Preserve POST semantics through proxies (#2498)

CHANGELOG.md

@@ -21,6 +21,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added root contributor and security policies, structured issue forms, repository agent guidance, discovery terminology, and an operator-focused documentation wiki ([d090a29a](https://github.com/laramies/theHarvester/commit/d090a29a), [7c491ef5](https://github.com/laramies/theHarvester/commit/7c491ef5), [8b9d420b](https://github.com/laramies/theHarvester/commit/8b9d420b)).
 
 ### Changed
+- Fixed proxied POST requests so they retain the request method, body, and query parameters.
 - Migrated Pentest-Tools discovery to its API v2 Bearer-authenticated scan, status, and output endpoints.
 - Included HIBP verified-domain in `all` and matching capability selectors like every other P0 source, with REST operator authentication applied after source expansion when its provider key is configured.
 - Allowed REST `/query` requests to select discovery sources by result capability, matching the CLI's union semantics while preserving explicit source selection.

tests/lib/test_core.py

@@ -494,7 +494,7 @@ async def test_post_fetch_can_include_response_metadata(monkeypatch) -> None:
 
 
 @pytest.mark.asyncio
-async def test_post_fetch_proxy_branch_uses_get_with_http_proxy(monkeypatch) -> None:
+async def test_post_fetch_proxy_branch_posts_body_and_params_with_http_proxy(monkeypatch) -> None:
     reset_dummy_sessions()
     created_connectors = []
     monkeypatch.setattr(core_module.aiohttp, 'ClientSession', DummySession)
@@ -509,12 +509,22 @@ async def test_post_fetch_proxy_branch_uses_get_with_http_proxy(monkeypatch) ->
 
     monkeypatch.setattr(AsyncFetcher, '_create_connector', fake_create_connector)
 
-    result = await AsyncFetcher.post_fetch('https://example.com/resource', proxy=True)
+    result = await AsyncFetcher.post_fetch(
+        'https://example.com/resource',
+        json_body={'scan': 'example'},
+        params={'page': 2},
+        json=True,
+        proxy=True,
+    )
 
-    assert result == 'response-text'
+    assert result == {'ok': True}
     assert created_connectors == [('http://proxy.local:8080', 'http', 'ssl-context')]
     session = DummySession.instances[0]
     assert session.connector == 'connector'
     assert session.requests == [
-        ('GET', 'https://example.com/resource', {'proxy': 'http://proxy.local:8080'})
+        (
+            'POST',
+            'https://example.com/resource',
+            {'json': {'scan': 'example'}, 'params': {'page': 2}, 'proxy': 'http://proxy.local:8080'},
+        )
     ]

theHarvester/lib/core.py

@@ -610,32 +610,23 @@ class AsyncFetcher:
             if proxy:
                 proxy_url, proxy_type = cls._resolve_proxy(proxy)
                 sslcontext = cls._ssl_context()
-
+                request_kwargs: dict[str, Any] = {
+                    'data': cls._normalize_data(data) if json_body is None else None,
+                    'proxy': proxy_url if proxy_type == 'http' else None,
+                }
                 if params != '':
-                    async with await cls._build_session(headers, timeout, proxy_url, proxy_type, sslcontext) as session:
-                        return await cls._request(
-                            session,
-                            'GET',
-                            url,
-                            params=params,
-                            proxy=proxy_url if proxy_type == 'http' else None,
-                            json=json,
-                            json_body=json_body,
-                            delay=5,
-                            include_metadata=include_metadata,
-                        )
-                else:
-                    async with await cls._build_session(headers, timeout, proxy_url, proxy_type, sslcontext) as session:
-                        return await cls._request(
-                            session,
-                            'GET',
-                            url,
-                            proxy=proxy_url if proxy_type == 'http' else None,
-                            json=json,
-                            json_body=json_body,
-                            delay=5,
-                            include_metadata=include_metadata,
-                        )
+                    request_kwargs['params'] = params
+                async with await cls._build_session(headers, timeout, proxy_url, proxy_type, sslcontext) as session:
+                    return await cls._request(
+                        session,
+                        'POST',
+                        url,
+                        json=json,
+                        json_body=json_body,
+                        delay=3,
+                        include_metadata=include_metadata,
+                        **request_kwargs,
+                    )
             elif params == '':
                 async with await cls._build_session(headers, timeout) as session:
                     return await cls._request(