Hosts a to l declare READS: places, teaser, stated seniority and employment

Ashby, BambooHR, Deel, Eightfold, Gem, Greenhouse, HiBob, HR Manager, Jibe,
Jobylon and Lever move to feed_url(slug, ask) and page(get, slug, cursor, ask),
declare READS with the robots decision, and drop robots_page. Rows carry
places (Ashby secondaryLocations, Lever allLocations, Greenhouse offices in
place of a Hybrid placeholder), Jobylon keeps its summary as teaser and maps
experience and employment, Eightfold reads creationTs as the posting date and
Ashby reads workplaceType. Fixtures <name>-places.* and jobylon-teaser.html
drive the conformance checks; the eleven names leave UNDECLARED.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 09:11:53 +02:00
1 parent 4c0da58da7
commit f2e652a8da
35 files changed
+1290 -391

No files matched your search

+41 -9
View File
@@ -16,13 +16,25 @@ from __future__ import annotations
import html
import json
import logging
import re
from collections.abc import Callable
from typing import Any
from desk.sources import strip_html
from ._shared import Row, num, only, parse_dt, pay_line
from ._contract import Ask, Fields, Reads, Row
from ._shared import num, only, parse_dt, pay_line
log = logging.getLogger(__name__)
READS = Reads(
scope="board", listing="whole", text="listing", complete="whole",
places="many",
fields=Fields(pay="line", posted="listed", remote="stated", employment="stated"),
robots="read: robots.txt allows the board page /<slug>; /api/ is disallowed and not read "
"(checked 2026-09-29)",
)
NAME = "deel"
LABEL = "Deel"
@@ -50,6 +62,12 @@ _TEXT = re.compile(rb"T([0-9a-f]+),")
#: Deel's `workArrangementEnum` -> `store._remote`'s words.
_REMOTE = {"ON_SITE": "onsite", "HYBRID": "hybrid", "REMOTE": "remote"}
#: The name of a `jobEmploymentTypes` entry -> the app's employment words.
_EMPLOYMENT = {"full-time": "full_time", "full time": "full_time", "part-time": "part_time",
"part time": "part_time", "contract": "contract", "contractor": "contract",
"consultant": "contract", "temporary": "temporary", "intern": "intern",
"internship": "intern", "freelance": "freelance"}
def slug_ok(slug: str) -> bool:
return bool(_SLUG.fullmatch(slug))
@@ -63,11 +81,7 @@ def careers_url(slug: str) -> str:
return f"https://{_HOST}/{slug}"
def robots_page(slug: str) -> str:
return careers_url(slug)
def feed_url(slug: str) -> str:
def feed_url(slug: str, ask: Ask) -> str:
return careers_url(slug)
@@ -106,9 +120,21 @@ def _postings(body: bytes) -> tuple[list[dict[str, Any]], dict[str, str]]:
raise ValueError("not a Deel job board: no jobPostings in the page")
def _employment(job: dict[str, Any]) -> str | None:
"""The first `jobEmploymentTypes` entry that names a known type."""
for entry in job.get("jobEmploymentTypes") or []:
name = str(((entry or {}).get("employmentType") or {}).get("name") or "").strip()
if not name:
continue
if found := _EMPLOYMENT.get(name.lower()):
return found
log.debug("deel: unknown employment type %r", name)
return None
def parse(body: bytes, slug: str) -> list[Row]:
"""`jobs.deel.com/<slug>` -> one row per posting. `location` joins the
role's places with "; ". `posted` is the day the posting was published
role's places with "; ", and `places` lists each. `posted` is the day the posting was published
(its publication's state), not the day the role was drafted.
Deel states pay as a currency and two amounts with no period, and the
@@ -132,9 +158,12 @@ def parse(body: bytes, slug: str) -> list[Row]:
description = p.get("richtextDescription") or ""
if description.startswith("$"):
description = stream.get(description[1:], "")
out.append({
arrangement = str(job.get("workArrangementEnum") or "")
remote = {"REMOTE": True, "HYBRID": False, "ON_SITE": False}.get(arrangement)
row: Row = {
"source_id": post_id,
"title": title,
"places": [{"text": name, "remote": remote} for name in dict.fromkeys(places)],
"location": "; ".join(dict.fromkeys(places)),
"url": f"https://{_HOST}/{slug}/job-details/{post_id}/overview",
"posted": parse_dt(published.get("createdAt") or p.get("createdAt")),
@@ -144,5 +173,8 @@ def parse(body: bytes, slug: str) -> list[Row]:
"salary_text": (pay_line(num(pay.get("minAmount")), num(pay.get("maxAmount")),
pay.get("currencyIsoCode"), "")
if p.get("isCompensationVisible") else ""),
})
}
if employment := _employment(job):
row["employment"] = employment
out.append(row)
return out