q792602257andClaude Opus 4.6
2b7db521c4
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>
38 lines
1.0 KiB
TOML
38 lines
1.0 KiB
TOML
[project]
|
|
name = "rakuten-scraper-service"
|
|
version = "0.1.0"
|
|
description = "API service for Rakuten Ichiba scraping tasks"
|
|
requires-python = ">=3.13"
|
|
dependencies = [
|
|
"fastapi>=0.115.0,<1.0.0",
|
|
"httpx[http2]>=0.27.0,<1.0.0",
|
|
"loguru>=0.7.0,<1.0.0",
|
|
"opentelemetry-api>=1.27.0,<2.0.0",
|
|
"opentelemetry-exporter-otlp>=1.27.0,<2.0.0",
|
|
"opentelemetry-instrumentation-fastapi>=0.48b0,<1.0.0",
|
|
"opentelemetry-instrumentation-httpx>=0.48b0,<1.0.0",
|
|
"opentelemetry-sdk>=1.27.0,<2.0.0",
|
|
"pydantic>=2.0.0,<3.0.0",
|
|
"pydantic-settings>=2.4.0,<3.0.0",
|
|
"selectolax>=0.3.21,<1.0.0",
|
|
"uvicorn[standard]>=0.30.0,<1.0.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
# 浏览器兜底：仅在纯 HTTP 被 Akamai 拦截时使用，日常运行不需要
|
|
browser = [
|
|
"playwright>=1.47.0,<2.0.0",
|
|
]
|
|
dev = [
|
|
"pytest>=8.3.0,<9.0.0",
|
|
"pytest-asyncio>=0.24.0,<1.0.0",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
asyncio_default_fixture_loop_scope = "function"
|
|
testpaths = ["tests"]
|
|
|
|
[tool.uv]
|
|
package = false
|