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

+20 -9
View File
@@ -16,6 +16,7 @@ from typing import Any
from desk.sources import strip_html
from ._contract import Ask, Fields, Place, Reads
from ._shared import Get, Page, Row, is_web_url, only, parse_dt
NAME = "teamtailor"
@@ -28,6 +29,12 @@ PATTERNS = (
r"cdn\.teamtailor\.com|teamtailor-cdn|teamtailor\.com/assets",
)
READS = Reads(
scope="board", listing="paged", page_size=50, text="listing", complete="end",
places="many", fields=Fields(posted="trusted", remote="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
)
#: The page size, asked for as `per_page`. A feed with neither parameter
#: answers with every role (73 of 73 at Shine, 2026-09-29), but says nowhere
#: that it is the whole list, so this reads by page to an empty one;
@@ -80,7 +87,7 @@ def probe_ok(body: bytes) -> bool:
return b"<item>" in body
def page(get: Get, slug: str, cursor: Any) -> Page:
def page(get: Get, slug: str, cursor: Any, ask: Ask = Ask()) -> Page:
offset = int(cursor or 0)
items = _items(get(f"https://{site(slug)}/jobs.rss?per_page={PAGE_SIZE}&offset={offset}"))
results = [{"id": item.findtext("guid") or item.findtext("link") or ""} for item in items]
@@ -106,32 +113,36 @@ def rows(items: list[ET.Element], slug: str) -> list[Row]:
own domain), a `guid` uuid, `pubDate`, the HTML `description` in full,
`remoteStatus` (fully, hybrid, onsite, none or temporary), and, in the
`tt:` namespace, `locations` (a list: `city` and `country` each, `name` free
text), `department` and `role`, either of which may be empty. `place` joins
the distinct locations with "; ", which `country_of` reads a location at a
time. No pay is stated anywhere in the feed."""
text), `department` and `role`, either of which may be empty. `places` keeps
the distinct locations, and `location` joins them with "; ". A place is
remote or an office as far as the role's `remoteStatus` says. No pay is
stated anywhere in the feed."""
out = []
for item in items:
title = (item.findtext("title") or "").strip()
url = (item.findtext("link") or "").strip()
if not title or not is_web_url(url):
continue
places: list[str] = []
status = (item.findtext("remoteStatus") or "").strip()
remote = {"fully": True, "hybrid": False, "onsite": False}.get(status)
places: list[Place] = []
for loc in item.findall(f"{_TT}locations/{_TT}location"):
city = (loc.findtext(f"{_TT}city") or loc.findtext(f"{_TT}name") or "").strip()
country = (loc.findtext(f"{_TT}country") or "").strip()
place = city if country == city else ", ".join(p for p in (city, country) if p)
if place and place not in places:
places.append(place)
if place and place not in (p["text"] for p in places):
places.append({"text": place, "remote": remote})
out.append({
"source_id": (item.findtext("guid") or url).strip(),
"title": title,
"location": "; ".join(places),
"places": places,
"location": "; ".join(p["text"] for p in places),
"url": url,
"posted": parse_dt(item.findtext("pubDate")),
"department": ((item.findtext(f"{_TT}department") or "").strip()
or (item.findtext(f"{_TT}role") or "").strip()),
"description": html.unescape(strip_html(item.findtext("description") or "")),
"remote": _REMOTE.get((item.findtext("remoteStatus") or "").strip()),
"remote": _REMOTE.get(status),
"salary_text": "", # Teamtailor's feed states no pay at all
})
return out