Naver Blog Research

__pycache__/
*.pyc
naver-images/


"""Shared HTTP utilities for Naver blog scripts (SSL handling, URL validation, urlopen wrapper)."""

from __future__ import annotations

import re
import ssl
import sys
import urllib.error
import urllib.parse
import urllib.request


TAG_RE = re.compile(r"<[^>]+>")

_ssl_ctx_secure: ssl.SSLContext | None = None
_ssl_ctx_insecure: ssl.SSLContext | None = None


def _get_ssl_context(*, insecure: bool = False) -> ssl.SSLContext:
    global _ssl_ctx_secure, _ssl_ctx_insecure
    if insecure:
        if _ssl_ctx_insecure is None:
            ctx = ssl.create_default_context()
            ctx.check_hostname = False
            ctx.verify_mode = ssl.CERT_NONE
            _ssl_ctx_insecure = ctx
        return _ssl_ctx_insecure
    if _ssl_ctx_secure is None:
        _ssl_ctx_secure = ssl.create_default_context()
    return _ssl_ctx_secure


_NAVER_DOMAINS = (".naver.com", ".naver.net", ".pstatic.net")


def is_naver_url(url: str) -> bool:
    host = urllib.parse.urlparse(url).hostname or ""
    return any(host == d.lstrip(".") or host.endswith(d) for d in _NAVER_DOMAINS)


def urlopen(request: urllib.request.Request, timeout: int, *, insecure: bool = False):
    """urlopen with explicit SSL insecure mode for Naver domains.

    When *insecure* is True and the target is a Naver domain, SSL certificate
    verification is skipped.  A warning is printed to stderr on every call so
    the caller is always aware.
    """
    if insecure:
        if not is_naver_url(request.full_url):
            raise ValueError("insecure 모드는 네이버 도메인에만 사용할 수 있습니다.")
        print(
            "[warn] SSL 인증서 검증이 비활성화되었습니다. 연결이 안전하지 않을 수 있습니다.",
            file=sys.stderr,
        )
        return urllib.request.urlopen(
            request, timeout=timeout, context=_get_ssl_context(insecure=True),
        )
    return urllib.request.urlopen(request, timeout=timeout, context=_get_ssl_context())


from __future__ import annotations

import argparse
import json
import os
import sys
import urllib.error
import urllib.request
from concurrent.futures import ThreadPoolExecutor, as_completed

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from _naver_http import is_naver_url, urlopen

DEFAULT_OUTPUT_DIR = "./naver-images"
DEFAULT_MAX = 10
DEFAULT_TIMEOUT = 15

DEFAULT_HEADERS = {
    "Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
    "Accept-Language": "ko,en-US;q=0.9,en;q=0.8",
    "Referer": "https://m.blog.naver.com/",
    "User-Agent": (
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
        "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36"
    ),
}

CONTENT_TYPE_TO_EXT = {
    "image/jpeg": ".jpg",
    "image/png": ".png",
    "image/gif": ".gif",
    "image/webp": ".webp",
    "image/bmp": ".bmp",
    "image/svg+xml": ".svg",
}


_MAGIC_BYTES = (
    (b"\x89PNG\r\n\x1a\n", ".png"),
    (b"GIF87a", ".gif"),
    (b"GIF89a", ".gif"),
    (b"RIFF", ".webp"),  # WebP: RIFF....WEBP (check first 4 bytes)
    (b"BM", ".bmp"),
)


def guess_extension(url: str, content_type: str | None = None, data: bytes | None = None) -> str:
    if content_type:
        ct = content_type.split(";")[0].strip().lower()
        if ct in CONTENT_TYPE_TO_EXT:
            return CONTENT_TYPE_TO_EXT[ct]

    lower_url = url.lower().split("?")[0]
    for ext in (".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp", ".svg"):
        if lower_url.endswith(ext):
            return ".jpg" if ext == ".jpeg" else ext

    if data:
        for magic, ext in _MAGIC_BYTES:
            if data[:len(magic)] == magic:
                if ext == ".webp" and data[8:12] != b"WEBP":
                    continue
                return ext
        if data[:2] in (b"\xff\xd8",):
            return ".jpg"

    return ".jpg"


def download_image(url: str, output_path: str, output_dir: str, timeout: int = DEFAULT_TIMEOUT, *, insecure: bool = False) -> dict:
    """Download a single image from a Naver CDN URL.

    *output_dir*