13 KiB
13 KiB
phase, plan, wave, title, depends_on, files_modified, autonomous, requirements
| phase | plan | wave | title | depends_on | files_modified | autonomous | requirements | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 2 | 1 | 新增 Boss HTTP 层 mock 测试 |
|
|
true |
|
Phase 2 Plan 02: Boss HTTP 层 mock 测试
Objective
使用 unittest.mock.MagicMock 为 Boss HTTP 层添加 mock 测试,
覆盖正常响应和错误响应两种场景,满足 QUAL-03。
测试文件位置:tests/boss/test_boss_client.py
为什么不用 respx: crawler_core.HTTPClient 底层使用 requests_go(非 httpx),
respx 只拦截 httpx,无法适用。使用 MagicMock 直接 mock http_client 接口,
不依赖网络,测试更快更稳定。
Must Haves
tests/boss/__init__.py存在(空文件即可)tests/boss/test_boss_client.py存在并包含 mock 测试pytest tests/boss/ -v全部通过(无 ImportError,无失败)- 测试组:SearchRecJobs(正常响应、业务错误、HTTP 非 200)
- 测试组:GetBrandDetail(正常响应)
- 测试组:SearchBrandJobs(正常响应、hasMore=True 时 is_end_page=False)
- 测试组:GetJobDetail.fetch()(通过 batch 接口,正常合并子请求)
- 测试组:BossClient(验证每次请求注入 Traceid 头、mpt/wt2 头)
Wave 1
Task 2.1: 创建 tests/boss/ 目录和 init.py
<read_first>
tests/crawler_core/test_boss_sign.py(参考现有测试风格和 conftest 依赖)conftest.py(项目根目录,确认 sys.path 设置) </read_first>
确认 conftest.py 已在项目根目录(Phase 1 已创建),无需重复创建。
<acceptance_criteria>
test -f tests/boss/__init__.py && echo "OK"输出 OKpytest tests/boss/ --collect-only 2>&1 | head -5无 "ERROR collecting" 字样 </acceptance_criteria>
Task 2.2: 编写 test_boss_client.py
<read_first>
spiderJobs/platforms/boss/api.py(迁移后版本,Task 1.2 产物)spiderJobs/platforms/boss/client.py(迁移后版本)tests/crawler_core/test_boss_sign.py(参考测试风格)crawler_core/base.py(Result 结构) </read_first>
"""
Boss 直聘 HTTP 层 mock 测试(QUAL-03)
使用 unittest.mock.MagicMock 替代真实 HTTP 客户端,
覆盖正常响应和错误响应场景,无网络依赖。
"""
from __future__ import annotations
from unittest.mock import MagicMock, patch, call
import pytest
from spiderJobs.platforms.boss.api import (
SearchRecJobs,
GetBrandDetail,
SearchBrandJobs,
GetJobDetail,
_parse_boss_response,
)
from spiderJobs.platforms.boss.client import BossClient
from crawler_core.base import Result
# ─────────────────────────────────────────────────────────
# 1. _parse_boss_response 纯函数测试
# ─────────────────────────────────────────────────────────
class TestParseBossResponse:
def test_http_error_returns_failure(self):
result = _parse_boss_response(500, {})
assert result.success is False
assert result.status_code == 500
def test_non_dict_raw_returns_failure(self):
result = _parse_boss_response(200, "not a dict")
assert result.success is False
def test_biz_error_code_35_returns_failure(self):
result = _parse_boss_response(200, {"code": 35, "message": "IP地址存在异常"})
assert result.success is False
assert result.status_code == 35
assert "IP" in result.error
def test_joblist_payload_parsed_correctly(self):
raw = {
"code": 0,
"zpData": {
"jobList": [{"title": "Python工程师"}],
"hasMore": True,
},
}
result = _parse_boss_response(200, raw)
assert result.success is True
assert len(result.list) == 1
assert result.list[0]["title"] == "Python工程师"
assert result.is_end_page is False # hasMore=True → is_end_page=False
def test_joblist_no_more_pages(self):
raw = {
"code": 0,
"zpData": {"jobList": [{"title": "测试"}], "hasMore": False},
}
result = _parse_boss_response(200, raw)
assert result.is_end_page is True
def test_detail_payload(self):
raw = {"code": 0, "zpData": {"companyName": "测试公司"}}
result = _parse_boss_response(200, raw)
assert result.success is True
assert result.data == {"companyName": "测试公司"}
# ─────────────────────────────────────────────────────────
# 2. SearchRecJobs
# ─────────────────────────────────────────────────────────
class TestSearchRecJobs:
def _make_mock_client(self, return_value):
mock_client = MagicMock()
mock_client.get.return_value = return_value
return mock_client
def test_search_success(self):
raw = {
"code": 0,
"zpData": {
"jobList": [{"title": "测试职位1"}, {"title": "测试职位2"}],
"hasMore": False,
},
}
searcher = SearchRecJobs(city_code="101010100", client=self._make_mock_client((200, raw)))
result = searcher.search(page_index=1)
assert result.success is True
assert len(result.list) == 2
assert result.is_end_page is True
def test_search_http_error(self):
searcher = SearchRecJobs(client=self._make_mock_client((403, {})))
result = searcher.search(page_index=1)
assert result.success is False
assert result.status_code == 403
def test_search_biz_error(self):
raw = {"code": 35, "message": "IP地址存在异常"}
searcher = SearchRecJobs(client=self._make_mock_client((200, raw)))
result = searcher.search(page_index=1)
assert result.success is False
def test_search_builds_correct_params(self):
mock_client = MagicMock()
mock_client.get.return_value = (200, {"code": 0, "zpData": {"jobList": [], "hasMore": False}})
