Merge the Jobindex link-out: the Se jobbet link kept as posting_url (wp-d-jobindex)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 13:45:27 +02:00
commit 27e24d0342
19 files changed
+695 -29

No files matched your search

+24 -1
View File
@@ -15,6 +15,13 @@ the paragraphs are an excerpt of the ad, handed over as `teaser`. A crawled ad
("robot job") has no logo, so its company is what follows the title's last
comma, or '' when there is none. An answer with no `<channel>` is not a search
result and raises, since an empty list would read as a search that ran out.
The `<link>` opens Jobindex's `vis-job` page, and `posting_link` reads the
"Se jobbet" button on it: the employer's site, The Hub or Jobindex's own
`jobannonce`, checked on 2026-09-30. It is not part of the search: fetching
that page counts as a click in Jobindex's statistics, so `app.jobs.posting`
does it only for a role somebody opened. The page's "other ads" cards carry
the same words on `/c?t=` redirects, which are not this ad and are skipped.
"""
from __future__ import annotations
@@ -24,7 +31,7 @@ import re
import xml.etree.ElementTree as ET
from collections.abc import Callable
from typing import Any
from urllib.parse import urlencode
from urllib.parse import urlencode, urljoin, urlsplit
from desk.sources import strip_html
@@ -62,6 +69,8 @@ _AREA = re.compile(r'class="jix_robotjob--area">(.*?)</span>', re.IGNORECASE | r
_PARAGRAPHS = re.compile(r"<p>(.*?)</p>", re.IGNORECASE | re.DOTALL)
#: "Ledige job i Region Hovedstaden indeholdende ..." -> "Region Hovedstaden".
_SEARCH_AREA = re.compile(r"Ledige job i (.+?) indeholdende")
_SE_JOBBET = re.compile(r"<a\b([^>]*)>\s*Se jobbet\s*</a>", re.IGNORECASE)
_HREF = re.compile(r'\bhref\s*=\s*"([^"]*)"', re.IGNORECASE)
def allowed(slug: str) -> Callable[[str], bool]:
@@ -77,6 +86,20 @@ def clean_params(params: dict[str, Any]) -> dict[str, Any]:
return out
def posting_link(page_html: str) -> str:
"""The "Se jobbet" link of a `vis-job` page: where the ad itself is, as an
absolute URL, or '' when the page has none. A `/c?t=` link is another ad's
redirect and is skipped."""
for tag in _SE_JOBBET.finditer(page_html):
found = _HREF.search(tag.group(1))
if not found:
continue
url = urljoin("https://www.jobindex.dk/", html.unescape(found.group(1)).strip())
if is_web_url(url) and urlsplit(url).path != "/c":
return url
return ""
def _text(fragment: str) -> str:
"""HTML to plain text. Jobindex breaks titles after a slash with a
zero-width space, which would otherwise end up in `title_key`."""