Log the first depth-limited link only (#7916)

docs/topics/stats.rst

@@ -121,6 +121,13 @@ one per actual value of the placeholder.
     :meth:`~scrapy.statscollectors.StatsCollector.get_stats` output is
     equivalent to a counter of 0.
 
+.. stat:: depth/request_ignored_count
+
+``depth/request_ignored_count``
+    Number of requests dropped for exceeding :setting:`DEPTH_LIMIT`.
+
+    Set by :class:`~scrapy.spidermiddlewares.depth.DepthMiddleware`.
+
 .. stat:: downloader/exception_count
 
 ``downloader/exception_count``

scrapy/spidermiddlewares/depth.py

@@ -41,6 +41,7 @@ class DepthMiddleware(BaseSpiderMiddleware):
         self.stats = stats
         self.verbose_stats = verbose_stats
         self.prio = prio
+        self._ignored_logged = False
 
     @classmethod
     def from_crawler(cls, crawler: Crawler) -> Self:
@@ -94,11 +95,14 @@ class DepthMiddleware(BaseSpiderMiddleware):
         if self.prio:
             request.priority -= depth * self.prio
         if self.maxdepth and depth > self.maxdepth:
-            logger.debug(
-                "Ignoring link (depth > %(maxdepth)d): %(requrl)s ",
-                {"maxdepth": self.maxdepth, "requrl": request.url},
-                extra={"spider": self.crawler.spider},
-            )
+            if not self._ignored_logged:
+                logger.debug(
+                    f"Ignoring link (depth > {self.maxdepth}): {request.url}"
+                    " - no more ignored links will be shown",
+                    extra={"spider": self.crawler.spider},
+                )
+                self._ignored_logged = True
+            self.stats.inc_value("depth/request_ignored_count")
             return None
         if self.verbose_stats:
             self.stats.inc_value(f"request_depth_count/{depth}")

tests/test_spidermiddleware_depth.py

@@ -85,6 +85,23 @@ async def test_process_spider_output_async_no_response(
     assert stats.get_value("request_depth_count/0") is None
 
 
+def test_ignored_logged_once(
+    mw: DepthMiddleware, stats: StatsCollector, caplog: pytest.LogCaptureFixture
+) -> None:
+    resp = Response("http://example.com")
+    resp.request = Request("http://example.com")
+    resp.meta["depth"] = 1
+    result = [Request(f"http://example.com/{i}") for i in range(3)]
+
+    with caplog.at_level("DEBUG", logger="scrapy.spidermiddlewares.depth"):
+        assert not list(mw.process_spider_output(resp, result))
+
+    messages = [r.getMessage() for r in caplog.records]
+    assert len(messages) == 1
+    assert "http://example.com/0" in messages[0]
+    assert stats.get_value("depth/request_ignored_count") == 3
+
+
 def test_priority_and_non_verbose_stats() -> None:
     crawler = get_crawler(
         Spider,