Require READS, search params and a dated robots record; record robots.txt per requested path

Every reader declares, so undeclared(), the scope() fallback, robots_page and
ROBOTS_ANY_CASE go. A search provider needs PARAMS and clean_params, a row may
carry company, places gains none. Each robots record names the paths the
reader requests, from robots.txt read again on 2026-09-30. Platsbanken states
remote, HR Manager states no place.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Fable 5.1 committed 2026-09-30 15:51:13 +02:00
1 parent 4e827665dd
commit 2349fc424b
46 files changed
+323 -100

No files matched your search

+14 -22
View File
@@ -241,7 +241,7 @@ from . import _contract
from ._contract import Ask, Fields, Filters, Key, Place, Reads, Row
__all__ = ["DEFAULT_RANK", "HOSTS", "PROVIDERS", "READERS", "Ask", "Fields", "Filters", "Key",
"Place", "Reads", "Row", "load", "problems", "scope", "undeclared"]
"Place", "Reads", "Row", "load", "problems"]
#: The rank of a module that states none: after the eight first hosts, whose
#: ranks (10 to 80) keep the order they had before there were modules.
@@ -250,27 +250,28 @@ DEFAULT_RANK = 100
#: What every board module defines.
REQUIRED = ("NAME", "LABEL", "PATTERNS", "slug_ok", "allowed", "careers_url")
#: What a module of `scope="search"` defines.
REQUIRED_SEARCH = ("NAME", "LABEL", "allowed")
#: What a module of `scope="search"` defines: `PARAMS` and `clean_params` are
#: what `app/jobs/sources.search_params` stores a search's params with.
REQUIRED_SEARCH = ("NAME", "LABEL", "allowed", "PARAMS", "clean_params")
#: The functions a module may define; each must be callable if present.
FUNCTIONS = ("slug_ok", "allowed", "careers_url", "feed_url", "parse", "page", "rows",
"fallback_url", "robots_page", "detail", "facets", "probe_url", "probe_ok",
"fallback_url", "detail", "facets", "clean_params", "probe_url", "probe_ok",
"probe_slugs")
def scope(module: ModuleType) -> str:
"""`board` or `search`; `board` for a module without `READS`."""
def _search(module: ModuleType) -> bool:
reads = getattr(module, "READS", None)
return reads.scope if isinstance(reads, Reads) else "board"
return isinstance(reads, Reads) and reads.scope == "search"
def problems(module: ModuleType, name: str | None = None) -> list[str]:
"""What `module` lacks or gets wrong against the contract, one phrase
each; empty for a module that keeps it. `name` is the module's own name
in the package, which `NAME` must equal. `READS` is checked when the
module declares one (`_contract.problems`)."""
required = REQUIRED_SEARCH if scope(module) == "search" else REQUIRED
in the package, which `NAME` must equal. A module without `READS` is
held to a board's names and fails on the missing declaration; the
declaration itself is `_contract.problems`."""
required = REQUIRED_SEARCH if _search(module) else REQUIRED
out = [f"no {attr}" for attr in required if not hasattr(module, attr)]
if name is not None and getattr(module, "NAME", name) != name:
out.append(f"NAME is {module.NAME!r}, not the module's name {name!r}")
@@ -278,8 +279,6 @@ def problems(module: ModuleType, name: str | None = None) -> list[str]:
out.append("LABEL is not a non-empty string")
if not isinstance(getattr(module, "KEEP_CASE", False), bool):
out.append("KEEP_CASE is not a bool")
if not isinstance(getattr(module, "ROBOTS_ANY_CASE", False), bool):
out.append("ROBOTS_ANY_CASE is not a bool")
rank = getattr(module, "RANK", DEFAULT_RANK)
if not isinstance(rank, int) or isinstance(rank, bool):
out.append("RANK is not an int")
@@ -323,20 +322,13 @@ def load(path: Iterable[str], package: str) -> dict[str, ModuleType]:
return {module.NAME: module for module in modules}
def undeclared(modules: dict[str, ModuleType] | None = None) -> list[str]:
"""The names of the modules (of `READERS` by default) without `READS`,
read with the older signatures until they declare."""
return [name for name, module in (READERS if modules is None else modules).items()
if not hasattr(module, "READS")]
#: name -> module for every reader, in order of `(RANK, NAME)`.
READERS: dict[str, ModuleType] = load(__path__, __name__)
#: host -> its module: the readers of `scope="board"` and the undeclared.
#: host -> its module: the readers of `scope="board"`.
HOSTS: dict[str, ModuleType] = {name: module for name, module in READERS.items()
if scope(module) == "board"}
if module.READS.scope == "board"}
#: provider -> its module: the readers of `scope="search"`.
PROVIDERS: dict[str, ModuleType] = {name: module for name, module in READERS.items()
if scope(module) == "search"}
if module.READS.scope == "search"}
+32 -12
View File
@@ -20,14 +20,14 @@ Signatures of a module that declares `READS`, with `Get` and `Page` from
def rows(decoded: Any, slug: str) -> list[Row] # listing="paged"
def detail(get: Get, slug: str, row: Row) -> dict[str, Any] # text="detail"
def facets(get: Get, slug: str) -> dict[str, dict[str, str]] # an "ids" filter
def clean_params(params: dict[str, Any]) -> dict[str, Any] # scope="search"
`facets` maps each `ids` dimension to `{value: host id}`: an ISO code for
`country`, a place name for `place`, any word for `remote`. A dimension the
host has no facet for is left out, and the runner then reads it unfiltered;
a dimension present without a wanted value means the host has none of it.
A module without `READS` keeps the signatures without `ask` until it
declares; `undeclared()` in the package lists those modules.
A module without `READS` fails the import: every reader declares.
"""
from __future__ import annotations
@@ -57,6 +57,9 @@ _CONFIG_NAME = re.compile(r"[a-z][a-z0-9_]*")
#: An environment variable name.
