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

+52 -5
View File
@@ -16,12 +16,32 @@ The field map is ported from `openings.go` in
from __future__ import annotations
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, is_web_url, num, only, parse_dt, path_slug_ok, pay_line, yearly_amount
from ._contract import Ask, Fields, Place, Reads, Row
from ._shared import is_web_url, num, only, parse_dt, path_slug_ok, pay_line, yearly_amount
log = logging.getLogger(__name__)
READS = Reads(
scope="board", listing="whole", text="listing", complete="whole",
places="many",
fields=Fields(pay="figures", posted="trusted", remote="stated", country="stated",
employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
)
#: `categories.commitment` -> the app's employment words. A commitment is free
#: text on Lever ("Permanent" is seen too and says nothing about hours).
_EMPLOYMENT = {"full-time": "full_time", "full time": "full_time", "fulltime": "full_time",
"part-time": "part_time", "part time": "part_time", "parttime": "part_time",
"intern": "intern", "internship": "intern", "contract": "contract",
"contractor": "contract", "temporary": "temporary", "freelance": "freelance"}
NAME = "lever"
LABEL = "Lever"
@@ -60,7 +80,7 @@ def careers_url(slug: str) -> str:
return f"https://jobs.{infix}lever.co/{site}"
def feed_url(slug: str) -> str:
def feed_url(slug: str, ask: Ask) -> str:
infix, site = _split(slug)
return f"https://api.{infix}lever.co/v0/postings/{site}?mode=json"
@@ -88,6 +108,19 @@ def _salary_text(salary_range: dict[str, Any]) -> str:
salary_range.get("currency"), period)
def _places(categories: dict[str, Any]) -> list[Place]:
"""`categories.allLocations` (every place of the role, the first being
`location`), or `location` alone when the list is missing."""
names = [categories.get("location"), *(categories.get("allLocations") or [])]
out: list[Place] = []
for name in names:
text = str(name or "").strip()
if text and text not in (p["text"] for p in out):
out.append({"text": text, "remote": True if re.search(r"\bremote\b", text, re.I)
else None})
return out
def parse(body: bytes, slug: str) -> list[Row]:
data = json.loads(body)
if not isinstance(data, list):
@@ -104,10 +137,12 @@ def parse(body: bytes, slug: str) -> list[Row]:
salary_min, salary_max, currency = yearly_amount(
salary_range.get("min"), salary_range.get("max"), salary_range.get("currency"),
salary_range.get("interval"), {"per-year-salary": 1, "per-month-salary": 12})
rows.append({
places = _places(categories)
row: Row = {
"source_id": str(j.get("id") or ""),
"title": title,
"location": (categories.get("location") or "").strip(),
"places": places,
"location": "; ".join(p["text"] for p in places),
"url": url,
"posted": parse_dt(j.get("createdAt")),
"department": (categories.get("department") or categories.get("team") or "").strip(),
@@ -117,5 +152,17 @@ def parse(body: bytes, slug: str) -> list[Row]:
"salary_min": salary_min,
"salary_max": salary_max,
"currency": currency,
})
}
# `country` is one code, for a role at one place; over several it would
# gate the others by the first's country.
country = str(j.get("country") or "").strip().upper()
if len(places) == 1 and re.fullmatch(r"[A-Z]{2}", country):
row["country"] = country
commitment = str(categories.get("commitment") or "").strip()
if commitment:
if employment := _EMPLOYMENT.get(commitment.lower()):
row["employment"] = employment
else:
log.debug("lever: unknown commitment %r", commitment)
rows.append(row)
return rows