Let the runner drop and count a row without an id, a title or a link, as ADR Plugins 3.8 has it, in one place for whole, paged and search reads: the count is stamped per target, logged, named on the board's row, and over 10% of the rows fails the read; the 28 readers hand every listing over instead of skipping it
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
38c31c830b
commit
911dfe8584
58 files changed
+479
-203
No files matched your search
@@ -63,7 +63,7 @@ from desk.sources import strip_html
|
||||
|
||||
from ._contract import Ask, Fields, Filters, Place, Reads
|
||||
from ._countries import NAMES
|
||||
from ._shared import Get, Page, Row, add_place, html_text, is_web_url, only, parse_dt
|
||||
from ._shared import Get, Page, Row, add_place, html_text, only, parse_dt
|
||||
|
||||
NAME = "successfactors"
|
||||
LABEL = "SuccessFactors"
|
||||
@@ -247,8 +247,9 @@ def _tile_fields(chunk: str) -> tuple[str, str, str]:
|
||||
def _entries(text: str) -> list[dict[str, Any]]:
|
||||
"""The roles of one search page, in the order shown, whichever layout it is
|
||||
in and before the prefix filter: `id`, `href` (as written, relative),
|
||||
`title`, `place`, `date` and `department`. A role is listed once, and a row
|
||||
without a link to a role is not one."""
|
||||
`title`, `place`, `date` and `department`. A role is listed once. The id
|
||||
and the title are in the role's link, so a row without one is handed over
|
||||
with an empty `id`, `href` and `title`, for the runner to drop and count."""
|
||||
table = _ROW.split(text)[1:]
|
||||
chunks = table or _TILE.split(text)[1:]
|
||||
out: list[dict[str, Any]] = []
|
||||
@@ -256,10 +257,12 @@ def _entries(text: str) -> list[dict[str, Any]]:
|
||||
for chunk in chunks:
|
||||
if table:
|
||||
chunk = chunk.split("</tr>", 1)[0]
|
||||
if not (link := _LINK.search(chunk)):
|
||||
continue
|
||||
href, job_id, title = html.unescape(link.group(1)), link.group(2), _text(link.group(3))
|
||||
if job_id in seen:
|
||||
if link := _LINK.search(chunk):
|
||||
href, job_id, title = (html.unescape(link.group(1)), link.group(2),
|
||||
_text(link.group(3)))
|
||||
else:
|
||||
href = job_id = title = ""
|
||||
if job_id and job_id in seen:
|
||||
continue
|
||||
seen.add(job_id)
|
||||
place, date, department = (_table_fields if table else _tile_fields)(chunk)
|
||||
@@ -283,12 +286,14 @@ def page(get: Get, slug: str, cursor: Any, ask: Ask = Ask()) -> Page:
|
||||
if not _SEARCH_PAGE.search(text):
|
||||
raise ValueError("not a SuccessFactors search page")
|
||||
found = _entries(text)
|
||||
ids = [entry["id"] for entry in found if entry["id"]]
|
||||
total = _total(text)
|
||||
if found and found[0]["id"] == previous:
|
||||
first = ids[0] if ids else None
|
||||
if first is not None and first == previous:
|
||||
return text, [], total, (start, previous)
|
||||
more = bool(found) and (total is None or start + len(found) < total)
|
||||
return (text, [{"id": entry["id"]} for entry in found], total,
|
||||
(start + len(found), found[0]["id"]) if more else None)
|
||||
return (text, [{"id": job_id} for job_id in ids], total,
|
||||
(start + len(found), first) if more else None)
|
||||
|
||||
|
||||
def rows(decoded: str, slug: str) -> list[Row]:
|
||||
@@ -296,17 +301,21 @@ def rows(decoded: str, slug: str) -> list[Row]:
|
||||
slug's prefix when it has one; the id in it is the requisition's `source_id`.
|
||||
The table and the tile layout give a title, a location, a date and, where
|
||||
the site has the column, a department; nothing else about a role is on
|
||||
the list, so its description and pay are empty."""
|
||||
the list, so its description and pay are empty.
|
||||
|
||||
A role linked on another host, or outside the prefix, is another board's
|
||||
(another site, or another brand of a shared site), and is left out: it is
|
||||
no role of this company. A row with no link or no title is handed over,
|
||||
and the runner drops it."""
|
||||
host, prefix = _parts(slug)
|
||||
base = f"https://{host}/"
|
||||
out = []
|
||||
for entry in _entries(decoded):
|
||||
url = urljoin(base, entry["href"])
|
||||
if urlsplit(url).hostname != host or not is_web_url(url):
|
||||
url = urljoin(base, entry["href"]) if entry["href"] else ""
|
||||
if url and urlsplit(url).hostname != host:
|
||||
continue
|
||||
if prefix and not urlsplit(url).path.lower().startswith(f"{prefix.lower()}/job/"):
|
||||
continue
|
||||
if not entry["title"]:
|
||||
if url and prefix and not urlsplit(url).path.lower().startswith(
|
||||
f"{prefix.lower()}/job/"):
|
||||
continue
|
||||
out.append({
|
||||
"source_id": entry["id"],
|
||||
|
||||
Reference in new issue
Block a user