_ENV_NAME = re.compile(r"[A-Z][A-Z0-9_]*")
#: The date a robots.txt record must carry: when the file was read.
_DATE = re.compile(r"20\d\d-\d\d-\d\d")
class _Frozen(Model):
"""A declaration: immutable, extra keys refused."""
@@ -123,11 +126,13 @@ class Reads(_Frozen):
`Row.teaser`. `complete`: `stated` (a total), `end` (an empty page),
`whole` (the one answer), `never` (a search). `places`: `one` (the host
states one), `many` (a list per role), `copies` (the host lists one
posting per place, each with its own id). `robots`: the robots.txt
decision, with the date, taken when the reader was built. `empty`:
`suspect` when an unknown slug answers an empty list rather than an
error. `title`: `provisional` when the listing may not state the title
(a sitemap), which detail then fills.
posting per place, each with its own id), `none` (the host states no
place; every row has `places == []`). `robots`: the robots.txt
decision for the paths the reader requests, with the date the file was
read. `empty`: `suspect` when an unknown slug answers an empty list
rather than an error. `title`: `provisional` when the listing may not
state the title (a sitemap), which detail then fills; nothing reads it
yet, since `_runner.DETAIL_FIELDS` has no `title`.
"""
scope: Literal["board", "search"]
@@ -138,7 +143,7 @@ class Reads(_Frozen):
teaser: bool = False
complete: Literal["stated", "end", "whole", "never"]
filters: Filters = Filters()
places: Literal["one", "many", "copies"]
places: Literal["one", "many", "copies", "none"]
fields: Fields = Fields()
robots: str
empty: Literal["trusted", "suspect"] = "trusted"
@@ -196,8 +201,10 @@ class Row(TypedDict, total=False):
place, kept while storage reads it. `posted` is an aware datetime or
None; `description` plain text; `remote` True, False, a word or None;
pay per `Fields.pay`. `country` (ISO alpha-2), `seniority` and
`employment` only where the host states them, as `Fields` declares. Any
other stated key is kept in `raw` by the runner.
`employment` only where the host states them, as `Fields` declares.
`company` is the employer's name on a search row, which lists many
(`plugins/search.py` stores it); a board row carries none, the board is
the company. Any other stated key is kept in `raw` by the runner.
"""
source_id: Required[str]
@@ -217,6 +224,7 @@ class Row(TypedDict, total=False):
country: str | None
seniority: str | None
employment: str | None
company: str
#: What a declared module's functions take, positionally.
@@ -227,6 +235,7 @@ SIGNATURES: dict[str, tuple[str, ...]] = {
"rows": ("decoded", "slug"),
"detail": ("get", "slug", "row"),
"facets": ("get", "slug"),
"clean_params": ("params",),
}
@@ -245,9 +254,9 @@ def _takes(function: Callable[..., Any], count: int) -> bool:
def problems(module: ModuleType) -> list[str]:
"""What `module`'s `READS` gets wrong, on its own or against the
module's functions; empty for a module that declares none."""
module's functions; "no READS" for a module that declares none."""
if not hasattr(module, "READS"):
return []
return ["no READS: every reader declares what it reads"]
reads = module.READS
if not isinstance(reads, Reads):
return ["READS is not a Reads"]
@@ -305,6 +314,17 @@ def problems(module: ModuleType) -> list[str]:
if not reads.robots.strip():
out.append("robots is empty: record the robots.txt decision and its date")
elif not _DATE.search(reads.robots):
out.append("robots has no date: record when robots.txt was read (YYYY-MM-DD)")
if reads.scope == "search" and hasattr(module, "PARAMS"):
params = module.PARAMS
if not isinstance(params, dict) or not params:
out.append("PARAMS is not a dict of saved param -> filter dimension")
else:
dimensions = set(Filters.model_fields)
out += [f"PARAMS maps {param!r} to {dimension!r}, not a filter dimension"
for param, dimension in params.items() if dimension not in dimensions]
for name, params in SIGNATURES.items():
if has(name) and not _takes(getattr(module, name), len(params)):
+2 -1
View File
@@ -31,7 +31,8 @@ READS = Reads(
scope="board", listing="whole", text="listing", complete="whole",
places="many", empty="suspect",
fields=Fields(pay="figures", posted="trusted", remote="stated", employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read: api.ashbyhq.com answers /robots.txt with 401 and no rules, so "
"/posting-api/job-board/<slug> is not disallowed (checked 2026-09-30)"),
)
_API = "api.ashbyhq.com"
+3 -1
View File
@@ -55,7 +55,9 @@ READS = Reads(
scope="board", listing="paged", page_size=10, text="detail", complete="stated",
places="many", filters=Filters(country="one", query="one"),
fields=Fields(posted="listed", remote="stated"),
robots="read: robots.txt allows /careers (checked 2026-09-29)",
robots=("read: robots.txt disallows / and allows /api/pcsx, which covers "
"/api/pcsx/search and /api/pcsx/position_details (jobs.ericsson.com, "
"checked 2026-09-30)"),
)
NAME = "eightfold"
+2 -1
View File
@@ -35,7 +35,8 @@ READS = Reads(
scope="board", listing="paged", text="detail", complete="end",
places="many", empty="suspect",
fields=Fields(posted="listed", remote="stated", employment="stated"),
robots="read: robots.txt allows /<board> (checked 2026-09-29)",
robots=("read: POST /api/public/graphql on jobs.gem.com, whose /robots.txt answers "
"404, so nothing is disallowed (checked 2026-09-30)"),
)
NAME = "gem"
+2 -1
View File
@@ -29,7 +29,8 @@ READS = Reads(
scope="board", listing="whole", text="listing", complete="whole",
places="many",
fields=Fields(pay="figures", posted="trusted"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read: boards-api.greenhouse.io's robots.txt disallows /embed/ only, so "
"/v1/boards/<slug>/jobs is allowed (checked 2026-09-30)"),
)
_API = "boards-api.greenhouse.io"
+2 -2
View File
@@ -34,8 +34,8 @@ READS = Reads(
scope="board", listing="paged", text="listing", complete="end",
places="copies",
fields=Fields(pay="figures", posted="listed", remote="stated", employment="stated"),
robots="read: robots.txt allows the careers site; its robots.txt is the single-page "
"app's index page with no rules (checked 2026-09-29)",
robots=("read: /api/job-ad on <slug>.careers.hibob.com, whose /robots.txt answers the "
"single-page app's index page, no rules (dixa, checked 2026-09-30)"),
)
NAME = "hibob"
+10 -5
View File
@@ -14,9 +14,11 @@ everything for `*` except the application form. The feed is on the API host,
which has no robots.txt (a 404, which allows); it is the interface HR Manager
publishes for readers like this one, and the portal's HTML list, which the
robots.txt does shut out, is never read. The role's link is the application
form the robots.txt names as allowed, and is only shown, not fetched. The
declaration says "disallowed" all the same, and the owner decides whether the
feed is read.
