンテンツ -->
<div id="wiki-container">
<!-- 共通左サイドバー(iframe共通化) -->
<div id="wiki-sidebar">
<iframe src="../common/sidebar.html" class="wiki-sidebar-frame" frameborder="0"></iframe>
</div>
<main id="wiki-main">
{content}
</main>
</div>
<!-- フッター -->
<footer id="wiki-footer">
<p>&copy; SQUARE ENIX CO., LTD. All Rights Reserved. | FINAL FANTASY XIV</p>
<p>FF14 攻略Wiki (Seesaa Wiki ニュートラルグレー テンプレート完全準拠)</p>
</footer>
</div>
<script src="../common/js/wiki_common.js"></script>
</body>
</html>
'''
return template
for p in ['trials/ultima_weapon.html', 'trials/extreme_hades.html']:
with open(p, 'r', encoding='utf-8', errors='ignore') as fp:
html = fp.read()
res = build_html(p, html)
lines = res.splitlines()
print(f"=== {p} PREVIEW (最初の35行) ===")
for l in lines[:35]:
print(l)
print(f"=== {p} PREVIEW (最後の20行) ===")
for l in lines[-20:]:
print(l)
print("\n" + "="*50 + "\n")
+64
View File
@@ -0,0 +1,64 @@
import os
import re
import sys
sys.stdout.reconfigure(encoding='utf-8')
def extract_content(html):
# 1. titleの抽出
title_match = re.search(r'<title>(.*?)</title>', html, re.DOTALL | re.IGNORECASE)
title = title_match.group(1).strip() if title_match else "FF14 攻略Wiki"
# 2. meta descriptionの抽出
desc_match = re.search(r'<meta\s+name=["\']description["\']\s+content=["\'](.*?)["\']', html, re.DOTALL | re.IGNORECASE)
if not desc_match:
desc_match = re.search(r'<meta\s+content=["\'](.*?)["\']\s+name=["\']description["\']', html, re.DOTALL | re.IGNORECASE)
meta_desc = f' <meta name="description" content="{desc_match.group(1).strip()}">\n' if desc_match else ""
# 3. メインコンテンツの抽出
# パターンA: <main id="wiki-main"> ... </main>
main_match = re.search(r'<main\s+id=["\']wiki-main["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main#wiki-main"
# パターンB: <main class=["\']wiki-main["\']>(.*?)</main>
main_match = re.search(r'<main\s+class=["\']wiki-main["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main.wiki-main"
# パターンC: <main id=["\']wiki-main-container["\']>(.*?)</main>
main_match = re.search(r'<main\s+id=["\']wiki-main-container["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "main#wiki-main-container"
# パターンD: <main id=["\']wiki-content["\']>(.*?)</main>
main_match = re.search(r'<main\s+id=["\']wiki-content["\']>(.*?)</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
content = main_match.group(1).strip()
# 空のパンくず除外
content = re.sub(r'<div id=["\']wiki-breadcrumb["\']>\s*</div>', '', content)
return title, meta_desc, content.strip(), "main#wiki-content"
# パターンE: <div class=["\']wiki-content["\']>(.*?)</div>\s*</main>
main_match = re.search(r'<div\s+class=["\']wiki-content["\']>(.*?)</div>\s*</main>', html, re.DOTALL | re.IGNORECASE)
if main_match:
return title, meta_desc, main_match.group(1).strip(), "div.wiki-content"
return title, meta_desc, None, "UNKNOWN"
test_files = [
'trials/ultima_weapon.html',
'trials/extreme_hades.html',
'trials/garuda.html',
'dungeons/amdapor_keep_hard.html',
'dungeons/aurum_vale.html',
'dungeons/index.html',
'raids/syrcus_tower.html',
'raids/index.html'
]
for p in test_files:
with open(p, 'r', encoding='utf-8', errors='ignore') as fp:
html = fp.read()
t, d, c, pattern = extract_content(html)
print(f"File: {p:<35} | Pattern: {pattern:<25} | Title: {t[:30]} | Content Length: {len(c) if c else 0}")
+20
View File
@@ -0,0 +1,20 @@
import re
import sys
sys.stdout.reconfigure(encoding='utf-8')
with open('tools/test_convert_preview.py', 'r', encoding='utf-8') as fp:
code = fp.read()
target = "for p in ['trials/ultima_weapon.html'"
exec(code[:code.find(target)])
with open('dungeons/index.html', 'r', encoding='utf-8') as fp:
html = fp.read()
res = build_html('dungeons/index.html', html)
lines = res.splitlines()
print('=== dungeons/index.html PREVIEW (最初の40行) ===')
for l in lines[:40]:
print(l)
print('=== dungeons/index.html PREVIEW (最後の20行) ===')
for l in lines[-20:]:
print(l)