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

+73 -29
View File
@@ -18,6 +18,7 @@ from __future__ import annotations
import html
import json
import logging
import re
from collections.abc import Callable
from datetime import UTC, datetime, timedelta
@@ -25,14 +26,21 @@ from typing import Any
from desk.sources import strip_html
from ._contract import Ask, Fields, Place, Reads
from ._shared import Get, Page, Row, only, parse_dt
log = logging.getLogger(__name__)
NAME = "workday"
LABEL = "Workday"
KEEP_CASE = True
#: A tenant answers `/jobs` and `/Jobs` alike, so a rule in either case
#: forbids the site.
ROBOTS_ANY_CASE = True
READS = Reads(
scope="board", listing="paged", page_size=20, ceiling=2000, text="detail",
complete="stated", places="many",
fields=Fields(posted="trusted", remote="stated", country="stated", employment="stated"),
robots="read: robots.txt allows /<Site>/ (checked 2026-09-29)",
)
#: One group for `<tenant>.<wdN>` and one for the site, which discovery joins
#: into the slug with "/". A locale segment (`/en-US/`, `/de-DE/`) may come
@@ -86,14 +94,7 @@ def careers_url(slug: str) -> str:
return f"https://{_host(slug)}/{_parts(slug)[2]}" # type: ignore[index]
def robots_page(slug: str) -> str:
"""With the trailing slash, since the rules the tenants write are
`Disallow: /<Site>/` and read as prefixes: `/<Site>` alone would slip
past the very rule that forbids the site."""
return careers_url(slug) + "/"
def page(get: Get, slug: str, cursor: Any) -> Page:
def page(get: Get, slug: str, cursor: Any, ask: Ask = Ask()) -> Page:
"""`cursor` is `(offset, total)`. `total` is read on the first page only:
on the later ones it is 0 on most tenants and the real figure on a few,
so it is carried. An offset at or past the end does not answer an empty
@@ -160,6 +161,32 @@ def _remote(value: Any) -> str | None:
return _REMOTE.get(str(value or "").strip().lower())
#: `timeType` -> the app's employment words.
_EMPLOYMENT = {"full time": "full_time", "part time": "part_time"}
#: What `locationsText` says of a role at several places: "2 Locations". The
#: places arrive with the role's own read.
_COUNT = re.compile(r"\d+ locations?", re.I)
def _place(text: Any, remote: str | None) -> Place | None:
"""A place as Workday writes it, or None for none. Some tenants write
"Country - City" ("Denmark - Copenhagen", "USA - Texas - Austin"), which
is turned round to the order the rest of the app reads, "Copenhagen,
Denmark"; a place that starts with a work-mode word ("Remote - Germany")
is left as it is. A place is remote or an office as far as the role's
`remoteType` says."""
text = " ".join(str(text or "").split())
if not text or _COUNT.fullmatch(text):
return None
parts = [part.strip() for part in text.split(" - ")]
if len(parts) > 1 and "," not in text and all(parts) \
and not parts[0].lower().startswith(("remote", "hybrid", "on-site", "onsite")):
text = ", ".join(reversed(parts))
return {"text": text, "remote": {"remote": True, "hybrid": False, "onsite": False}.get(
remote or "")}
def rows(decoded: dict[str, Any], slug: str) -> list[Row]:
"""One page of `.../wday/cxs/<tenant>/<Site>/jobs` -> `{"total",
"jobPostings": [...], "facets": [...]}`. A posting has `title`,
@@ -167,7 +194,7 @@ def rows(decoded: dict[str, Any], slug: str) -> list[Row]:
(a place, or "2 Locations"), `postedOn` (relative text) and
`bulletFields`, which lead with the requisition id, and on some tenants
`remoteType`. No description, no date and no country: `detail` has
those. The id is the requisition id where the path carries it, and the
those, and the places of a role that "2 Locations" hides. The id is the requisition id where the path carries it, and the
path where not; a posting with no title or no path is skipped."""
out = []
for p in decoded.get("jobPostings") or []:
@@ -175,15 +202,18 @@ def rows(decoded: dict[str, Any], slug: str) -> list[Row]:
path = (p.get("externalPath") or "").strip()
if not title or not _ROLE_PATH.fullmatch(path):
continue
remote = _remote(p.get("remoteType"))
place = _place(p.get("locationsText"), remote)
out.append({
"source_id": _requisition(p, path) or path,
"title": title,
"location": (p.get("locationsText") or "").strip(),
"places": [place] if place else [],
"location": place["text"] if place else "",
"url": f"https://{_host(slug)}/{_parts(slug)[2]}{path}", # type: ignore[index]
"posted": _posted(p.get("postedOn") or ""),
"department": "",
"description": "",
"remote": _remote(p.get("remoteType")),
"remote": remote,
"salary_text": "", # no field for pay, only the description's text
})
return out
@@ -208,26 +238,40 @@ def detail(get: Get, slug: str, row: Row) -> dict[str, Any]:
if description := " ".join(html.unescape(strip_html(posting.get("jobDescription") or ""))
.split()):
out["description"] = description
if location := _location(posting):
out["location"] = location
remote = _remote(posting.get("remoteType"))
if places := _places(posting, remote):
out["places"] = places
out["location"] = "; ".join(p["text"] for p in places)
if len(places) == 1 and (code := _country_code(posting)):
out["country"] = code
if employment := _EMPLOYMENT.get(str(posting.get("timeType") or "").strip().lower()):
out["employment"] = employment
if posted := parse_dt(posting.get("startDate")):
out["posted"] = posted
if remote := _remote(posting.get("remoteType")):
if remote:
out["remote"] = remote
return out
def _location(posting: dict[str, Any]) -> str:
"""The main location and the others, joined by "; " as Teamtailor does, so
that `country_of` reads them one at a time and the listing's "2 Locations"
is replaced by places. A single location that does not name its country
def _country_code(posting: dict[str, Any]) -> str | None:
"""The role's country as an ISO code, from the requisition's location. The
code belongs to the main location only, so it is used for a role with one
place."""
country = (posting.get("jobRequisitionLocation") or {}).get("country") or {}
code = str(country.get("alpha2Code") or "").strip().upper()
return code if len(code) == 2 else None
def _places(posting: dict[str, Any], remote: str | None) -> list[Place]:
"""The main location and the additional ones, each once, which replace the
listing's "2 Locations". A single location that does not name its country
(LEGO's "Billund") gets it from the role's `country`."""
places: list[str] = []
for place in [posting.get("location"), *(posting.get("additionalLocations") or [])]:
place = str(place or "").strip()
if place and place not in places:
places.append(place)
found: list[Place] = []
for name in [posting.get("location"), *(posting.get("additionalLocations") or [])]:
place = _place(name, remote)
if place and place["text"] not in (p["text"] for p in found):
found.append(place)
country = str((posting.get("country") or {}).get("descriptor") or "").strip()
if len(places) == 1 and country and country.lower() not in places[0].lower():
places[0] += f", {country}"
return "; ".join(places)
if len(found) == 1 and country and country.lower() not in found[0]["text"].lower():
found[0]["text"] += f", {country}"
return found