Decode HTML entities in freehire titles and companies, and separate the region ids in the searches help

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-10-03 12:28:19 +02:00
1 parent a9c387c130
commit 10dec33dce
3 files changed
+12 -4

No files matched your search

+3 -2
View File
@@ -27,6 +27,7 @@ table of the host's words in `app/prep/hosts/freehire.py`.
from __future__ import annotations
import html
import json
import re
from collections.abc import Callable
@@ -166,7 +167,7 @@ def _pay(enrichment: dict[str, Any]) -> dict[str, Any]:
def rows(decoded: Any, slug: str) -> list[Row]:
out: list[Row] = []
for hit in decoded.get("data") or []:
title = " ".join(str(hit.get("title") or "").split())
title = " ".join(html.unescape(str(hit.get("title") or "")).split())
source_id = str(hit.get("public_slug") or "").strip()
url = _url(str(hit.get("url") or ""))
if not title or not source_id or not is_web_url(url):
@@ -177,7 +178,7 @@ def rows(decoded: Any, slug: str) -> list[Row]:
out.append({
"source_id": source_id,
"title": title,
"company": str(hit.get("company") or "").strip(),
"company": html.unescape(str(hit.get("company") or "")).strip(),
"url": url,
"places": places,
"location": places[0]["text"] if places else "",