slrclub자유게시판 크롤링.

README.md

@@ -0,0 +1,21 @@
+# SLRClub Mobile Free Page Proxy
+
+This simple Python web server fetches and displays the mobile free page from `https://m.slrclub.com/l/free`.
+
+## Run
+
+```bash
+python3 app.py
+```
+
+Then open:
+
+```text
+http://localhost:8000/
+```
+
+## Notes
+
+- The server uses Python built-in libraries only.
+- Relative links and resources are resolved with a `<base>` tag.
+- If the target page cannot be fetched, an error message is shown.

app.py

@@ -0,0 +1,80 @@
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from urllib.request import Request, urlopen
+from urllib.error import URLError, HTTPError
+import re
+
+TARGET_URL = "https://m.slrclub.com/l/free"
+
+class ProxyHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        requested_path = self.path
+        if requested_path == "/" or requested_path == "":
+            requested_path = "/l/free"
+
+        target_url = f"https://m.slrclub.com{requested_path}"
+
+        try:
+            req = Request(
+                target_url,
+                headers={
+                    "User-Agent": "Mozilla/5.0 (compatible; Python crawler/1.0)",
+                    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+                },
+            )
+            with urlopen(req, timeout=15) as response:
+                content_type = response.headers.get_content_type()
+                charset = response.headers.get_content_charset(failobj="utf-8")
+                raw_html = response.read().decode(charset, errors="replace")
+
+            # Rewrite relative links to use this local proxy.
+            if "<head" in raw_html.lower():
+                host = self.headers.get("Host", f"localhost:{self.server.server_port}")
+                raw_html = re.sub(
+                    r"(<head[^>]*>)",
+                    rf"\1<base href=\"http://{host}/\" />",
+                    raw_html,
+                    count=1,
+                    flags=re.IGNORECASE,
+                )
+
+            self.send_response(200)
+            self.send_header("Content-Type", f"{content_type}; charset={charset}")
+            self.end_headers()
+            self.wfile.write(raw_html.encode(charset, errors="replace"))
+
+        except HTTPError as e:
+            self.send_response(e.code)
+            self.send_header("Content-Type", "text/plain; charset=utf-8")
+            self.end_headers()
+            self.wfile.write(f"HTTP Error: {e.code} {e.reason}".encode("utf-8"))
+        except URLError as e:
+            self.send_response(502)
+            self.send_header("Content-Type", "text/plain; charset=utf-8")
+            self.end_headers()
+            self.wfile.write(f"Failed to fetch target page: {e.reason}".encode("utf-8"))
+        except Exception as e:
+            self.send_response(500)
+            self.send_header("Content-Type", "text/plain; charset=utf-8")
+            self.end_headers()
+            self.wfile.write(f"Server error: {e}".encode("utf-8"))
+
+
+def run(server_class=HTTPServer, handler_class=ProxyHandler, port=8000):
+    server_address = ("", port)
+    try:
+        httpd = server_class(server_address, handler_class)
+    except OSError as exc:
+        if exc.errno == 98:
+            raise SystemExit(f"Port {port} is already in use. Run with a different port using --port.") from exc
+        raise
+    print(f"Serving crawler homepage at http://localhost:{port}/")
+    httpd.serve_forever()
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Proxy crawler for https://m.slrclub.com/l/free")
+    parser.add_argument("--port", type=int, default=8000, help="Port to listen on")
+    args = parser.parse_args()
+    run(port=args.port)