feat(scrapers): add Himalayas remote jobs API scraper

scripts/capture_gui_shots.py

@@ -17,7 +17,7 @@
 
 
 def main() -> None:
-    from PySide6.QtCore import QTimer, Qt
+    from PySide6.QtCore import QTimer
     from PySide6.QtGui import QFont, QGuiApplication
     from PySide6.QtWidgets import QApplication
 

src/nerajob/cli.py

@@ -1,26 +1,31 @@
 from __future__ import annotations
+
 from pathlib import Path
 
 import typer
 from rich.console import Console
 from rich.table import Table
 
 from nerajob import __version__
-from nerajob.match import SKILL_ALIASES, extract_skills_from_text
 from nerajob.apply.assistant import prepare_application
 from nerajob.cv.builder import write_cv_files
-from nerajob.match import DEFAULT_MATCH_WEIGHTS, MatchWeights
-from nerajob.models import JobPosting
+from nerajob.match import (
+    DEFAULT_MATCH_WEIGHTS,
+    SKILL_ALIASES,
+    MatchWeights,
+    extract_skills_from_text,
+)
+from nerajob.models import ApplicationPackage, JobPosting
 from nerajob.scrapers.registry import available_scrapers, get_scraper
-from nerajob.models import ApplicationPackage
 from nerajob.storage import (
     default_profile,
     get_job,
     load_applications,
     load_jobs,
     load_profile,
-    load_scan_preset, save_scan_preset,
+    load_scan_preset,
     save_profile,
+    save_scan_preset,
     upsert_jobs,
 )
 
@@ -411,7 +416,7 @@ def jobs_match(
 ) -> None:
     """Rank saved jobs against your profile (keyword skill match)."""
     from nerajob.match import match_score, rank_jobs
-    from nerajob.models import Profile, JobPosting
+    from nerajob.models import JobPosting, Profile
     from nerajob.storage import load_jobs, load_profile
 
     profile = None

src/nerajob/cv/builder.py

@@ -132,7 +132,7 @@ def write_cv_pdf(profile: Profile, target_role: str = "") -> Path | None:
                 if line.startswith("# "):
                     pdf.set_font("Helvetica", "B", 16)
                     pdf.cell(0, 10, line[2:], new_x="LMARGIN", new_y="NEXT")
-                elif line.startswith("## ") or line.startswith("### "):
+                elif line.startswith(("## ", "### ")):
                     pdf.set_font("Helvetica", "B", 14)
                     label = line[line.index(" ") + 1 :]
                     pdf.cell(0, 10, label, new_x="LMARGIN", new_y="NEXT")

src/nerajob/gui/app.py

@@ -11,10 +11,10 @@ def main(argv: list[str] | None = None) -> int:
     except ImportError:
         print("Install GUI extras: pip install -e \".[gui]\"  (needs PySide6)", file=sys.stderr)
         return 1
-    from nerajob.gui.main_window import MainWindow
-
     from PySide6.QtGui import QFont
 
+    from nerajob.gui.main_window import MainWindow
+
     app = QApplication(sys.argv if argv is None else argv)
     app.setApplicationName("NeraJob")
     app.setOrganizationName("MergeOS")

src/nerajob/gui/main_window.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from PySide6.QtCore import Qt, QSize
+from PySide6.QtCore import QSize, Qt
 from PySide6.QtGui import QFont
 from PySide6.QtWidgets import (
     QAbstractItemView,

src/nerajob/match.py

@@ -34,7 +34,7 @@ def as_dict(self) -> dict[str, float]:
 SKILL_ALIASES: dict[str, set[str]] = {
     "python": {"python", "django", "fastapi", "flask"},
     "javascript": {"javascript", "js", "typescript", "node", "react"},
-    "devops": {"devops", "docker", "kubernetes", "k8s", "ci/cd", "terraform", "helm", "ansible", "puppet", "chef", "prometheus", "grafana", "sre", "docker swarm", "nomad", "consul", "vault", "istio", "service mesh", "infrastructure as code", "iac", "site reliability", "argocd", "jenkins", "github actions", "gitlab ci", "vault", "consul", "nomad"},
+    "devops": {"devops", "docker", "kubernetes", "k8s", "ci/cd", "terraform", "helm", "ansible", "puppet", "chef", "prometheus", "grafana", "sre", "docker swarm", "nomad", "consul", "vault", "istio", "service mesh", "infrastructure as code", "iac", "site reliability", "argocd", "jenkins", "github actions", "gitlab ci"},
     "security_ops": {"secops", "soc analyst", "incident response", "threat hunting", "siem", "edr", "blue team", "detection"},
     "platform_eng": {"platform engineer", "platform engineering", "internal developer platform", "idp", "developer experience", "devex", "paved path", "golden path"},
     "sales_eng": {"solutions engineer", "sales engineer", "pre-sales", "demo", "poc", "technical account", "se ", "rfp"},