form the robots.txt names as allowed, and is only shown, not fetched.
`READS.robots` records both hosts and the owner's decision.
The feed names no place (the title or the text may), so every row has
`places == []` (`places="none"`).
"""
from __future__ import annotations
@@ -34,9 +36,12 @@ from ._shared import Get, Page, is_web_url, only, parse_dt
READS = Reads(
scope="board", listing="paged", page_size=100, text="listing", complete="end",
places="one",
places="none",
fields=Fields(posted="listed"),
robots="disallowed by robots.txt; owner to decide",
robots=("read: the feed /JobPortal.svc/<customer>/PositionList/rss/ is on "
"api.hr-manager.net, whose /robots.txt answers 404 (checked 2026-09-30); the portal "
"candidate.hr-manager.net disallows all but /ApplicationInit.aspx? and is not "
"read: owner, 2026-09-29"),
)
NAME = "hrmanager"
+2 -1
View File
@@ -46,7 +46,8 @@ 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)",
robots=("read: robots.txt allows /, so /api/jobs, with crawl-delay 5 not honoured "
"(jobs.booking.com, checked 2026-09-30)"),
)
NAME = "jibe"
+4 -1
View File
@@ -34,7 +34,10 @@ 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)",
robots=("read: robots.txt allows / for * and disallows /jobs/*/preview/, so "
"/jobs/companies/<id>/embed/v2/ on cdn.jobylon.com and /jobs/<id>-<name>/ on "
"emp.jobylon.com are allowed; it disallows / for named job crawlers (JobrapidoBot, "
"JoobleBot, AdzunaBot, ...), which this reader's agent is not (checked 2026-09-30)"),
)
NAME = "jobylon"
+2 -1
View File
@@ -32,7 +32,8 @@ READS = Reads(
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",
robots=("read: robots.txt of api.lever.co and api.eu.lever.co allows /, so "
"/v0/postings/<site>, with crawl-delay 1, one request a board (checked 2026-09-30)"),
)
NAME = "lever"
+3 -2
View File
@@ -60,8 +60,9 @@ READS = Reads(
scope="board", listing="paged", page_size=200, text="detail", teaser=True,
complete="stated", places="many", filters=Filters(country="ids", remote="one", query="one"),
fields=Fields(posted="trusted", remote="stated"),
robots=("read: robots.txt allows /hcmUI/CandidateExperience/en/sites/<site>/jobs "
"(checked 2026-09-29)"),
robots=("read: /hcmRestApi/resources/latest/recruitingCEJobRequisitions and "
"recruitingCEJobRequisitionDetails on the tenant's host, whose /robots.txt answers "
"404, so nothing is disallowed (four seed tenants, checked 2026-09-30)"),
)
#: The page size asked for. 200 was answered in full by Nokia (600 roles in
+2 -1
View File
@@ -24,7 +24,8 @@ READS = Reads(
scope="board", listing="whole", text="listing", complete="whole",
places="many",
fields=Fields(pay="figures", posted="trusted", seniority="stated", employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read: /xml on <slug>.jobs.personio.de, whose /robots.txt answers 404, so "
"nothing is disallowed (penneo, checked 2026-09-30)"),
)
#: Personio's `salaryInformation/type` spellings, to the plain period word
+4 -1
View File
@@ -52,7 +52,10 @@ READS = Reads(
scope="board", listing="paged", page_size=100, text="detail", teaser=True,
complete="stated", places="many", filters=Filters(country="many", query="one"),
fields=Fields(posted="trusted", remote="stated"),
robots="read: robots.txt allows /<country>/<lang>/search-results (checked 2026-09-29)",
robots=("read: robots.txt has no rule on POST /widgets or /<country>/<lang>/job/<id>; "
"it disallows */apply, */px-widgets, */jobcart and the like (careers.king.com, "
"careers.justeattakeaway.com; www.careers.philips.com redirects /robots.txt to "
"its careers page; checked 2026-09-30)"),
)
#: The page size asked for. 100 is what the site's own search sends; `size`
+1 -1
View File
@@ -33,7 +33,7 @@ READS = Reads(
text="listing", complete="stated",
filters=Filters(query="one", place="one"),
places="many",
fields=Fields(posted="trusted", country="stated"),
fields=Fields(posted="trusted", remote="stated", country="stated"),
robots="read: the host publishes no robots.txt, /robots.txt answers 404 "
"(checked 2026-09-30)")
+2 -1
View File
@@ -26,7 +26,8 @@ READS = Reads(
places="many",
fields=Fields(pay="figures", posted="trusted", remote="stated",
seniority="stated", employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read: <slug>.recruitee.com's robots.txt disallows /v/ only, so /api/offers/ "
"is allowed (famly, checked 2026-09-30)"),
)
#: What the board writes as a place for a role that is worked anywhere.
