接入 OTel 链路追踪 + 镜像默认启用

抓取-解析链路原本只有日志，出现"抓回内容但解析不出预期字段"时定位慢。
接入 OpenTelemetry traces（FastAPI/httpx 自动 + 手写 fetch/parse span），
解析失败时把页面 HTML 作为 span event 上报，便于事后复现。
Dockerfile 默认开启，镜像一启动即导出到自建 OTLP endpoint。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/scraping/services/rakuma_session.py

@@ -18,6 +18,7 @@ import logging
 from typing import Any
 
 import httpx
+from opentelemetry import trace
 
 from app.scraping.core import rakuma_site as site
 from app.shared.config import Settings
@@ -27,6 +28,7 @@ from app.shared.errors import (
     UpstreamBlockedError,
     UpstreamRequestError,
 )
+from app.shared.telemetry import snapshot
 
 logger = logging.getLogger(__name__)
 
@@ -89,47 +91,71 @@ class RakumaSession:
         if client is None:
             raise UpstreamRequestError("ラクマ 会话尚未初始化")
 
+        tracer = trace.get_tracer(__name__)
         max_attempts = max(1, self._settings.http_max_attempts)
         last_error = "unknown error"
+        last_text: str | None = None
 
-        try:
-            await asyncio.wait_for(
-                self._semaphore.acquire(),
-                timeout=self._settings.request_timeout_seconds,
-            )
-        except TimeoutError as exc:
-            raise ResourceBusyError() from exc
+        with tracer.start_as_current_span("scrape.fetch") as span:
+            span.set_attribute("scrape.url", url)
+            span.set_attribute("scrape.profile", "rakuma")
 
-        try:
-            for attempt in range(1, max_attempts + 1):
-                try:
-                    response = await client.get(url)
-                except httpx.HTTPError as exc:
-                    last_error = f"{type(exc).__name__}: {exc}"
+            try:
+                await asyncio.wait_for(
+                    self._semaphore.acquire(),
+                    timeout=self._settings.request_timeout_seconds,
+                )
+            except TimeoutError as exc:
+                err = ResourceBusyError()
+                span.record_exception(err)
+                span.set_attribute("scrape.fail_reason", "ResourceBusyError")
+                raise err from exc
+
+            try:
+                for attempt in range(1, max_attempts + 1):
+                    span.set_attribute("scrape.attempts", attempt)
+                    try:
+                        response = await client.get(url)
+                    except httpx.HTTPError as exc:
+                        last_error = f"{type(exc).__name__}: {exc}"
+                        logger.warning(
+                            "ラクマ 抓取请求异常：url=%s attempt=%s/%s err=%s",
+                            url, attempt, max_attempts, last_error,
+                        )
+                        continue
+
+                    if response.status_code == 404:
+                        err = ItemNotFoundError(f"Page not found: {url}")
+                        span.record_exception(err)
+                        span.set_attribute("scrape.fail_reason", "ItemNotFoundError")
+                        raise err
+
+                    if response.status_code < 400:
+                        span.set_attribute("scrape.last_status_code", response.status_code)
+                        span.set_attribute("scrape.final_url", str(response.url))
+                        span.set_attribute("scrape.html_bytes", len(response.text))
+                        return response.text
+
+                    last_error = (
+                        f"upstream status {response.status_code}"
+                        if response.status_code >= 500
+                        else f"status {response.status_code}"
+                    )
+                    last_text = response.text
+                    span.set_attribute("scrape.last_status_code", response.status_code)
+                    span.set_attribute("scrape.html_bytes", len(response.text))
                     logger.warning(
-                        "ラクマ 抓取请求异常：url=%s attempt=%s/%s err=%s",
+                        "ラクマ 抓取结果异常：url=%s attempt=%s/%s %s",
                         url, attempt, max_attempts, last_error,
                     )
-                    continue
 
-                if response.status_code == 404:
-                    raise ItemNotFoundError(f"Page not found: {url}")
-
-                if response.status_code < 400:
-                    return response.text
-
-                last_error = (
-                    f"upstream status {response.status_code}"
-                    if response.status_code >= 500
-                    else f"status {response.status_code}"
-                )
-                logger.warning(
-                    "ラクマ 抓取结果异常：url=%s attempt=%s/%s %s",
-                    url, attempt, max_attempts, last_error,
-                )
-
-            if last_error.startswith("upstream status") or ":" in last_error:
-                raise UpstreamRequestError(f"Upstream request failed: {last_error}")
-            raise UpstreamBlockedError(f"Failed to fetch {url}: {last_error}")
-        finally:
-            self._semaphore.release()
+                if last_error.startswith("upstream status") or ":" in last_error:
+                    err = UpstreamRequestError(f"Upstream request failed: {last_error}")
+                else:
+                    err = UpstreamBlockedError(f"Failed to fetch {url}: {last_error}")
+                span.record_exception(err)
+                span.set_attribute("scrape.fail_reason", type(err).__name__)
+                snapshot(span, "scrape.failed_html", last_text, self._settings.otel_snapshot_max_bytes)
+                raise err
+            finally:
+                self._semaphore.release()