Files
jobboard/plugins/readers/workable.py
T

151 lines
5.9 KiB
Python

"""Workable: `workable:<account>`, paged ten roles at a time with a stated
total.
Written from one real board, Hugging Face's, on 2026-09-28, when the first
board with roles was seen; jobhunt-hq did not read Workable.
The list carries no text. The text is read per role by `detail`, `GET
/api/v2/accounts/{slug}/jobs/{shortcode}` (checked 2026-09-30, Hugging Face's
DB4D7C0EC8): the list's fields again, and `description`, `requirements` and
`benefits` as HTML. The list gives the numeric `id` and the `shortcode`; the
role's `source_id` is the number, so the row keeps the `shortcode` for this
request. The API answers 429 to a run of requests; the runner spaces the
reads and stops on one.
"""
from __future__ import annotations
import html
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 Get, Page, Row, add_place, only, parse_dt, path_slug_ok
NAME = "workable"
LABEL = "Workable"
RANK = 40
PATTERNS = (
r"apply\.workable\.com/(?:api/v\d/accounts/)?([A-Za-z0-9_-]+)",
r"https?://(?!apply\.|www\.)([a-z0-9-]+)\.workable\.com",
)
READS = Reads(
scope="board", listing="paged", page_size=10, text="detail", complete="stated",
places="many",
fields=Fields(posted="trusted", remote="stated", employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
)
_API = "apply.workable.com"
# No probe: Workable's API sits behind a rate limit that a run of guesses
# trips, and a Workable site links its board plainly anyway.
def slug_ok(slug: str) -> bool:
return path_slug_ok(slug)
def allowed(slug: str) -> Callable[[str], bool]:
return only(_API)
def careers_url(slug: str) -> str:
return f"https://{_API}/{slug}"
def page(get: Get, slug: str, cursor: Any, ask: Ask = Ask()) -> Page:
"""One POST of the list; the next page is the same POST with
`{"token": nextPage}`, and the last page has no `nextPage`."""
url = f"https://{_API}/api/v3/accounts/{slug}/jobs"
data = json.loads(get(url, method="POST", payload={"token": cursor} if cursor else {}))
return data, data.get("results") or [], data.get("total"), data.get("nextPage") or None
def parse(body: bytes, slug: str) -> list[Row]:
return rows(json.loads(body), slug)
def _places(job: dict[str, Any], remote: bool) -> list[Place]:
"""Every place of a role. `locations`
lists them (city, region, country; `hidden` ones are stated too), and
`location` is the first alone, the fallback for a role that lists none.
A place is remote when the role is."""
found: list[Place] = []
listed = [loc for loc in job.get("locations") or [] if isinstance(loc, dict)]
for loc in listed or [job.get("location") or {}]:
parts: list[str] = []
for part in (loc.get("city"), loc.get("region"), loc.get("country")):
part = str(part or "").strip()
if part and part not in parts:
parts.append(part)
text = ", ".join(parts)
add_place(found, {"text": text, "remote": remote})
return found
def rows(data: dict[str, Any], slug: str) -> list[Row]:
"""One page of POST https://apply.workable.com/api/v3/accounts/{slug}/jobs
-> `{"total": int, "results": [...], "nextPage": token}`, as Hugging
Face's board answered on 2026-09-28. A result carries no URL and no text:
the job page is `https://apply.workable.com/{slug}/j/{shortcode}/`, and
the description is only on the per-job endpoint, which `detail` reads, so
`description` stays empty here. The `shortcode` is kept in the row for it.
`location` is the first place and `locations` all of them; `department`
is a list; `remote` is a flag beside `workplace` (remote, hybrid,
on_site); `type` is the hours or the contract (full, part, ...)."""
out = []
for j in data.get("results") or []:
title = (j.get("title") or "").strip()
shortcode = (j.get("shortcode") or "").strip()
if not title or not shortcode:
continue
workplace = str(j.get("workplace") or "").strip()
remote = bool(j.get("remote")) or workplace == "remote"
places = _places(j, remote)
dept = j.get("department") or ""
if isinstance(dept, list):
dept = ", ".join(d for d in dept if d)
out.append({
"source_id": str(j.get("id") or shortcode),
"shortcode": shortcode,
"title": title,
"places": places,
"location": "; ".join(p["text"] for p in places),
"url": f"https://{_API}/{slug}/j/{shortcode}/",
"posted": parse_dt(j.get("published")),
"department": dept.strip(),
"description": "",
"remote": workplace or j.get("remote"),
"salary_text": "", # Workable's list endpoint states no pay at all
"employment": str(j.get("type") or "").strip() or None,
})
return out
#: The parts of a role's ad that make its description, in reading order.
_PARTS = ("description", "requirements", "benefits")
def detail(get: Get, slug: str, row: Row) -> dict[str, Any]:
"""`/api/v2/accounts/{slug}/jobs/{shortcode}` -> the HTML of
`description`, `requirements` and `benefits`, joined as one text. An
answer with none of the three keys is not a role and raises, so the role
is asked again on a later pull."""
shortcode = str(row.get("shortcode") or "")
if not path_slug_ok(shortcode):
raise ValueError(f"no Workable shortcode in the row: {shortcode!r}")
data = json.loads(get(f"https://{_API}/api/v2/accounts/{slug}/jobs/{shortcode}"))
if not isinstance(data, dict) or not any(k in data for k in _PARTS):
raise ValueError("not a Workable role: no description")
parts = []
for key in _PARTS:
text = " ".join(html.unescape(strip_html(str(data.get(key) or ""))).split())
if text:
parts.append(text)
return {"description": " ".join(parts)}