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:
1 parent
4c0da58da7
commit
f2e652a8da
35 files changed
+1290
-391
No files matched your search
+50
-10
@@ -30,13 +30,29 @@ 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, Page, Row, only, parse_dt
|
||||
from ._contract import Ask, Fields, Place, Reads, Row
|
||||
from ._shared import Get, Page, only, parse_dt
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
READS = Reads(
|
||||
scope="board", listing="paged", page_size=100, text="listing", complete="stated",
|
||||
places="many",
|
||||
fields=Fields(posted="listed", country="stated", employment="stated"),
|
||||
robots="read: robots.txt allows /jobs, with crawl-delay 5 not honoured (checked 2026-09-29)",
|
||||
)
|
||||
|
||||
#: `employment_type` -> the app's employment words.
|
||||
_EMPLOYMENT = {"FULL_TIME": "full_time", "PART_TIME": "part_time", "CONTRACTOR": "contract",
|
||||
"CONTRACT": "contract", "TEMPORARY": "temporary", "INTERN": "intern",
|
||||
"INTERNSHIP": "intern", "FREELANCE": "freelance"}
|
||||
|
||||
NAME = "jibe"
|
||||
LABEL = "Jibe"
|
||||
@@ -73,11 +89,7 @@ def careers_url(slug: str) -> str:
|
||||
return f"https://{slug.lower()}/jobs"
|
||||
|
||||
|
||||
def robots_page(slug: str) -> str:
|
||||
return careers_url(slug)
|
||||
|
||||
|
||||
def page(get: Get, slug: str, cursor: Any) -> Page:
|
||||
def page(get: Get, slug: str, cursor: Any, ask: Ask) -> Page:
|
||||
"""One page of `/api/jobs`; the next is the following number, and an empty
|
||||
page ends the read."""
|
||||
number = int(cursor or 1)
|
||||
@@ -99,6 +111,21 @@ def _plain(markup: Any) -> str:
|
||||
return " ".join(html.unescape(strip_html(str(markup or ""))).split())
|
||||
|
||||
|
||||
def _places(j: dict[str, Any]) -> list[Place]:
|
||||
"""`full_location` names every place of the role, "; " apart, each as
|
||||
"City, Country"; the site's `city` and `country` stand in when it is
|
||||
missing."""
|
||||
line = str(j.get("full_location") or "").strip() \
|
||||
or ", ".join(p for p in (j.get("city"), j.get("country")) if p)
|
||||
out: list[Place] = []
|
||||
for part in line.split(";"):
|
||||
text = part.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 rows(data: dict[str, Any], slug: str) -> list[Row]:
|
||||
"""One page: each `jobs[].data` has `slug` (equal to `req_id`), `title`,
|
||||
the HTML `description` and, on some, `qualifications`, `full_location`
|
||||
@@ -117,16 +144,29 @@ def rows(data: dict[str, Any], slug: str) -> list[Row]:
|
||||
categories = j.get("categories") or []
|
||||
text = "\n\n".join(p for p in (_plain(j.get("description")),
|
||||
_plain(j.get("qualifications"))) if p)
|
||||
out.append({
|
||||
places = _places(j)
|
||||
row: Row = {
|
||||
"source_id": role,
|
||||
"title": title,
|
||||
"location": (j.get("full_location")
|
||||
or ", ".join(p for p in (j.get("city"), j.get("country")) if p)).strip(),
|
||||
"places": places,
|
||||
"location": "; ".join(p["text"] for p in places),
|
||||
"url": f"https://{slug.lower()}/jobs/{role}",
|
||||
"posted": parse_dt(j.get("posted_date")),
|
||||
"department": str((categories[0] if categories else {}).get("name") or "").strip(),
|
||||
"description": text,
|
||||
"remote": None,
|
||||
"salary_text": "",
|
||||
})
|
||||
}
|
||||
# One code, for a role at one place: over several countries it would
|
||||
# gate the others by the site's own.
|
||||
code = str(j.get("country_code") or "").strip().upper()
|
||||
if len(places) == 1 and re.fullmatch(r"[A-Z]{2}", code):
|
||||
row["country"] = code
|
||||
kind = str(j.get("employment_type") or "").strip()
|
||||
if kind:
|
||||
if employment := _EMPLOYMENT.get(kind.upper()):
|
||||
row["employment"] = employment
|
||||
else:
|
||||
log.debug("jibe: unknown employment_type %r", kind)
|
||||
out.append(row)
|
||||
return out
|
||||
Reference in new issue
Block a user