feat: complete production workflow migration

This commit is contained in:
2026-08-06 14:29:57 +08:00
parent 7f215e79c4
commit 8df5266abb
448 changed files with 56937 additions and 14619 deletions
@@ -0,0 +1,86 @@
from __future__ import annotations
from pathlib import Path
from gyxx_flow.adapters import environment_for_child_script
PROJECT_ROOT = Path(__file__).resolve().parents[1]
MODULE_ROOT = PROJECT_ROOT / "src" / "gyxx_flow" / "modules"
NESTED_TARGETS = {
"content_marketing": (
"bilibili_scraper.py",
"pgy_xhs_scraper_v2.py",
"xingtu_scraper_v2.py",
"self_douyin_scraper.py",
),
"shop_intelligence": (
"collectors/jd_data_collector.py",
"collectors/jd_peer_store_data_collector.py",
"collectors/dy_store_competitor_store_scraping.py",
"collectors/taobao_sycm.py",
"collectors/jd_self_operated_brand_daily.py",
"collectors/jd_self_operated_product_daily.py",
),
"product_commerce": (
"orchestrate_daily_collection.py",
"collect_persona_to_bitable.py",
"collect_dy_persona_to_bitable.py",
"collect_jd_persona_to_bitable.py",
"taobao_dmp_item_crowd_insight_screenshots.py",
"dy_audience_profile_collect.py",
"collect_erp_yesterday_metrics.py",
"jd_product_data_collector.py",
"dy_product_scraping.py",
"taobao_sycm_collect.py",
"taobao_sycm_collect_backfill.py",
"import_product_reviews.py",
"aggregate_daily_final.py",
"export_bitable_records.py",
"insert_bitable_records.py",
"analyze_style_with_hermes.py",
"check_nine_day_decline.py",
"collect_sycm_market_rank.py",
"collect_jd_market_rank.py",
"collect_dy_market_rank.py",
"taobao_wanxiang_ai_creative_report.py",
"scripts/insert_main_image_records.py",
"jd_main_image_collector.py",
"scripts/insert_jd_main_image_records.py",
),
}
def test_nested_workflow_targets_have_complete_unique_browser_bindings(tmp_path) -> None:
bindings: list[dict[str, str]] = []
for module, entries in NESTED_TARGETS.items():
module_root = MODULE_ROOT / module
base_environment = {
"GYXX_MODULE_ID": module,
"GYXX_MODULE_ROOT": str(module_root),
"GYXX_PROJECT_ROOT": str(PROJECT_ROOT),
"GYXX_DATA_ROOT": str(tmp_path / "portable-data"),
}
for entry in entries:
environment = environment_for_child_script(
module_root / entry,
base_environment,
)
assert environment["GYXX_SCRIPT_ID"] == f"{module}:{entry}"
for key in (
"GYXX_BROWSER_CDP_PORT",
"GYXX_BROWSER_CDP_URL",
"GYXX_BROWSER_PROFILE_DIR",
"GYXX_BROWSER_COOKIE_FILE",
"GYXX_BROWSER_STORAGE_STATE_FILE",
):
assert environment[key]
bindings.append(environment)
assert len({item["GYXX_BROWSER_CDP_PORT"] for item in bindings}) == len(bindings)
assert len({item["GYXX_BROWSER_CDP_URL"] for item in bindings}) == len(bindings)
assert len({item["GYXX_BROWSER_PROFILE_DIR"] for item in bindings}) == len(bindings)
assert len({item["GYXX_BROWSER_COOKIE_FILE"] for item in bindings}) == len(bindings)
assert len(
{item["GYXX_BROWSER_STORAGE_STATE_FILE"] for item in bindings}
) == len(bindings)