자유게시판 오류 수정
This commit is contained in:
Binary file not shown.
@@ -2,6 +2,7 @@ from http.server import BaseHTTPRequestHandler, HTTPServer
|
|||||||
from urllib.request import Request, urlopen
|
from urllib.request import Request, urlopen
|
||||||
from urllib.error import URLError, HTTPError
|
from urllib.error import URLError, HTTPError
|
||||||
import re
|
import re
|
||||||
|
from html import unescape
|
||||||
|
|
||||||
TARGET_URL = "https://m.slrclub.com/l/free"
|
TARGET_URL = "https://m.slrclub.com/l/free"
|
||||||
|
|
||||||
@@ -26,21 +27,93 @@ class ProxyHandler(BaseHTTPRequestHandler):
|
|||||||
charset = response.headers.get_content_charset(failobj="utf-8")
|
charset = response.headers.get_content_charset(failobj="utf-8")
|
||||||
raw_html = response.read().decode(charset, errors="replace")
|
raw_html = response.read().decode(charset, errors="replace")
|
||||||
|
|
||||||
# Rewrite relative links to use this local proxy.
|
# Extract up to 10 post entries (제목 + 링크) and render a simple list.
|
||||||
if "<head" in raw_html.lower():
|
items = []
|
||||||
host = self.headers.get("Host", f"localhost:{self.server.server_port}")
|
|
||||||
raw_html = re.sub(
|
# First try: find anchors inside list items (common for post lists)
|
||||||
r"(<head[^>]*>)",
|
li_blocks = re.findall(r"<li[^>]*>(.*?)</li>", raw_html, flags=re.DOTALL | re.IGNORECASE)
|
||||||
rf"\1<base href=\"http://{host}/\" />",
|
for block in li_blocks:
|
||||||
raw_html,
|
m = re.search(r"<a[^>]+href=[\"']([^\"']+)[\"'][^>]*>(.*?)</a>", block, flags=re.DOTALL | re.IGNORECASE)
|
||||||
count=1,
|
if m:
|
||||||
flags=re.IGNORECASE,
|
href = m.group(1).strip()
|
||||||
)
|
anchor_html = m.group(0)
|
||||||
|
inner_html = m.group(2)
|
||||||
|
txt = re.sub(r"<[^>]+>", "", inner_html).strip()
|
||||||
|
txt = unescape(txt)
|
||||||
|
|
||||||
|
# If inner text is empty, try anchor title or image alt attributes
|
||||||
|
if not txt:
|
||||||
|
t = re.search(r'title=["\']([^"\']+)["\']', anchor_html, flags=re.IGNORECASE)
|
||||||
|
if t:
|
||||||
|
txt = unescape(t.group(1).strip())
|
||||||
|
|
||||||
|
if not txt:
|
||||||
|
img_alt = re.search(r'<img[^>]+alt=["\']([^"\']+)["\']', anchor_html, flags=re.IGNORECASE)
|
||||||
|
if img_alt:
|
||||||
|
txt = unescape(img_alt.group(1).strip())
|
||||||
|
|
||||||
|
# Only append if we have a non-empty title
|
||||||
|
if txt:
|
||||||
|
items.append((href, txt))
|
||||||
|
|
||||||
|
# Fallback: collect anchors from whole page if no list-items found
|
||||||
|
if not items:
|
||||||
|
anchors = re.findall(r"<a[^>]+href=[\"']([^\"']+)[\"'][^>]*>(.*?)</a>", raw_html, flags=re.DOTALL | re.IGNORECASE)
|
||||||
|
for href, txt_html in anchors:
|
||||||
|
href = href.strip()
|
||||||
|
txt = re.sub(r"<[^>]+>", "", txt_html).strip()
|
||||||
|
txt = unescape(txt)
|
||||||
|
if txt and not href.lower().startswith("javascript:"):
|
||||||
|
items.append((href, txt))
|
||||||
|
|
||||||
|
# Deduplicate and filter out obvious navigation/header links
|
||||||
|
seen = set()
|
||||||
|
filtered = []
|
||||||
|
for href, txt in items:
|
||||||
|
key = (href, txt)
|
||||||
|
if key in seen:
|
||||||
|
continue
|
||||||
|
seen.add(key)
|
||||||
|
lowtxt = (txt or "").strip().lower()
|
||||||
|
if href in ("#", "/", "", "/l/free"):
|
||||||
|
continue
|
||||||
|
if lowtxt in ("홈", "로그인", "검색", "공지", "more", "더보기"):
|
||||||
|
continue
|
||||||
|
filtered.append((href, txt))
|
||||||
|
|
||||||
|
# Skip the top 5 posts and show the next 10
|
||||||
|
posts = filtered[5:5+10]
|
||||||
|
|
||||||
|
# Build simple HTML list for posts only
|
||||||
|
host = self.headers.get("Host", f"localhost:{self.server.server_port}")
|
||||||
|
out_lines = [
|
||||||
|
'<!doctype html>',
|
||||||
|
'<html><head><meta charset="utf-8"><title>SLRClub - 게시글 목록</title></head><body>',
|
||||||
|
'<h1>게시글 (최대 10개)</h1>',
|
||||||
|
'<ul>'
|
||||||
|
]
|
||||||
|
for href, txt in posts:
|
||||||
|
# Build absolute URL to original site so clicks open the real page
|
||||||
|
abs_url = href
|
||||||
|
if href.startswith("/"):
|
||||||
|
abs_url = "https://m.slrclub.com" + href
|
||||||
|
elif href.startswith("//"):
|
||||||
|
abs_url = "https:" + href
|
||||||
|
elif not href.startswith("http"):
|
||||||
|
# relative path without leading slash
|
||||||
|
abs_url = "https://m.slrclub.com/" + href.lstrip("/")
|
||||||
|
|
||||||
|
# Escape minimal characters in title
|
||||||
|
safe_txt = txt.replace("<", "<").replace(">", ">")
|
||||||
|
out_lines.append(f'<li><a href="{abs_url}" target="_blank" rel="noopener noreferrer">{safe_txt}</a></li>')
|
||||||
|
|
||||||
|
out_lines.extend(["</ul>", "</body></html>"])
|
||||||
|
out = "\n".join(out_lines)
|
||||||
|
|
||||||
self.send_response(200)
|
self.send_response(200)
|
||||||
self.send_header("Content-Type", f"{content_type}; charset={charset}")
|
self.send_header("Content-Type", "text/html; charset=utf-8")
|
||||||
self.end_headers()
|
self.end_headers()
|
||||||
self.wfile.write(raw_html.encode(charset, errors="replace"))
|
self.wfile.write(out.encode("utf-8", errors="replace"))
|
||||||
|
|
||||||
except HTTPError as e:
|
except HTTPError as e:
|
||||||
self.send_response(e.code)
|
self.send_response(e.code)
|
||||||
|
|||||||
Reference in New Issue
Block a user