173 lines
7.0 KiB
Python
173 lines
7.0 KiB
Python
"""collect 단계 - HTML/CSS 텍스트에서 brand 로고 URL + 색상 추출"""
|
|
import logging
|
|
import re
|
|
from collections import Counter
|
|
from urllib.parse import urljoin
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
# ── 로고 URL 추출 ─────────────────────────────────────────────────────────────
|
|
|
|
|
|
LOGO_IMG_PATTERNS = [
|
|
re.compile(r'<img[^>]*\bclass=["\'][^"\']*\blogo\b[^"\']*["\'][^>]*\bsrc=["\']([^"\']+)["\']', re.IGNORECASE),
|
|
re.compile(r'<img[^>]*\bsrc=["\']([^"\']+)["\'][^>]*\bclass=["\'][^"\']*\blogo\b[^"\']*["\']', re.IGNORECASE),
|
|
re.compile(r'<img[^>]*\bid=["\'][^"\']*\blogo\b[^"\']*["\'][^>]*\bsrc=["\']([^"\']+)["\']', re.IGNORECASE),
|
|
re.compile(r'<img[^>]*\balt=["\'][^"\']*\blogo\b[^"\']*["\'][^>]*\bsrc=["\']([^"\']+)["\']', re.IGNORECASE),
|
|
re.compile(r'<(?:a|h[1-6]|div|span)[^>]*\b(?:class|id)=["\'][^"\']*\blogo\b[^"\']*["\'][^>]*>(?:[^<]|<(?!img))*<img[^>]*\bsrc=["\']([^"\']+)["\']', re.IGNORECASE | re.DOTALL),
|
|
re.compile(r'<(?:a|div|span|h[1-6])[^>]*\b(?:class|id)=["\'][^"\']*\blogo\b[^"\']*["\'][^>]*\bstyle=["\'][^"\']*background(?:-image)?\s*:\s*url\(\s*["\']?([^"\')\s]+)', re.IGNORECASE),
|
|
re.compile(r'<(?:a|div|span|h[1-6])[^>]*\bstyle=["\'][^"\']*background(?:-image)?\s*:\s*url\(\s*["\']?([^"\')\s]+)[^"\']*["\'][^>]*\b(?:class|id)=["\'][^"\']*\blogo\b', re.IGNORECASE),
|
|
re.compile(r'<img[^>]*\bsrc=["\']([^"\']*\blogo\b[^"\']*\.(?:png|svg|jpe?g|webp)[^"\']*)["\']', re.IGNORECASE),
|
|
re.compile(r'<header\b[^>]*>(?:[^<]|<(?!img))*<img[^>]*\bsrc=["\']([^"\']+\.(?:png|svg|jpe?g|webp)[^"\']*)["\']', re.IGNORECASE | re.DOTALL),
|
|
re.compile(r'<nav\b[^>]*>(?:[^<]|<(?!img))*<img[^>]*\bsrc=["\']([^"\']+\.(?:png|svg|jpe?g|webp)[^"\']*)["\']', re.IGNORECASE | re.DOTALL),
|
|
re.compile(r'<meta[^>]*\bproperty=["\']og:image["\'][^>]*\bcontent=["\']([^"\']+)["\']', re.IGNORECASE),
|
|
re.compile(r'<meta[^>]*\bcontent=["\']([^"\']+)["\'][^>]*\bproperty=["\']og:image["\']', re.IGNORECASE),
|
|
]
|
|
|
|
LOGO_CSS_PATTERN = re.compile(
|
|
r'\.[\w-]*\blogo\b[\w-]*\s*(?:,\s*\.[\w-]+\s*)*\{[^}]*background(?:-image)?\s*:\s*url\(\s*["\']?([^"\')\s]+)',
|
|
re.IGNORECASE | re.DOTALL,
|
|
)
|
|
|
|
|
|
def find_logo_url_in_html(html: str, base_url: str, css_texts: list[str] | None = None) -> str | None:
|
|
"""HTML 에서 logo URL 찾기. 우선순위: 1) class/id/alt 명시 img 2) 외부 CSS .logo bg 3) header/nav 첫 img."""