+3 -1
View File
@@ -49,7 +49,9 @@ READS = Reads(
places="one", empty="suspect", filters=Filters(country="one", query="one"),
fields=Fields(posted="trusted", remote="stated", country="stated", seniority="stated",
employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read though api.smartrecruiters.com's robots.txt disallows / for every agent "
"but LinkedInBot, which alone is allowed /v1/companies/, the path of the listing "
"and of each posting: owner to decide, checked 2026-09-30"),
)
_API = "api.smartrecruiters.com"
+3 -1
View File
@@ -32,7 +32,9 @@ PATTERNS = (
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",
robots=("read: a career site's robots.txt disallows /app/, /messages/, /messenger/, "
"/facebook/tab/ and /jobs/internal/, so /jobs.rss is allowed (lunar, which "
"redirects to jobs.lunar.app, and careers.trackunit.com, checked 2026-09-30)"),
)
#: The page size, asked for as `per_page`. A feed with neither parameter
+3 -1
View File
@@ -37,7 +37,9 @@ READS = Reads(
scope="board", listing="paged", page_size=10, text="detail", complete="stated",
places="many",
fields=Fields(posted="trusted", remote="stated", employment="stated"),
robots="api: no robots.txt check needed (public board API), 2026-09-30",
robots=("read: apply.workable.com's robots.txt disallows nothing (an empty Disallow), so "
"POST /api/v3/accounts/<slug>/jobs and /api/v2/accounts/<slug>/jobs/<shortcode> "
"are allowed (checked 2026-09-30)"),
)
_API = "apply.workable.com"
+3 -1
View File
@@ -52,7 +52,9 @@ READS = Reads(
scope="board", listing="paged", page_size=20, ceiling=2000, text="detail",
complete="stated", places="many", filters=Filters(country="ids", remote="ids", query="one"),
fields=Fields(posted="trusted", remote="stated", employment="stated"),
robots="read: robots.txt allows /<Site>/ (checked 2026-09-29)",
robots=("read: robots.txt allows /<Site>/ and disallows /refreshFacet/ and has no rule "
"on /wday/cxs/<tenant>/<site>/, the listing's POST .../jobs and each role's "
"JSON (zendesk.wd1, lego.wd103, saxobank.wd3, checked 2026-09-30)"),
)
#: One group for `<tenant>.<wdN>` and one for the site, which discovery joins
+55
View File
@@ -0,0 +1,55 @@
<!DOCTYPE html>
<html><head><title>CDL Driver Recruiter - Einride | Jobylon</title>
<script type="application/ld+json">
{
"@context": "http://schema.org",
"@type": "JobPosting",
"datePosted": "2026-09-22T11:58:11+00:00",
"description": "<p>Want to be part of transforming road freight? Einride is showing the world a new way to move, based on the latest digital, autonomous and electric technologies. We build the technology that hauls freight efficiently, and we put it to work for the world's leading manufacturers, retailers, logistics providers and defense organizations, all working toward a future where moving goods costs less for our customers, and less for the planet.</p>",
"hiringOrganization": {
"@type": "Organization",
"name": "Einride",
"sameAs": ""
},
"title": "CDL Driver Recruiter",
"jobLocation": [
{
"@type": "Place",
"address": {
"@type": "PostalAddress",
"streetAddress": "Houston, TX, USA",
"addressLocality": "Houston",
"url": "https://maps.google.com/?cid=14559296326948160827"
}
},
{
"@type": "Place",
"address": {
"@type": "PostalAddress",
"streetAddress": "Dallas, TX, USA",
"addressLocality": "Dallas",
"url": "https://maps.google.com/?cid=13397254124329199503"
}
},
{
"@type": "Place",
"address": {
"@type": "PostalAddress",
"streetAddress": "New Jersey, USA",
"addressLocality": "",
"url": "https://maps.google.com/?cid=3229779156937960845"
}
},
{
"@type": "Place",
"address": {
"@type": "PostalAddress",
"streetAddress": "Atlanta, GA, USA",
"addressLocality": "Atlanta",
"url": "https://maps.google.com/?cid=7421613531965645579"
}
}
]
}
</script>
</head><body></body></html>
+28
View File
@@ -0,0 +1,28 @@
<!DOCTYPE html>
<html><head><title>Financial Controller - Einride | Jobylon</title>
<script type="application/ld+json">
{
"@context": "http://schema.org",
"@type": "JobPosting",
"datePosted": "2026-09-25T13:59:14+00:00",
"description": "<p>Want to be part of transforming road freight? Einride is showing the world a new way to move, based on the latest digital, autonomous and electric technologies. We build the technology that hauls freight efficiently, and we put it to work for the world's leading manufacturers, retailers, logistics providers and defense organizations, all working toward a future where moving goods costs less for our customers, and less for the planet.</p>",
"hiringOrganization": {
"@type": "Organization",
"name": "Einride",
"sameAs": ""
},
"title": "Financial Controller",
"jobLocation": [
{
"@type": "Place",
"address": {
"@type": "PostalAddress",
"streetAddress": "Stockholm, Sweden",
"addressLocality": "Stockholm",
"url": "https://maps.google.com/?cid=12109378761999087462"
}
}
]
}
</script>
</head><body></body></html>
+53
View File
@@ -0,0 +1,53 @@
{
"uuid": "0fbcec57-3012-4271-96bf-12b145cf6dea",
"name": "General Applications: Engineering",
"description": {
