Every reader declares, so undeclared(), the scope() fallback, robots_page and ROBOTS_ANY_CASE go. A search provider needs PARAMS and clean_params, a row may carry company, places gains none. Each robots record names the paths the reader requests, from robots.txt read again on 2026-09-30. Platsbanken states remote, HR Manager states no place. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
134 lines
4.7 KiB
Python
134 lines
4.7 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 ._contract import Ask, Fields, Place, Reads
|
|
from ._shared import Row, add_place, 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",)
|
|
|
|
READS = Reads(
|
|
scope="board", listing="whole", text="listing", complete="whole",
|
|
places="many",
|
|
fields=Fields(pay="figures", posted="trusted", remote="stated",
|
|
seniority="stated", employment="stated"),
|
|
robots=("read: <slug>.recruitee.com's robots.txt disallows /v/ only, so /api/offers/ "
|
|
"is allowed (famly, checked 2026-09-30)"),
|
|
)
|
|
|
|
#: What the board writes as a place for a role that is worked anywhere.
|
|
_NO_PLACE = ("remote job",)
|
|
|
|
|
|
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, ask: Ask = Ask()) -> 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 _places(offer: dict[str, Any]) -> list[Place]:
|
|
"""Every place of an offer. `locations`
|
|
lists them (city, state, country), `location` is the first as one line and
|
|
is the fallback for an offer that lists none. The board writes "Remote
|
|
job" where an offer has no place: that is not one, and a remote offer with
|
|
no other place has the place "Remote"."""
|
|
found: list[Place] = []
|
|
|
|
def add(text: str) -> None:
|
|
text = text.strip()
|
|
if text.lower() not in _NO_PLACE:
|
|
add_place(found, {"text": text, "remote": None})
|
|
|
|
for loc in offer.get("locations") or []:
|
|
if not isinstance(loc, dict):
|
|
continue
|
|
parts: list[str] = []
|
|
for part in (loc.get("city") or loc.get("name"), loc.get("state"), loc.get("country")):
|
|
part = str(part or "").strip()
|
|
if part and part not in parts:
|
|
parts.append(part)
|
|
add(", ".join(parts))
|
|
if not found:
|
|
add(str(offer.get("location") or offer.get("city") or ""))
|
|
if not found and offer.get("remote"):
|
|
found.append({"text": "Remote", "remote": True})
|
|
return found
|
|
|
|
|
|
def parse(body: bytes, slug: str) -> list[Row]:
|
|
"""`{slug}.recruitee.com/api/offers/` -> `{"offers": [...]}`. An offer has
|
|
`locations` (a list; 9 of 16 at bunq have two or three), `remote`,
|
|
`experience_code` and `employment_type_code`, and the salary object."""
|
|
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})
|
|
places = _places(j)
|
|
rows.append({
|
|
"source_id": str(j.get("id") or ""),
|
|
"title": title,
|
|
"places": places,
|
|
"location": "; ".join(p["text"] for p in places),
|
|
"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,
|
|
"seniority": str(j.get("experience_code") or "").strip() or None,
|
|
"employment": str(j.get("employment_type_code") or "").strip() or None,
|
|
})
|
|
return rows
|