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

+29 -14
View File
@@ -21,6 +21,7 @@ from urllib.parse import quote
from desk.sources import strip_html
from ._contract import Ask, Fields, Place, Reads
from ._shared import Get, Page, Row, only, parse_dt
NAME = "oracle"
@@ -38,6 +39,14 @@ PATTERNS = (
r"oraclecloud\.(?:com|eu)/hcmUI(?!/CandidateExperience/[A-Za-z_-]+/sites/)",
)
READS = Reads(
scope="board", listing="paged", page_size=200, text="detail", teaser=True,
complete="stated", places="many",
fields=Fields(posted="trusted", remote="stated", country="stated"),
robots=("read: robots.txt allows /hcmUI/CandidateExperience/en/sites/<site>/jobs "
"(checked 2026-09-29)"),
)
#: The page size asked for. 200 was answered in full by Nokia (600 roles in
#: three calls of about 360 KB, 2026-09-29); the cursor advances by what a page
#: returned, so a tenant that caps `limit` lower would not skip a role.
@@ -77,15 +86,11 @@ def careers_url(slug: str) -> str:
return f"{_base(slug)}/jobs"
def robots_page(slug: str) -> str:
return careers_url(slug)
def _api(slug: str) -> str:
return f"https://{_parts(slug)[0]}/hcmRestApi/resources/latest"
def page(get: Get, slug: str, cursor: Any) -> Page:
def page(get: Get, slug: str, cursor: Any, ask: Ask = Ask()) -> Page:
"""One page of `recruitingCEJobRequisitions`. The answer's outer `count`,
`hasMore` and `limit` describe the one search wrapper in `items`, so the
total (`TotalJobsCount`) and the roles (`requisitionList`) are read from
@@ -135,22 +140,32 @@ def rows(search: dict[str, Any], slug: str) -> list[Row]:
# The id goes into a URL, and a listing is external content.
if not title or not re.fullmatch(r"[A-Za-z0-9_-]+", role_id):
continue
places: list[str] = []
for name in (_text(role.get("PrimaryLocation")),
*(_text(s.get("Name")) for s in role.get("secondaryLocations") or []
if isinstance(s, dict))):
if name and name not in places:
places.append(name)
remote = _REMOTE.get(_text(role.get("WorkplaceTypeCode")).lower())
places: list[Place] = []
codes: set[str] = set()
secondary = [s for s in role.get("secondaryLocations") or [] if isinstance(s, dict)]
for name, code in ((_text(role.get("PrimaryLocation")),
_text(role.get("PrimaryLocationCountry"))),
*((_text(s.get("Name")), _text(s.get("CountryCode")))
for s in secondary)):
if name and name not in (p["text"] for p in places):
places.append({"text": name, "remote": {"remote": True, "hybrid": False,
"onsite": False}.get(remote or "")})
if code:
codes.add(code.upper())
out.append({
"source_id": role_id,
"title": title,
"location": "; ".join(places),
"places": places,
"location": "; ".join(p["text"] for p in places),
"url": f"{_base(slug)}/job/{role_id}",
"posted": parse_dt(role.get("PostedDate")),
"department": (_text(role.get("JobFamily")) or _text(role.get("JobFunction"))
or _text(role.get("Department")) or _text(role.get("Organization"))),
"description": _plain(role.get("ShortDescriptionStr")),
"remote": _REMOTE.get(_text(role.get("WorkplaceTypeCode")).lower()),
"description": "",
"teaser": _plain(role.get("ShortDescriptionStr")),
"country": next(iter(codes)) if len(codes) == 1 else None,
"remote": remote,
"salary_text": "", # the resource states no pay
})
return out