"company": "<meta><h3 style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;line-height:1.6;font-size:13.5pt;font-weight:600;letter-spacing:0.25px;margin-top:14px;margin-bottom:4px;text-align:start;padding-left:0px;\"><b><strong style=\"white-space:pre-wrap;\">Not finding the perfect engineering role on our careers page?</strong></b></h3><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11.25pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;\"><span style=\"white-space:pre-wrap;\">We are constantly seeking talented individuals to join our team. If you are a Software Engineer and haven\u2019t found the perfect role on our careers page, don\u2019t worry \u2014 you\u2019ve come to the right place.</span></p><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11.25pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;\"><br></p><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11.25pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;\"><span style=\"white-space:pre-wrap;\">We strongly believe that each person has something unique to bring to the table. Whether you\u2019re a recent graduate or a seasoned professional, we\u2019re genuinely excited to hear from you. At Prisma, we work with modern technologies, including </span><b><strong style=\"white-space:pre-wrap;\">TypeScript</strong>",
"role": "<meta><h3 style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;line-height:1.6;font-size:13.5pt;font-weight:600;letter-spacing:0.25px;margin-top:14px;margin-bottom:4px;text-align:start;padding-left:0px;\"><b><strong style=\"white-space:pre-wrap;\">What is it like to work at Prisma?</strong></b></h3><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11.25pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;text-align:start;\"><span style=\"white-space:pre-wrap;\">You're likely to be a great fit for the team if you ...</span></p><ul data-pattern=\"discCircleSquare\" data-depth=\"1\" style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11pt;font-weight:400;margin:8px 0px;line-height:1.6;padding:0px 0px 0px 32px;list-style-type:disc;\"><li style=\"font-size:11pt;margin:3px 0px;letter-spacing:0.25px;line-height:1.6;\"><b><strong style=\"white-space:pre-wrap;\">... have an ownership mindset.</strong></b><span style=\"white-space:pre-wrap;\"> As part of a small team, you'll have an outsize impact on decisions and the way things are executed.</span></li><li style=\"font-size:11pt;margin:3px 0px;letter-spacing:0.25px;line-height:1.6;\"><b><strong style=\"white-space:pre-wrap;\">... stay nimble.</strong></b><span style=\"white-space:pre-wrap;\"> As a growing startup, the team and strategy evolves quickly. Be ready to re-calibrate often and stay flexible.</span></p></div>"
},
"workLocations": [
"Remote (Germany)"
],
"department": {
"name": "Engineering",
"base_department": "Engineering",
"department_tree": [
"Engineering"
]
},
"employmentType": {
"label": "SALARIED_FT",
"id": "Full-Time Employee"
},
"createdOn": "2024-11-14T01:57:03.744000-08:00",
"eeocQuestionnaireEnabled": false,
"eeocQuestionnaireEnabledForJobPost": false,
"url": "https://ats.rippling.com/prisma-careers/jobs/0fbcec57-3012-4271-96bf-12b145cf6dea",
"board": {
"boardType": "RIPPLING",
"slug": "prisma-careers",
"banner": {
"name": "",
"url": null,
"type": ""
},
"title": "Join Prisma",
"subtitle": "At Prisma, we are building the data layer for modern apps. Join our distributed team, backed by top investors, with 380k+ users!",
"boardURL": "https://ats.rippling.com/prisma-careers/jobs",
"fontType": "ARIAL_SANS_SERIF",
"linkColor": null,
"buttonColor": "#5a67d8",
"buttonTextColor": null,
"noOpeningsMessage": null,
"groupJobsByLocation": true,
"showBoardLogoOnJobPost": false,
"showCompanyInfoUnderJobPost": false,
"companyName": "Prisma Data, Inc."
},
"payRangeDetails": [],
"applicationConfirmationTemplate": "66b4c6bc65d129d95c33c48b",
"hasAIEvaluationsEnabled": false,
"companyName": "Prisma Data, Inc.",
"unlistedFromSearch": false,
"jsonLd": null
}
+61
View File
@@ -0,0 +1,61 @@
{
"uuid": "2f2ae4c8-ec56-4d1f-8f2a-0d295674e19c",
"name": "Director of Engineering - Infrastructure",
"description": {
"company": "<meta><h2 style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;line-height:1.6;font-size:15pt;font-weight:600;letter-spacing:0.5px;margin-top:18px;margin-bottom:4px;padding-left:0px;\"><b><strong style=\"white-space:pre-wrap;\">About Rippling</strong></b></h2><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;text-align:start;\"><span style=\"font-size:11pt;white-space:pre-wrap;\">Rippling gives businesses one place to run HR, IT, and Finance. It brings together all of the workforce systems that are normally scattered across a company, like payroll, expenses, benefits, and computers. For the first time ever, you can manage and automate every part of the employee lifecycle in a single system.</span></p><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;text-align:start;\"><span style=\"font-size:11pt;white-space:pre-wrap;\">Take onboarding, for example. With Rippling, you can hire a new employee anywhere in the world and set up their payroll, corporate card, computer, benefits, and even third-party apps like Slack and Microsoft 365\u2014all within 90 seconds.</span>",
