Fetch a posting's text on demand, following a Jobindex ad to the posting itself

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 13:26:20 +02:00
1 parent d168d9eb6c
commit b98561f64a
3 files changed
+307 -4

No files matched your search

+5 -4
View File
@@ -13,6 +13,7 @@ task in `pipeline.TASKS` and the default schedule in `pipeline.SCHEDULES`.
sources.py what a pull reads, changed by hand: boards and searches
added, switched on or off
discover.py which ATS a company's careers site runs on, from its pages
posting.py one role's posting page fetched as text, on demand
reach.py which countries a pull asks each big board for, from the agents
"""
@@ -20,8 +21,8 @@ from __future__ import annotations
from typing import Any
from app.jobs import (cascade, discover, embed, extract, pull, reach, score, sources, stages,
summarise)
from app.jobs import (cascade, discover, embed, extract, posting, pull, reach, score, sources,
stages, summarise)
from app.jobs.pull import search_target, seed_searches
from app.jobs.score import seed_agents
@@ -40,5 +41,5 @@ def bootstrap(config_path: str = "") -> tuple[Any, Any]:
return config, Store(config.database)
__all__ = ["BOOTSTRAP", "bootstrap", "cascade", "discover", "embed", "extract", "pull",
"reach", "score", "search_target", "seed_agents", "seed_searches", "sources", "stages", "summarise"]
__all__ = ["BOOTSTRAP", "bootstrap", "cascade", "discover", "embed", "extract", "posting",
"pull", "reach", "score", "search_target", "seed_agents", "seed_searches", "sources", "stages", "summarise"]