Copy known zyte_api_session-prefixed meta into session initialization requests (#205)

Author: Gallaecio

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
     hooks:
     - id: black
 -   repo: https://github.com/pycqa/flake8
-    rev: 7.0.0
+    rev: 7.1.0
     hooks:
     - id: flake8
       additional_dependencies:

docs/usage/session.rst

@@ -145,6 +145,13 @@ define a separate :ref:`session config override <session-configs>` for each
 website, each with its own implementation of
 :meth:`~scrapy_zyte_api.SessionConfig.check`.
 
+The :reqmeta:`zyte_api_session_location` and :reqmeta:`zyte_api_session_params`
+request metadata keys, if present in a request that triggers a session
+initialization request, will be copied into the session initialization request,
+so that they are available when :setting:`ZYTE_API_SESSION_CHECKER` or
+:meth:`~scrapy_zyte_api.SessionConfig.check` are called for a session
+initialization request.
+
 If your session checking implementation relies on the response body (e.g. it
 uses CSS or XPath expressions), you should make sure that you are getting one,
 which might not be the case if you are mostly using :ref:`Zyte API automatic

scrapy_zyte_api/_session.py

@@ -505,6 +505,11 @@ async def _init_session(self, session_id: str, request: Request, pool: str) -> b
                 SESSION_INIT_META_KEY: True,
                 "dont_merge_cookies": True,
                 "zyte_api": {**session_params, "session": {"id": session_id}},
+                **{
+                    k: v
+                    for k, v in request.meta.items()
+                    if k in {"zyte_api_session_location", "zyte_api_session_params"}
+                },
             },
             callback=NO_CALLBACK,
         )

tests/test_sessions.py

@@ -1348,6 +1348,85 @@ def parse(self, response):
     session_config_registry.__init__()  # type: ignore[misc]
 
 
+@ensureDeferred
+async def test_session_config_check_meta(mockserver):
+    """When initializing a session, known zyte_api_session-prefixed params
+    should be included in the session initialization request, so that they can
+    be used from check methods validating those requests.
+
+    For example, when validating a location, access to
+    zyte_api_session_location may be necessary.
+    """
+    pytest.importorskip("web_poet")
+
+    params = {
+        "actions": [
+            {
+                "action": "setLocation",
+                "address": {"postalCode": "10001"},
+            }
+        ]
+    }
+
+    @session_config(["example.com"])
+    class CustomSessionConfig(SessionConfig):
+
+        def check(self, response, request):
+            return (
+                bool(self.location(request))
+                and response.meta["zyte_api_session_params"] == params
+                and (
+                    (
+                        response.meta.get("_is_session_init_request", False)
+                        and "zyte_api_session_foo" not in response.meta
+                    )
+                    or response.meta["zyte_api_session_foo"] == "bar"
+                )
+            )
+
+    settings = {
+        "RETRY_TIMES": 0,
+        "ZYTE_API_URL": mockserver.urljoin("/"),
+        "ZYTE_API_SESSION_ENABLED": True,
+        "ZYTE_API_SESSION_MAX_BAD_INITS": 1,
+    }
+
+    class TestSpider(Spider):
+        name = "test"
+        start_urls = ["https://example.com"]
+
+        def start_requests(self):
+            for url in self.start_urls:
+                yield Request(
+                    url,
+                    meta={
+                        "zyte_api_automap": params,
+                        "zyte_api_session_params": params,
+                        "zyte_api_session_location": {"postalCode": "10001"},
+                        "zyte_api_session_foo": "bar",
+                    },
+                )
+
+        def parse(self, response):
+            pass
+
+    crawler = await get_crawler(settings, spider_cls=TestSpider, setup_engine=False)
+    await crawler.crawl()
+
+    session_stats = {
+        k: v
+        for k, v in crawler.stats.get_stats().items()
+        if k.startswith("scrapy-zyte-api/sessions")
+    }
+    assert session_stats == {
+        "scrapy-zyte-api/sessions/pools/example.com/init/check-passed": 1,
+        "scrapy-zyte-api/sessions/pools/example.com/use/check-passed": 1,
+    }
+
+    # Clean up the session config registry.
+    session_config_registry.__init__()  # type: ignore[misc]
+
+
 @ensureDeferred
 async def test_session_config_param_error(mockserver):
     pytest.importorskip("web_poet")