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

+64 -13
View File
@@ -18,13 +18,24 @@ 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 ._shared import Get, Row, parse_dt
from ._contract import Ask, Fields, Place, Reads, Row
from ._shared import Get, parse_dt
log = logging.getLogger(__name__)
READS = Reads(
scope="board", listing="whole", text="detail", teaser=True, complete="whole",
places="many",
fields=Fields(posted="trusted", remote="stated", seniority="stated", employment="stated"),
robots="read: robots.txt allows /jobs/companies/ (checked 2026-09-29)",
)
NAME = "jobylon"
LABEL = "Jobylon"
@@ -47,6 +58,21 @@ _SLUG = re.compile(r"[0-9]{1,12}")
#: from.
_ROLE_PATH = re.compile(r"/jobs/[0-9]+(?:-[A-Za-z0-9_-]*)?/?")
#: The embed's `experience` -> `app.models.SENIORITIES`. Only the coarse levels
#: are mapped; "Experienced" sits between "Mid level" and the managerial
#: levels and says too little to place, so it stays unmapped and is logged.
_SENIORITY = {"student": "intern", "internship": "intern", "trainee": "intern",
"entry level": "junior", "entry-level": "junior", "junior": "junior",
"graduate": "junior", "mid level": "mid", "mid-level": "mid", "mid": "mid",
"senior": "senior", "lead": "lead", "manager": "manager", "director": "director",
"executive": "exec", "not applicable": ""}
#: The embed's `employment_type` -> the app's employment words.
_EMPLOYMENT = {"full-time": "full_time", "full time": "full_time", "part-time": "part_time",
"part time": "part_time", "contract": "contract", "consultant": "contract",
"temporary": "temporary", "internship": "intern", "intern": "intern",
"freelance": "freelance", "summer job": "temporary", "seasonal": "temporary"}
_ASSIGNMENT = "JBL.embed_v2['jobs'] = "
_KEY = re.compile(r"[A-Za-z_][A-Za-z0-9_]*")
_TRAILING_COMMA = re.compile(r",(\s*[\]}])")
@@ -74,17 +100,13 @@ def careers_url(slug: str) -> str:
return f"https://{_EMP}/companies/{slug}/"
def feed_url(slug: str) -> str:
def feed_url(slug: str, ask: Ask) -> str:
"""Both hosts serve the same robots.txt (compared on 2026-09-29), so the
roles' pages on emp.jobylon.com are covered by what was checked for this
one."""
return f"https://{_CDN}/jobs/companies/{slug}/embed/v2/"
def robots_page(slug: str) -> str:
"""The page the board is read from. Both hosts serve the same robots.txt
(compared on 2026-09-29), so the roles' pages on emp.jobylon.com are
covered by the check on this one."""
return feed_url(slug)
def _json(text: str) -> Any:
"""A JavaScript array or object literal as JSON: keys quoted, strings
single-quoted with `\\uXXXX` escapes, trailing commas."""
@@ -157,6 +179,22 @@ def _published(value: Any) -> Any:
return parse_dt(f"{match.group(3)}-{month:02d}-{int(match.group(2)):02d}")
def _mapped(table: dict[str, str], value: Any, what: str) -> str | None:
"""`table`'s word for the host's `value`; None when the host states none
or the table does not know it (logged, so the table can grow)."""
word = str(value or "").strip()
if not word:
return None
found = table.get(word.lower())
if found is None:
log.debug("jobylon: unknown %s %r", what, word)
return found or None
def _place(text: str) -> Place:
return {"text": text, "remote": True if re.search(r"\bremote\b", text, re.I) else None}
def parse(body: bytes, slug: str) -> list[Row]:
"""The embed page -> one row per role. `posted` is the day `published_date`
names, which `detail` replaces with the exact time. `location` joins the
@@ -172,18 +210,30 @@ def parse(body: bytes, slug: str) -> list[Row]:
if not title or not job_id or not _ROLE_PATH.fullmatch(path):
continue
function = str(j.get("function") or "").strip()
out.append({
places = [_place(name) for name in dict.fromkeys(
str(name).strip() for name in j.get("locations") or [] if str(name).strip())]
row: Row = {
"source_id": job_id,
"title": title,
"location": "; ".join(dict.fromkeys(
str(name).strip() for name in j.get("locations") or [] if str(name).strip())),
"places": places,
"location": "; ".join(pl["text"] for pl in places),
"url": f"https://{_EMP}{path}",
"posted": _published(j.get("published_date")),
"department": "" if function == "All functions" else function,
"description": "",
"remote": _REMOTE.get(str(j.get("workspace") or "").strip().lower()),
"salary_text": "", # the embed states no pay
})
}
# `summary` is the text the company gave the listing, the string
# "None" when it gave none.
summary = " ".join(html.unescape(strip_html(str(j.get("summary") or ""))).split())
if summary and summary != "None":
row["teaser"] = summary
if seniority := _mapped(_SENIORITY, j.get("experience"), "experience"):
row["seniority"] = seniority
if employment := _mapped(_EMPLOYMENT, j.get("employment_type"), "employment_type"):
row["employment"] = employment
out.append(row)
return out
@@ -213,4 +263,5 @@ def detail(get: Get, slug: str, row: Row) -> dict[str, Any]:
}
if places:
found["location"] = "; ".join(places)
found["places"] = [_place(name) for name in places]
return found