"role": "<meta><h2 style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;line-height:1.6;font-size:15pt;font-weight:600;letter-spacing:0.5px;margin-top:18px;margin-bottom:4px;padding-left:0px;\"><b><strong style=\"white-space:pre-wrap;\">About The Role</strong></b></h2><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11.25pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;\"><br></p><p style=\"font-family:&quot;Basel Grotesk&quot;,Arial,sans-serif;font-size:11pt;font-weight:400;line-height:1.6;letter-spacing:0.25px;margin:4px 0px;padding:0px;\"><span style=\"white-space:pre-wrap;\">Rippling Infrastructure operates as a scaled engineering organization responsible for the mission-critical systems that power every product and platform across the company. We support nearly 1,000 engineers globally and deliver the foundational infrastructure that enables Rippling's products to scale reliably and efficiently.</span></p></div>"
},
"workLocations": [
"San Francisco, CA",
"Seattle, WA",
"New York, NY"
],
"department": {
"name": "Platform",
"base_department": "Engineering",
"department_tree": [
"Engineering",
"Platform"
]
},
"employmentType": {
"label": "SALARIED_FT",
"id": "Salaried, full-time"
},
"createdOn": "2025-04-07T12:29:19.348000-07:00",
"eeocQuestionnaireEnabled": true,
"eeocQuestionnaireEnabledForJobPost": true,
"url": "https://ats.rippling.com/rippling/jobs/2f2ae4c8-ec56-4d1f-8f2a-0d295674e19c",
"board": {
"boardType": "CUSTOM",
"slug": "rippling",
"banner": null,
"title": "Current Openings",
"subtitle": null,
"boardURL": "http://www.rippling.com/careers/open-roles",
"fontType": null,
"linkColor": null,
"buttonColor": null,
"buttonTextColor": null,
"noOpeningsMessage": null,
"groupJobsByLocation": false,
"showBoardLogoOnJobPost": false,
"showCompanyInfoUnderJobPost": false,
"companyName": "Rippling"
},
"payRangeDetails": [
{
"location": "US Tier 1",
"currency": "USD",
"frequency": "YEAR",
"rangeStart": 216000.0,
"rangeEnd": 378000.0,
"isRemote": false
}
],
"applicationConfirmationTemplate": "6348729c5a9a6e6df0bb6f64",
"hasAIEvaluationsEnabled": true,
"companyName": "Rippling",
"unlistedFromSearch": false,
"jsonLd": null
}
+2 -2
View File
@@ -35,10 +35,10 @@ def test_the_employment_type_is_the_hosts_word() -> None:
assert (first["employment"], second["employment"]) == ("FullTime", "Contract")
def test_it_declares_a_whole_listing_of_trusted_dates_and_no_robots_check() -> None:
def test_it_declares_a_whole_listing_of_trusted_dates_and_its_robots_record() -> None:
reads = ashby.READS
assert (reads.listing, reads.text, reads.places, reads.empty) == (
"whole", "listing", "many", "suspect")
assert reads.fields.posted == "trusted" and reads.fields.pay == "figures"
assert reads.robots == "api: no robots.txt check needed (public board API), 2026-09-30"
assert reads.robots.startswith("read: ") and "(checked 2026-09-30)" in reads.robots
assert ashby.feed_url("acme", Ask()).endswith("/job-board/acme?includeCompensation=true")
-1
View File
@@ -156,7 +156,6 @@ def test_it_declares_what_it_reads() -> None:
assert (reads.listing, reads.text, reads.places, reads.fields.posted) == (
"whole", "detail", "one", "trusted")
assert reads.robots.startswith("read: robots.txt allows /careers")
assert not hasattr(bamboohr, "robots_page")
def test_the_slug_the_urls_and_the_allow_list() -> None:
-1
View File
@@ -113,7 +113,6 @@ def test_it_declares_a_whole_listing_read_from_the_page() -> None:
assert (reads.listing, reads.text, reads.places, reads.complete) == (
"whole", "listing", "many", "whole")
assert reads.fields.pay == "line" and "/api/ is disallowed and not read" in reads.robots
assert not hasattr(deel, "robots_page")
# ------------------------------------------------------- slugs and hosts
+1 -2
View File
@@ -210,5 +210,4 @@ def test_it_declares_a_paged_read_of_ten_with_a_total_and_one_country_a_request(
"paged", 10, "detail", "stated", "many")
assert reads.filters.declared() == {"country": "one", "query": "one"}
assert reads.fields.posted == "listed"
assert reads.robots.startswith("read: robots.txt allows /careers")
assert not hasattr(eightfold, "robots_page")
assert "/api/pcsx/search" in reads.robots and "/api/pcsx/position_details" in reads.robots
+1 -2
View File
@@ -103,8 +103,7 @@ def test_it_declares_one_page_that_may_be_empty_by_mistake() -> None:
reads = gem.READS
assert (reads.listing, reads.text, reads.places, reads.empty) == (
"paged", "detail", "many", "suspect")
assert reads.robots.startswith("read: robots.txt allows /<board>")
assert not hasattr(gem, "robots_page")
assert "POST /api/public/graphql" in reads.robots
@pytest.mark.parametrize(("body", "message"), [
+2 -2
View File
@@ -43,10 +43,10 @@ def test_without_offices_the_name_is_the_place() -> None:
assert nothing["places"] == [] and nothing["location"] == ""
def test_it_declares_a_whole_listing_of_trusted_dates_and_no_robots_check() -> None:
def test_it_declares_a_whole_listing_of_trusted_dates_and_its_robots_record() -> None:
reads = greenhouse.READS
assert (reads.listing, reads.text, reads.places) == ("whole", "listing", "many")
assert reads.fields.posted == "trusted" and reads.fields.pay == "figures"
assert reads.robots == "api: no robots.txt check needed (public board API), 2026-09-30"
assert reads.robots.startswith("read: ") and "(checked 2026-09-30)" in reads.robots
assert greenhouse.feed_url("acme", Ask()).endswith("/boards/acme/jobs?content=true&pay_transparency=true")
assert greenhouse.fallback_url("acme").endswith("/boards/acme/jobs")
+1 -2
View File
@@ -163,8 +163,7 @@ def test_it_declares_copies_with_a_page_and_a_robots_decision() -> None:
reads = hibob.READS