|
|
|
|
def _is_noise(src: str) -> bool:
|
|
if not src or src.startswith("data:"):
|
|
return True
|
|
if re.search(r"(blank|spacer|pixel|transparent|1x1)\b", src, re.IGNORECASE):
|
|
return True
|
|
if re.search(r"(lang[-_]?(kor|eng|chn|jpn|rus|jp|en|ko|cn|ar|in)|flag|country|icon-|btn-|arrow|prev|next|search)\b", src, re.IGNORECASE):
|
|
return True
|
|
return False
|
|
|
|
for pat in LOGO_IMG_PATTERNS[:8]:
|
|
for m in pat.finditer(html):
|
|
src = m.group(1)
|
|
if _is_noise(src):
|
|
continue
|
|
return urljoin(base_url, src)
|
|
|
|
for css in (css_texts or []):
|
|
m = LOGO_CSS_PATTERN.search(css)
|
|
if m:
|
|
src = m.group(1)
|
|
if not _is_noise(src):
|
|
return urljoin(base_url, src)
|
|
|
|
for pat in LOGO_IMG_PATTERNS[8:]:
|
|
for m in pat.finditer(html):
|
|
src = m.group(1)
|
|
if _is_noise(src):
|
|
continue
|
|
return urljoin(base_url, src)
|
|
|
|
return None
|
|
|
|
|
|
# ── 색상 추출 ────────────────────────────────────────────────────────────────
|
|
|
|
|
|
HEX6 = re.compile(r"#([0-9a-fA-F]{6})\b")
|
|
HEX3 = re.compile(r"#([0-9a-fA-F]{3})\b(?![0-9a-fA-F])")
|
|
RGB = re.compile(r"rgba?\(\s*(\d{1,3})\s*,\s*(\d{1,3})\s*,\s*(\d{1,3})\s*(?:,\s*[\d.]+\s*)?\)")
|
|
STYLE_BLOCK = re.compile(r"<style[^>]*>(.*?)</style>", re.IGNORECASE | re.DOTALL)
|
|
|
|
NOISE = {
|
|
"#ffffff", "#000000", "#fff", "#000",
|
|
"#333", "#222", "#111", "#444", "#555", "#666", "#777", "#888", "#999",
|
|
"#aaa", "#bbb", "#ccc", "#ddd", "#eee", "#f0f0f0", "#f5f5f5", "#fafafa",
|
|
}
|
|
|
|
|
|
def _normalize(hex_str: str) -> str:
|
|
h = hex_str.lstrip("#").lower()
|
|
if len(h) == 3:
|
|
h = "".join(c * 2 for c in h)
|
|
if len(h) == 8:
|
|
h = h[:6]
|
|
return f"#{h}"
|
|
|
|
|
|
def _rgb_to_hex(r: int, g: int, b: int) -> str:
|
|
return f"#{r:02x}{g:02x}{b:02x}"
|
|
|
|
|
|
def _hex_to_rgb(h: str) -> tuple[int, int, int]:
|
|
h = h.lstrip("#")
|
|
return int(h[0:2], 16), int(h[2:4], 16), int(h[4:6], 16)
|
|
|
|
|
|
def _distance(a: str, b: str) -> float:
|
|
ar, ag, ab = _hex_to_rgb(a)
|
|
br, bg, bb = _hex_to_rgb(b)
|
|
return ((ar - br) ** 2 + (ag - bg) ** 2 + (ab - bb) ** 2) ** 0.5
|
|
|
|
|
|
def _is_grayscale(h: str, tol: int = 12) -> bool:
|
|
r, g, b = _hex_to_rgb(h)
|
|
return max(r, g, b) - min(r, g, b) < tol
|
|
|
|
|
|
def _extract_hex(text: str) -> list[str]:
|
|
out: list[str] = []
|
|
out.extend(_normalize(m.group(0)) for m in HEX6.finditer(text))
|
|
out.extend(_normalize(m.group(0)) for m in HEX3.finditer(text))
|
|
for m in RGB.finditer(text):
|
|
r, g, b = int(m.group(1)), int(m.group(2)), int(m.group(3))
|
|
if 0 <= r <= 255 and 0 <= g <= 255 and 0 <= b <= 255:
|
|
out.append(_rgb_to_hex(r, g, b))
|
|
return out
|
|
|
|
|
|
def _cluster(colors: Counter, threshold: float = 25.0) -> list[tuple[str, int]]:
|
|
ranked = colors.most_common()
|
|
clusters: list[tuple[str, int]] = []
|
|
for color, count in ranked:
|
|
merged = False
|
|
for i, (rep, rep_count) in enumerate(clusters):
|
|
if _distance(color, rep) < threshold:
|
|
clusters[i] = (rep, rep_count + count)
|
|
merged = True
|
|
break
|
|
if not merged:
|
|
clusters.append((color, count))
|
|
return clusters
|
|
|
|
|
|
def extract_brand_colors_from_text(html: str, css_texts: list[str], source_url: str = "") -> dict:
|
|
"""HTML + CSS 텍스트에서 hex 빈도 분석 → primary/accent/text + palette. (fetch 없음)"""
|
|
all_text_chunks: list[str] = list(STYLE_BLOCK.findall(html))
|
|
all_text_chunks.append(html)
|
|
all_text_chunks.extend(css_texts)
|
|
|
|
counter: Counter = Counter()
|
|
for text in all_text_chunks:
|
|
for color in _extract_hex(text):
|
|
if color in NOISE:
|
|
continue
|
|
counter[color] += 1
|
|
|
|
if not counter:
|
|
logger.info("[brand_parser] no colors extracted from %s", source_url)
|
|
return {}
|
|
|
|
clustered = _cluster(counter)
|
|
chromatic = [c for c, _ in clustered if not _is_grayscale(c)]
|
|
grayscale = [c for c, _ in clustered if _is_grayscale(c)]
|
|
|
|
palette_top = clustered[:8]
|
|
palette = [{"name": f"색상 {i+1}", "hex": h, "usage": f"빈도 {n}"} for i, (h, n) in enumerate(palette_top)]
|
|
|
|
return {
|
|
"brand_colors": {
|
|
"primary": chromatic[0] if chromatic else None,
|
|
"accent": chromatic[1] if len(chromatic) > 1 else None,
|
|
"text": grayscale[0] if grayscale else None,
|
|
},
|
|
"color_palette": palette,
|
|
"extracted_from": "html+css",
|
|
}
|