searcher = SearchRecJobs(city_code="101280600", page_size=10, client=mock_client)
searcher.search(page_index=2)
called_args = mock_client.get.call_args
params = called_args[0][1] if len(called_args[0]) > 1 else called_args[1].get("params", called_args[0][1])
assert params["cityCode"] == "101280600"
assert params["page"] == 2
assert params["pageSize"] == 10
# ─────────────────────────────────────────────────────────
# 3. GetBrandDetail
# ─────────────────────────────────────────────────────────
class TestGetBrandDetail:
def test_fetch_success(self):
mock_client = MagicMock()
mock_client.get.return_value = (200, {
"code": 0,
"zpData": {"brandName": "测试公司", "brandId": "abc123"},
})
fetcher = GetBrandDetail(brand_id="abc123", client=mock_client)
result = fetcher.fetch()
assert result.success is True
assert result.data["brandName"] == "测试公司"
def test_fetch_404(self):
mock_client = MagicMock()
mock_client.get.return_value = (404, {})
fetcher = GetBrandDetail(brand_id="notexist", client=mock_client)
result = fetcher.fetch()
assert result.success is False
assert result.status_code == 404
# ─────────────────────────────────────────────────────────
# 4. SearchBrandJobs
# ─────────────────────────────────────────────────────────
class TestSearchBrandJobs:
def test_search_success_has_more(self):
mock_client = MagicMock()
mock_client.get.return_value = (200, {
"code": 0,
"zpData": {"list": [{"jobName": "测试岗位"}], "hasMore": True},
})
searcher = SearchBrandJobs(brand_id="abc123", client=mock_client)
result = searcher.search(page_index=1)
assert result.success is True
assert len(result.list) == 1
assert result.is_end_page is False
def test_search_success_no_more(self):
mock_client = MagicMock()
mock_client.get.return_value = (200, {
"code": 0,
"zpData": {"list": [], "hasMore": False},
})
searcher = SearchBrandJobs(brand_id="abc123", client=mock_client)
result = searcher.search(page_index=1)
assert result.is_end_page is True
# ─────────────────────────────────────────────────────────
# 5. GetJobDetail(batch 接口路径)
# ─────────────────────────────────────────────────────────
class TestGetJobDetail:
def test_fetch_success_merges_sub_requests(self):
mock_client = MagicMock()
mock_client.batch.return_value = (200, {
"code": 0,
"zpData": {
"/wapi/zpgeek/miniapp/job/detail.json": {
"zpData": {"jobName": "数据工程师"}
},
"/wapi/zpgeek/miniapp/jobdetail/improvement/query.json": {
"zpData": {"tags": ["Python", "大数据"]}
},
},
})
fetcher = GetJobDetail(security_id="sid123", job_id="jid456", client=mock_client)
result = fetcher.fetch()
assert result.success is True
assert result.data["detail"]["jobName"] == "数据工程师"
assert "Python" in result.data["improvement"]["tags"]
def test_fetch_biz_error(self):
mock_client = MagicMock()
mock_client.batch.return_value = (200, {"code": 35, "message": "IP地址存在异常"})
fetcher = GetJobDetail(security_id="sid", job_id="jid", client=mock_client)
result = fetcher.fetch()
assert result.success is False
def test_fetch_exception_handled(self):
mock_client = MagicMock()
mock_client.batch.side_effect = ConnectionError("连接超时")
fetcher = GetJobDetail(security_id="sid", job_id="jid", client=mock_client)
result = fetcher.fetch()
assert result.success is False
assert "连接超时" in result.error
# ─────────────────────────────────────────────────────────
# 6. BossClient — Traceid/mpt/wt2 请求头注入
# ─────────────────────────────────────────────────────────
class TestBossClientHeaders:
def test_get_injects_traceid(self):
"""每次 GET 请求头包含 Traceid"""
client = BossClient(tunnel_proxy=None)
headers = client._boss_headers()
assert "Traceid" in headers
assert headers["Traceid"].startswith("M-W")
def test_traceid_is_unique_per_call(self):
"""每次调用生成不同的 Traceid"""
client = BossClient()
t1 = client._boss_headers()["Traceid"]
t2 = client._boss_headers()["Traceid"]
# 大概率不同(极低碰撞概率可忽略)
assert len(t1) > 10
assert len(t2) > 10
def test_mpt_wt2_in_headers(self):
"""signer 的 mpt/wt2 注入到请求头"""
from crawler_core.boss.sign import BossSign
signer = BossSign(mpt="test_mpt_value", wt2="test_wt2_value")
client = BossClient(signer=signer)
headers = client._boss_headers()
assert headers["mpt"] == "test_mpt_value"
assert headers["wt2"] == "test_wt2_value"
<acceptance_criteria>
test -f tests/boss/test_boss_client.py && echo "OK"输出 OKpytest tests/boss/ -v 2>&1 | tail -10输出包含 "passed",无 "failed" 或 "error"pytest tests/boss/ -v 2>&1 | grep "PASSED" | wc -l输出 >= 15(至少 15 个测试通过)pytest tests/boss/ -v 2>&1 | grep "import"无输出(无 ImportError) </acceptance_criteria>
Verification
# 运行所有 Boss mock 测试
pytest tests/boss/ -v
# 同时运行 Phase 1 签名测试,确认没有回归
pytest tests/crawler_core/ -v
# 汇总结果
pytest tests/ -v --tb=short