assert (reads.listing, reads.text, reads.places, reads.complete) == (
"paged", "listing", "copies", "end")
assert reads.robots.startswith("read: robots.txt allows")
assert not hasattr(hibob, "robots_page")
assert reads.robots.startswith("read: /api/job-ad")
# ------------------------------------------------------- slugs and hosts
+2 -3
View File
@@ -122,9 +122,8 @@ def test_the_feed_states_no_place_and_the_robots_decision_is_the_owners() -> Non
assert all(r["places"] == [] for r in rows)
reads = hrmanager.READS
assert (reads.listing, reads.page_size, reads.text, reads.places) == (
"paged", 100, "listing", "one")
assert reads.robots == "disallowed by robots.txt; owner to decide"
assert not hasattr(hrmanager, "robots_page")
"paged", 100, "listing", "none")
assert "api.hr-manager.net" in reads.robots and "owner, 2026-09-29" in reads.robots
# ------------------------------------------------------- slugs and hosts
-1
View File
@@ -184,4 +184,3 @@ def test_it_declares_a_paged_read_with_a_total_and_many_places() -> None:
assert (reads.listing, reads.page_size, reads.text, reads.complete, reads.places) == (
"paged", 100, "listing", "stated", "many")
assert reads.fields.country == "stated" and reads.robots.startswith("read: robots.txt")
assert not hasattr(jibe, "robots_page")
+5 -6
View File
@@ -87,8 +87,8 @@ def _get(pages: dict[str, bytes], asked: list[str] | None = None) -> Any:
def test_detail_reads_the_role_pages_json_ld() -> None:
rows = {r["source_id"]: r for r in jobylon.parse(BOARD, "3143")}
asked: list[str] = []
pages = {ROLE: (FIXTURES / "jobylon-role.html").read_bytes(),
ROLE_2: (FIXTURES / "jobylon-role-2.html").read_bytes()}
pages = {ROLE: (FIXTURES / "jobylon-detail.html").read_bytes(),
ROLE_2: (FIXTURES / "jobylon-detail-2.html").read_bytes()}
first = jobylon.detail(_get(pages, asked), "3143", rows["385191"])
assert asked == [ROLE]
assert set(first) <= set(ats.DETAIL_FIELDS) | {"places"}
@@ -116,8 +116,8 @@ def test_detail_without_a_job_posting_fails_the_read() -> None:
def test_the_board_is_one_request_and_each_role_is_read_on_its_own_page() -> None:
asked: list[str] = []
pages = {FEED: BOARD, ROLE: (FIXTURES / "jobylon-role.html").read_bytes(),
ROLE_2: (FIXTURES / "jobylon-role-2.html").read_bytes()}
pages = {FEED: BOARD, ROLE: (FIXTURES / "jobylon-detail.html").read_bytes(),
ROLE_2: (FIXTURES / "jobylon-detail-2.html").read_bytes()}
get = _get(pages, asked)
rows = jobylon.parse(get(jobylon.feed_url("3143", Ask())), "3143")
assert len(rows) == 5 and asked == [FEED]
@@ -150,8 +150,7 @@ def test_it_declares_a_whole_listing_with_a_teaser_and_detail() -> None:
assert (reads.listing, reads.text, reads.teaser, reads.places) == (
"whole", "detail", True, "many")
assert (reads.fields.posted, reads.fields.seniority) == ("trusted", "stated")
assert reads.robots.startswith("read: robots.txt allows /jobs/companies/")
assert not hasattr(jobylon, "robots_page")
assert "/jobs/companies/<id>/embed/v2/" in reads.robots
# ------------------------------------------------------- slugs and hosts
+2 -2
View File
@@ -33,9 +33,9 @@ def test_the_commitment_is_the_hosts_word() -> None:
assert several["employment"] == "Full-time" and one["employment"] == "Permanent"
def test_it_declares_a_whole_listing_of_trusted_dates_and_no_robots_check() -> None:
def test_it_declares_a_whole_listing_of_trusted_dates_and_its_robots_record() -> None:
reads = lever.READS
assert (reads.listing, reads.text, reads.places) == ("whole", "listing", "many")
assert reads.fields.posted == "trusted" and reads.fields.country == "stated"
assert reads.robots == "api: no robots.txt check needed (public board API), 2026-09-30"
assert reads.robots.startswith("read: ") and "(checked 2026-09-30)" in reads.robots
assert lever.feed_url("eu/tomtom", Ask()) == "https://api.eu.lever.co/v0/postings/tomtom?mode=json"
-1
View File
@@ -253,7 +253,6 @@ def test_the_careers_page_is_the_candidate_site() -> None:
url = f"https://{HOST}/hcmUI/CandidateExperience/en/sites/CX_1/jobs"
assert oracle.careers_url(SLUG) == ats.careers_url(f"oracle:{SLUG}") == url
assert oracle.allowed(SLUG)(httpx.URL(url).host)
assert not hasattr(oracle, "robots_page") # decided when built, see READS.robots
def test_a_slug_written_with_capitals_names_the_same_pod() -> None:
+1 -2
View File
@@ -24,8 +24,7 @@ def test_the_declaration_says_what_the_feed_gives() -> None:
reads = personio.READS
assert (reads.listing, reads.places, reads.text) == ("whole", "many", "listing")
assert reads.fields.posted == "trusted" and reads.fields.seniority == "stated"
assert reads.robots.startswith("api: no robots.txt check needed")
assert not hasattr(personio, "robots_page")
assert reads.robots.startswith("read: /xml")
assert personio.feed_url("acme", Ask()) == "https://acme.jobs.personio.de/xml"
-1
View File
@@ -289,7 +289,6 @@ def test_the_careers_page_is_the_search_page() -> None:
url = "https://careers.king.com/us/en/search-results"
assert phenom.careers_url(SLUG) == ats.careers_url(f"phenom:{SLUG}") == url
assert phenom.allowed(SLUG)(httpx.URL(url).host)
assert not hasattr(phenom, "robots_page") # decided when built, see READS.robots
assert phenom.careers_url("www.careers.philips.com/global/en") == \
"https://www.careers.philips.com/global/en/search-results"
-1
View File
