Files
ff14-guide/tools/test_extract.py
T

65 lines
2.8 KiB
Python

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}")