yakenator/web-inspector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: 4개 검사 엔진을 YAML 기반 표준 규칙으로 리팩토링

Browse Source 
- YAML 규칙 파일 4개 신규 생성 (html_css, accessibility, seo, performance_security)
  W3C, WCAG 2.0/2.1/2.2, OWASP, Google Search Essentials 공식 표준 기반
- rules/__init__.py: YAML 로더 + 캐싱 + 리로드 모듈
- html_css.py: 30개 폐기 요소, 100+개 폐기 속성을 YAML에서 동적 로드
- accessibility.py: WCAG 버전 선택 지원 (wcag_version 파라미터)
- seo.py: title/description 길이, OG 필수 태그 등 임계값 YAML 로드
- performance_security.py: COOP/COEP/CORP 검사 추가, 정보 노출 헤더 검사 추가,
  TTFB/페이지 크기 임계값 YAML 로드
- PyYAML 의존성 추가

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
jungwoo choi
2026-02-13 15:49:57 +09:00
parent cdb6405714
commit 44ad36e2ab
10 changed files with 3393 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

144
backend/app/engines/html_css.py
View File

@ -2,6 +2,7 @@
HTML/CSS Standards Checker Engine (F-002).
Checks HTML5 validity, semantic tags, CSS inline usage, etc.
Uses BeautifulSoup4 + html5lib for parsing.
Rules loaded from rules/html_css.yaml.
"""
import re
@ -13,15 +14,28 @@ from bs4 import BeautifulSoup
from app.engines.base import BaseChecker
from app.models.schemas import CategoryResult, Issue
from app.rules import get_rules
logger = logging.getLogger(__name__)
DEPRECATED_TAGS = [
"font", "center", "marquee", "blink", "strike", "big", "tt",
"basefont", "applet", "dir", "isindex",
]
SEMANTIC_TAGS = ["header", "nav", "main", "footer", "section", "article"]
def _load_obsolete_elements() -> list[dict]:
"""Load obsolete elements from YAML."""
rules = get_rules("html_css")
return rules.get("obsolete_elements", [])
def _load_obsolete_attributes() -> dict[str, list[dict]]:
"""Load obsolete attributes from YAML, keyed by element name."""
rules = get_rules("html_css")
return rules.get("obsolete_attributes", {})
def _load_semantic_tags() -> list[str]:
"""Load structural semantic tag names from YAML."""
rules = get_rules("html_css")
structural = rules.get("semantic_elements", {}).get("structural", [])
return [item["tag"] for item in structural]
class HtmlCssChecker(BaseChecker):
@ -50,16 +64,21 @@ class HtmlCssChecker(BaseChecker):
await self.update_progress(50, "시맨틱 태그 검사 중...")
issues += self._check_semantic_tags(soup)
await self.update_progress(60, "이미지 alt 속성 검사 중...")
await self.update_progress(55, "이미지 alt 속성 검사 중...")
issues += self._check_img_alt(soup)
await self.update_progress(70, "중복 ID 검사 중...")
await self.update_progress(60, "중복 ID 검사 중...")
issues += self._check_duplicate_ids(soup)
await self.update_progress(80, "링크 및 스타일 검사 중...")
await self.update_progress(65, "링크 및 스타일 검사 중...")
issues += self._check_empty_links(soup)
issues += self._check_inline_styles(soup)
issues += self._check_deprecated_tags(soup)
await self.update_progress(75, "Obsolete 태그 검사 중...")
issues += self._check_obsolete_tags(soup)
await self.update_progress(80, "Obsolete 속성 검사 중...")
issues += self._check_obsolete_attributes(soup)
await self.update_progress(90, "heading 구조 검사 중...")
issues += self._check_heading_hierarchy(soup)
@ -134,21 +153,22 @@ class HtmlCssChecker(BaseChecker):
def _check_semantic_tags(self, soup: BeautifulSoup) -> list[Issue]:
"""H-05: Check for semantic HTML5 tag usage."""
semantic_tags = _load_semantic_tags()
found_tags = set()
for tag_name in SEMANTIC_TAGS:
for tag_name in semantic_tags:
if soup.find(tag_name):
found_tags.add(tag_name)
if not found_tags:
tag_list = ", ".join(semantic_tags)
return [self._create_issue(
code="H-05",
severity="minor",
message="시맨틱 태그가 사용되지 않았습니다 (header, nav, main, footer, section, article)",
message=f"시맨틱 태그가 사용되지 않았습니다 ({tag_list})",
suggestion="적절한 시맨틱 태그를 사용하여 문서 구조를 명확히 하세요",
)]
missing = set(SEMANTIC_TAGS) - found_tags
# Only report if major structural elements are missing (main is most important)
missing = set(semantic_tags) - found_tags
if "main" in missing:
return [self._create_issue(
code="H-05",
@ -240,23 +260,105 @@ class HtmlCssChecker(BaseChecker):
))
return issues
def _check_deprecated_tags(self, soup: BeautifulSoup) -> list[Issue]:
"""H-10: Check for deprecated HTML tags."""