@@ -116,7 +116,6 @@ def test_the_board_is_read_through_the_app_and_is_complete() -> None:
def test_the_slug_the_urls_and_the_allow_list() -> None:
assert pinpoint.slug_ok("xeneta") and pinpoint.slug_ok("Xeneta") and pinpoint.slug_ok("a-b1")
assert pinpoint.careers_url("xeneta") == "https://xeneta.pinpointhq.com/"
assert not hasattr(pinpoint, "robots_page") # decided when built, see READS.robots
assert pinpoint.feed_url("Xeneta") == "https://xeneta.pinpointhq.com/postings.json"
allow = pinpoint.allowed("Xeneta")
assert allow("xeneta.pinpointhq.com") and allow("XENETA.pinpointhq.com")
+1 -1
View File
@@ -25,7 +25,7 @@ def test_the_declaration_says_what_the_feed_gives() -> None:
reads = recruitee.READS
assert (reads.listing, reads.places, reads.text) == ("whole", "many", "listing")
assert reads.fields.posted == "trusted" and reads.fields.country == "none"
assert reads.robots.startswith("api: no robots.txt check needed")
assert "/api/offers/ is allowed" in reads.robots
assert recruitee.feed_url("acme", Ask()) == "https://acme.recruitee.com/api/offers/"
+2 -3
View File
@@ -82,7 +82,7 @@ def _get(answer: bytes, asked: list[str] | None = None) -> Any:
def test_detail_reads_description_places_date_and_a_single_yearly_range() -> None:
row = {r["source_id"]: r for r in rippling.parse(BOARD, "rippling")}[DIRECTOR]
asked: list[str] = []
found = rippling.detail(_get((FIXTURES / "rippling-role.json").read_bytes(), asked),
found = rippling.detail(_get((FIXTURES / "rippling-detail.json").read_bytes(), asked),
"rippling", row)
assert asked == [f"https://api.rippling.com/platform/api/ats/v1/board/rippling/jobs/{DIRECTOR}"]
assert found["description"].startswith("About The Role")
@@ -96,7 +96,7 @@ def test_detail_reads_description_places_date_and_a_single_yearly_range() -> Non
def test_detail_without_pay_leaves_the_pay_columns_out() -> None:
found = rippling.detail(_get((FIXTURES / "rippling-role-2.json").read_bytes()),
found = rippling.detail(_get((FIXTURES / "rippling-detail-2.json").read_bytes()),
"prisma-careers", {"source_id": "x"})
assert found["description"].startswith("What is it like to work at Prisma?")
assert found["location"] == "Remote (Germany)"
@@ -165,7 +165,6 @@ def test_the_module_is_registered_as_a_feed_host_with_detail() -> None:
def test_the_urls() -> None:
assert rippling.feed_url("rippling") == FEED
assert rippling.careers_url("prisma-careers") == "https://ats.rippling.com/prisma-careers/jobs"
assert not hasattr(rippling, "robots_page") # decided when built, see READS.robots
allow = rippling.allowed("rippling")
assert allow("api.rippling.com") and allow("ATS.RIPPLING.COM")
for host in ("rippling.com", "www.rippling.com", "api.rippling.com.evil.example", "localhost"):
+1 -1
View File
@@ -35,7 +35,7 @@ def test_the_declaration_says_what_the_list_gives() -> None:
assert (reads.listing, reads.page_size, reads.places, reads.text, reads.empty) == \
("paged", 100, "one", "detail", "suspect")
assert reads.fields.posted == "trusted" and reads.fields.seniority == "stated"
assert reads.robots.startswith("api: no robots.txt check needed")
assert reads.robots.startswith("read though") and "owner to decide" in reads.robots
def test_page_reads_by_offset_and_takes_the_ask() -> None:
-1
View File
@@ -451,7 +451,6 @@ def test_careers_url_is_the_search_page() -> None:
page = successfactors.careers_url(slug)
assert httpx.URL(page).host == slug.split("/")[0]
assert successfactors.allowed(slug)(httpx.URL(page).host)
assert not hasattr(successfactors, "robots_page") # decided when built, see READS.robots
def test_the_module_is_case_sensitive_about_the_prefix() -> None:
+1 -2
View File
@@ -24,8 +24,7 @@ def test_the_declaration_says_what_the_feed_gives() -> None:
assert (reads.listing, reads.page_size, reads.places, reads.text, reads.complete) == \
("paged", 50, "many", "listing", "end")
assert reads.fields.posted == "trusted" and reads.fields.remote == "stated"
assert reads.robots.startswith("api: no robots.txt check needed")
assert not hasattr(teamtailor, "robots_page")
assert "/jobs.rss is allowed" in reads.robots
def test_page_takes_the_ask_and_reads_the_same_url() -> None:
+1 -1
View File
@@ -30,7 +30,7 @@ def test_the_declaration_says_what_the_list_gives() -> None:
assert (reads.listing, reads.page_size, reads.places, reads.text) == \
("paged", 10, "many", "detail")
assert reads.fields.posted == "trusted" and reads.fields.employment == "stated"
assert reads.robots.startswith("api: no robots.txt check needed")
assert "/api/v3/accounts/<slug>/jobs" in reads.robots
def test_page_takes_the_ask_and_posts_the_same_body() -> None:
+4 -4
View File
@@ -446,10 +446,10 @@ def test_the_case_of_the_site_is_kept() -> None:
assert "workday" in ats.HOSTS and ats.HOSTS["workday"] == "Workday"
def test_the_runtime_robots_check_has_left_the_module() -> None:
"""Decided when the reader was built (`READS.robots`): nothing to ask now."""
assert not hasattr(workday, "robots_page") and not hasattr(workday, "ROBOTS_ANY_CASE")
assert "robots.txt allows /<Site>/" in workday.READS.robots
def test_the_robots_record_names_the_api_path() -> None:
"""Decided when the reader was built (`READS.robots`), for the paths it
requests, not only the career site's."""
assert "/wday/cxs/<tenant>/<site>/" in workday.READS.robots
# -------------------------------------------------------------- discovery