Every import, test and live doc follows the new path; behaviour is unchanged. tests/test_atshosts.py becomes tests/test_readers.py. plan-readers.md and review-ingest.md keep the old name, since they describe the state before. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
85 lines
2.6 KiB
Python
85 lines
2.6 KiB
Python
"""Recruitee: `recruitee:<subdomain>`, the whole board in one JSON answer
|
|
from the company's own subdomain of recruitee.com.
|
|
|
|
Written from one real board on 2026-09-23; jobhunt-hq did not read
|
|
Recruitee.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from collections.abc import Callable
|
|
from typing import Any
|
|
|
|
from desk.sources import strip_html
|
|
|
|
from ._shared import Row, is_web_url, label_slug_ok, num, only, parse_dt, pay_line, yearly_amount
|
|
|
|
NAME = "recruitee"
|
|
LABEL = "Recruitee"
|
|
RANK = 60
|
|
PATTERNS = (r"https?://([a-z0-9-]+)\.recruitee\.com",)
|
|
|
|
|
|
def slug_ok(slug: str) -> bool:
|
|
return label_slug_ok(slug)
|
|
|
|
|
|
def allowed(slug: str) -> Callable[[str], bool]:
|
|
"""The company's own subdomain, so one company's slug cannot pass for
|
|
another's."""
|
|
return only(f"{slug}.recruitee.com")
|
|
|
|
|
|
def careers_url(slug: str) -> str:
|
|
return f"https://{slug}.recruitee.com"
|
|
|
|
|
|
def feed_url(slug: str) -> str:
|
|
return f"https://{slug}.recruitee.com/api/offers/"
|
|
|
|
|
|
def probe_url(slug: str) -> str:
|
|
return feed_url(slug)
|
|
|
|
|
|
def probe_ok(body: bytes) -> bool:
|
|
return b'"offers":[' in body and b'"offers":[]' not in body
|
|
|
|
|
|
def _salary_text(salary: dict[str, Any]) -> str:
|
|
"""One line from Recruitee's `salary` object; `period` is already a
|
|
plain word ("year", "month")."""
|
|
period = str(salary.get("period") or "").strip().lower()
|
|
return pay_line(num(salary.get("min")), num(salary.get("max")),
|
|
salary.get("currency"), period)
|
|
|
|
|
|
def parse(body: bytes, slug: str) -> list[Row]:
|
|
data = json.loads(body)
|
|
rows = []
|
|
for j in data.get("offers") or []:
|
|
title = (j.get("title") or "").strip()
|
|
url = (j.get("careers_url") or "").strip()
|
|
if not title or not is_web_url(url):
|
|
continue
|
|
salary = j.get("salary") if isinstance(j.get("salary"), dict) else {}
|
|
salary_min, salary_max, currency = yearly_amount(
|
|
salary.get("min"), salary.get("max"), salary.get("currency"),
|
|
salary.get("period"), {"year": 1, "month": 12})
|
|
rows.append({
|
|
"source_id": str(j.get("id") or ""),
|
|
"title": title,
|
|
"location": (j.get("location") or j.get("city") or "").strip(),
|
|
"url": url,
|
|
"posted": parse_dt(j.get("published_at") or j.get("created_at")),
|
|
"department": (j.get("department") or "").strip(),
|
|
"description": strip_html(j.get("description") or ""),
|
|
"remote": j.get("remote"),
|
|
"salary_text": _salary_text(salary),
|
|
"salary_min": salary_min,
|
|
"salary_max": salary_max,
|
|
"currency": currency,
|
|
})
|
|
return rows
|