def _check_obsolete_tags(self, soup: BeautifulSoup) -> list[Issue]:
"""H-10: Check for obsolete HTML tags (loaded from YAML)."""
issues = []
for tag_name in DEPRECATED_TAGS:
obsolete = _load_obsolete_elements()
for entry in obsolete:
tag_name = entry["tag"]
found = soup.find_all(tag_name)
if found:
replacement = entry.get("replacement", "CSS")
severity = entry.get("severity", "major")
first_el = found[0]
issues.append(self._create_issue(
code="H-10",
severity="major",
message=f"사용 중단된(deprecated) 태그 <{tag_name}>이(가) {len(found)}회 사용되었습니다",
severity=severity,
message=f"사용 중단된(obsolete) 태그 <{tag_name}>이(가) {len(found)}회 사용되었습니다",
element=self._truncate_element(str(first_el)),
line=self._get_line_number(first_el),
suggestion=f"<{tag_name}> 대신 CSS를 사용하여 스타일을 적용하세요",
suggestion=f"<{tag_name}> 대신 {replacement}을(를) 사용하세요",
))
return issues
def _check_obsolete_attributes(self, soup: BeautifulSoup) -> list[Issue]:
"""H-13: Check for obsolete HTML attributes (loaded from YAML)."""
issues = []
obsolete_attrs = _load_obsolete_attributes()
# Check element-specific obsolete attributes
element_checks = {
"a": "a", "body": "body", "br": "br", "form": "form",
"hr": "hr", "html": "html", "iframe": "iframe", "img": "img",
"input": "input", "link": "link", "meta": "meta", "script": "script",
"style": "style", "table": "table", "embed": "embed",
}
# Multi-element groups
multi_checks = {
"td_th": ["td", "th"],
"tr": ["tr"],
"thead_tbody_tfoot": ["thead", "tbody", "tfoot"],
"ol_ul": ["ol", "ul"],
"heading": ["h1", "h2", "h3", "h4", "h5", "h6"],
"embed": ["embed"],
}
found_count = 0
first_element = None
first_line = None
first_attr = None
# Single-element checks
for yaml_key, html_tag in element_checks.items():
attr_list = obsolete_attrs.get(yaml_key, [])
for attr_entry in attr_list:
attr_name = attr_entry["attr"]
elements = soup.find_all(html_tag, attrs={attr_name: True})
if elements:
found_count += len(elements)
if first_element is None:
first_element = self._truncate_element(str(elements[0]))
first_line = self._get_line_number(elements[0])
first_attr = f'{html_tag}[{attr_name}]'
# Multi-element group checks
for yaml_key, html_tags in multi_checks.items():
attr_list = obsolete_attrs.get(yaml_key, [])
for attr_entry in attr_list:
attr_name = attr_entry["attr"]
for html_tag in html_tags:
elements = soup.find_all(html_tag, attrs={attr_name: True})
if elements:
found_count += len(elements)
if first_element is None:
first_element = self._truncate_element(str(elements[0]))
first_line = self._get_line_number(elements[0])
first_attr = f'{html_tag}[{attr_name}]'
# Global obsolete attributes
global_attrs = obsolete_attrs.get("global", [])
for attr_entry in global_attrs:
attr_name = attr_entry["attr"]
elements = soup.find_all(attrs={attr_name: True})
if elements:
found_count += len(elements)
if first_element is None:
first_element = self._truncate_element(str(elements[0]))
first_line = self._get_line_number(elements[0])
first_attr = attr_name
if found_count > 0:
issues.append(self._create_issue(
code="H-13",
severity="minor",
message=f"사용 중단된(obsolete) HTML 속성이 {found_count}개 발견되었습니다 (예: {first_attr})",
element=first_element,
line=first_line,
suggestion="사용 중단된 HTML 속성 대신 CSS를 사용하세요 (W3C HTML Living Standard 참조)",
))
return issues
def _check_heading_hierarchy(self, soup: BeautifulSoup) -> list[Issue]:
"""H-11: Check heading hierarchy (h1-h6 should not skip levels)."""
issues = []
@ -277,7 +379,7 @@ class HtmlCssChecker(BaseChecker):
line=self._get_line_number(heading),
suggestion=f"h{prev_level} 다음에는 h{prev_level + 1}을 사용하세요",
))
break # Only report first skip
break
prev_level = level
return issues
@ -295,14 +397,12 @@ class HtmlCssChecker(BaseChecker):
@staticmethod
def _get_line_number(element) -> Optional[int]:
"""Extract source line number from a BeautifulSoup element."""
if element and hasattr(element, "sourceline"):
return element.sourceline
return None
@staticmethod
def _truncate_element(element_str: str, max_len: int = 200) -> str:
"""Truncate element string for display."""
if len(element_str) > max_len:
return element_str[:max_len] + "..."
return element_str