Declare READS for Oracle, Personio, Phenom, Pinpoint, Recruitee, Rippling, SmartRecruiters, SuccessFactors, Teamtailor, Workable and Workday

Every row carries places (Personio additionalOffices, Workable and Recruitee
locations[], every SuccessFactors address, Workday's own read), the list
teaser of Phenom and Oracle is kept in teaser, and the level, employment and
country a host states are mapped. Workday "N Locations" and "Country - City",
and Recruitee "Remote job", are no longer places. Phenom takes dateCreated
as posted. robots_page and ROBOTS_ANY_CASE go; READS.robots records the
decision. Signatures are feed_url(slug, ask) and page(get, slug, cursor, ask),
with an empty Ask as the default so the runner of today still calls them.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 09:14:27 +02:00
1 parent 4c0da58da7
commit 4316624769
42 files changed
+3126 -199

No files matched your search

+45 -15
View File
@@ -12,14 +12,18 @@ 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 ._contract import Ask, Fields, Place, Reads
from ._shared import Get, Row, parse_dt, yearly_amount
log = logging.getLogger(__name__)
NAME = "rippling"
LABEL = "Rippling"
KEEP_CASE = True
@@ -28,6 +32,13 @@ PATTERNS = (
r"api\.rippling\.com/platform/api/ats/v1/board/([A-Za-z0-9][A-Za-z0-9_-]*)",
)
READS = Reads(
scope="board", listing="whole", text="detail", complete="whole", places="many",
fields=Fields(pay="figures", posted="trusted", employment="stated"),
robots=("read: robots.txt allows /<slug>/jobs on ats.rippling.com, the API host has none "
"(checked 2026-09-29)"),
)
_API = "api.rippling.com"
_SITE = "ats.rippling.com"
@@ -35,6 +46,11 @@ _SITE = "ats.rippling.com"
#: whole; it is also what discovery's patterns take.
_SLUG = re.compile(r"[A-Za-z0-9][A-Za-z0-9_-]*")
#: The words of `employmentType.label` (`SALARIED_FT`), split at "_".
_EMPLOYMENT = {"FT": "full_time", "PT": "part_time", "INTERN": "internship",
"INTERNSHIP": "internship", "CONTRACT": "contract", "CONTRACTOR": "contract",
"TEMP": "temporary", "TEMPORARY": "temporary", "SEASONAL": "temporary"}
#: A role's id in the board's own links.
_UUID = re.compile(r"[0-9A-Za-z-]{8,64}")
@@ -51,17 +67,17 @@ def careers_url(slug: str) -> str:
return f"https://{_SITE}/{slug}/jobs"
def robots_page(slug: str) -> str:
"""The page a person opens. The API host has no robots.txt (a 404, which
allows), so the site's is the one that says something."""
return careers_url(slug)
def _board(slug: str) -> str:
return f"https://{_API}/platform/api/ats/v1/board/{slug}"
def feed_url(slug: str) -> str:
def _place(text: str) -> Place:
"""A place as the board labels it; "Remote (United States)" is remote, any
other label says nothing."""
return {"text": text, "remote": True if text.lower().startswith("remote") else None}
def feed_url(slug: str, ask: Ask = Ask()) -> str:
return f"{_board(slug)}/jobs"
@@ -69,14 +85,14 @@ def parse(body: bytes, slug: str) -> list[Row]:
"""The board's array -> one row per role. The array has one entry per
role and place, so a role in three cities is three entries with one
`uuid` (Rippling's own board: 638 entries, 326 roles); the rows merge
them, the places joined with "; ". The entry has no description, date
them, the places kept as a list and joined with "; " for `location`. The entry has no description, date
or pay: `detail` reads them. `remote` is True only when every place is a
"Remote (...)" one, since a label says nothing else about the work."""
data = json.loads(body)
if not isinstance(data, list):
raise ValueError("not a Rippling board: the answer is not a list")
roles: dict[str, Row] = {}
places: dict[str, list[str]] = {}
places: dict[str, list[Place]] = {}
for entry in data:
job_id = str(entry.get("uuid") or "").strip()
title = (entry.get("name") or "").strip()
@@ -84,8 +100,8 @@ def parse(body: bytes, slug: str) -> list[Row]:
continue
place = str(((entry.get("workLocation") or {}).get("label")) or "").strip()
places.setdefault(job_id, [])
if place and place not in places[job_id]:
places[job_id].append(place)
if place and place not in (p["text"] for p in places[job_id]):
places[job_id].append(_place(place))
roles.setdefault(job_id, {
"source_id": job_id,
"title": title,
@@ -96,12 +112,23 @@ def parse(body: bytes, slug: str) -> list[Row]:
"salary_text": "", # the board's list states no pay
})
for job_id, row in roles.items():
row["location"] = "; ".join(places[job_id])
row["places"] = places[job_id]
row["location"] = "; ".join(p["text"] for p in places[job_id])
row["remote"] = True if places[job_id] and all(
p.lower().startswith("remote") for p in places[job_id]) else None
p["remote"] for p in places[job_id]) else None
return list(roles.values())
def _employment(kind: Any) -> str | None:
label = str((kind or {}).get("label") or "").strip().upper() if isinstance(kind, dict) else ""
for word in label.split("_"):
if word in _EMPLOYMENT:
return _EMPLOYMENT[word]
if label:
log.debug("rippling: unknown employmentType %r", label)
return None
def detail(get: Get, slug: str, row: Row) -> dict[str, Any]:
"""`<board>/jobs/<uuid>`: the description as HTML (`description.role`, or
the company's text when a role has none), every place in `workLocations`,
@@ -114,8 +141,11 @@ def detail(get: Get, slug: str, row: Row) -> dict[str, Any]:
"description": html.unescape(strip_html(text.get("role") or text.get("company") or "")),
"posted": parse_dt(data.get("createdOn")),
}
if places := [p for p in (str(p).strip() for p in data.get("workLocations") or []) if p]:
found["location"] = "; ".join(dict.fromkeys(places))
if names := [p for p in (str(p).strip() for p in data.get("workLocations") or []) if p]:
found["places"] = [_place(name) for name in dict.fromkeys(names)]
found["location"] = "; ".join(dict.fromkeys(names))
if employment := _employment(data.get("employmentType")):
found["employment"] = employment
ranges = data.get("payRangeDetails") or []
if len(ranges) == 1:
pay = ranges[0]