From 9645dbca8d78d379b3e45d5acdbd14f3e8f40e70 Mon Sep 17 00:00:00 2001
From: Dennis Thiessen <dennis@thiessen.io>
Date: Fri, 10 Jul 2026 23:19:22 +0200
Subject: [PATCH] Add PostFinance to job scout

---
 job_scout/scout.py | 37 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/job_scout/scout.py b/job_scout/scout.py
index 7d075ff..4f453a3 100644
--- a/job_scout/scout.py
+++ b/job_scout/scout.py
@@ -313,6 +313,21 @@ COMPANIES = [
     # (IT/data + energy-trading, incl. the flagged Energiehandel roles). German/generic
     # titles, so _score_floor keeps the pre-filtered set visible.
     ("bkw",       "BKW (Bern)", "bkw", {"_score_floor": 2}),
+    # PostFinance (Bern). The careers site renders a small, client-side paginated board;
+    # scrape all pages through its stable next-page control. No title filter: the board is
+    # low-volume, and the scorer keeps unrelated banking/customer-service roles out of the
+    # default report while retaining locally relevant engineering variants.
+    ("postfinance", "PostFinance (Bern)", "playwright", {
+        "url": "https://jobs.postfinance.ch/PostFinance/search?locale=de_DE",
+        "wait_for": "a[href*='/PostFinance/job/']",
+        "card": "a[href*='/PostFinance/job/']",
+        "title_attr": "text",
+        "link_attr": "href",
+        "default_location": "Switzerland",
+        "use_inner_text_as_blob": True,
+        "next_button": "#pfch-pagination-next",
+        "max_pages": 10,
+    }),
 ]
 
 # Companies where adapter probing did not yield a reliable scrape. Reasons noted.
@@ -922,7 +937,27 @@ def fetch_playwright(args):
                 if p > 0 and added == 0:
                     break
         else:
-            scrape_current()
+            # Optional in-page pagination for client-side job boards. This is distinct from
+            # query-param pagination above: the URL does not change when moving between pages.
+            next_button = args.get("next_button")
+            if next_button:
+                for _ in range(args.get("max_pages", 8)):
+                    added = scrape_current()
+                    button = page.locator(next_button)
+                    if button.count() != 1:
+                        break
+                    try:
+                        if not button.is_visible() or button.is_disabled():
+                            break
+                        button.click()
+                        page.wait_for_timeout(args.get("next_wait_ms", 800))
+                    except Exception:
+                        break
+                    # A page with no unseen cards signals a loop or exhausted pagination.
+                    if added == 0:
+                        break
+            else:
+                scrape_current()
     finally:
         ctx.close()