src/nerajob/models.py

@@ -1,13 +1,13 @@
 from __future__ import annotations
 
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any, ClassVar
 
 from pydantic import BaseModel, Field, field_validator
 
 
 def utc_now_iso() -> str:
-    return datetime.now(timezone.utc).replace(microsecond=0).isoformat()
+    return datetime.now(UTC).replace(microsecond=0).isoformat()
 
 
 class Experience(BaseModel):

src/nerajob/scrapers/ashby.py

@@ -4,12 +4,12 @@
 
 import hashlib
 import json
-from urllib.request import Request, urlopen
 from urllib.error import HTTPError, URLError
+from urllib.request import Request, urlopen
 
+from nerajob.config import http_timeout, user_agent
 from nerajob.models import JobPosting
 from nerajob.scrapers.base import BaseScraper
-from nerajob.config import http_timeout, user_agent
 
 
 class AshbyScraper(BaseScraper):

src/nerajob/scrapers/greenhouse.py

@@ -127,9 +127,7 @@ def _matches_query(self, job: JobResult, query: str, location: str) -> bool:
         q = query.strip().strip("*")
         if q and q.lower() not in job.title.lower() and q.lower() not in job.description.lower():
             return False
-        if location and location.lower() not in job.location.lower():
-            return False
-        return True
+        return not (location and location.lower() not in job.location.lower())
 
     # ------------------------------------------------------------------
     # Offline fallback

src/nerajob/scrapers/himalayas.py

@@ -0,0 +1,153 @@
+"""Himalayas remote jobs public API adapter with offline fallback."""
+
+from __future__ import annotations
+
+import hashlib
+import os
+import urllib.parse
+
+import httpx
+
+from nerajob.config import http_timeout, user_agent
+from nerajob.models import JobPosting
+from nerajob.scrapers.base import BaseScraper
+
+_OFFLINE = [
+    (
+        "Social Media and Creative Manager",
+        "Tala",
+        "Mexico",
+        ["brand", "marketing", "social-media"],
+        "https://himalayas.app/companies/tala/jobs/social-media-and-creative-manager",
+    ),
+    (
+        "Systems Migration & Support Specialist",
+        "Asset Living",
+        "United States",
+        ["it", "support", "systems"],
+        "https://himalayas.app/companies/asset-living/jobs/systems-migration-support-specialist",
+    ),
+    (
+        "Mobile Automation Engineer",
+        "CXT Software",
+        "Argentina",
+        ["qa", "automation", "playwright"],
+        "https://himalayas.app/companies/cxt-software/jobs/mobile-automation-engineer",
+    ),
+]
+
+
+class HimalayasScraper(BaseScraper):
+    """
+    Himalayas remote jobs API.
+
+    Docs: https://himalayas.app/jobs/api
+    Endpoints:
+      - Unfiltered: https://himalayas.app/jobs/api?offset=0&limit=20
+      - Search: https://himalayas.app/jobs/api/search?q=query
+    """
+
+    name = "himalayas"
+    API_URL = "https://himalayas.app/jobs/api"
+    SEARCH_URL = "https://himalayas.app/jobs/api/search"
+
+    def search(self, query: str, location: str = "", limit: int = 20) -> list[JobPosting]:
+        if os.getenv("NERAJOB_HIMALAYAS_OFFLINE", "").strip().lower() in {"1", "true", "yes"}:
+            return self._offline(query, limit)
+
+        headers = {
+            "User-Agent": user_agent(),
+            "Accept": "application/json",
+        }
+
+        q = query.strip()
+        loc = location.strip().lower()
+
+        # Build URL
+        if q:
+            url = f"{self.SEARCH_URL}?q={urllib.parse.quote(q)}"
+        else:
+            url = f"{self.API_URL}?limit={limit}"
+
+        try:
+            with httpx.Client(timeout=http_timeout(), headers=headers, follow_redirects=True) as client:
+                response = client.get(url)
+                response.raise_for_status()
+                payload = response.json()
+        except Exception:
+            return self._offline(query, limit)
+
+        jobs_raw = payload.get("jobs") if isinstance(payload, dict) else None
+        if not isinstance(jobs_raw, list):
+            return self._offline(query, limit)
+
+        jobs: list[JobPosting] = []
+        for item in jobs_raw:
+            if not isinstance(item, dict):
+                continue
+            title = str(item.get("title") or "").strip()
+            company = str(item.get("companyName") or "").strip()
+            if not title:
+                continue
+
+            tags = [str(t).lower() for t in (item.get("categories") or []) if t]
+
+            loc_restrictions = item.get("locationRestrictions") or []
+            place = ", ".join(loc_restrictions) if isinstance(loc_restrictions, list) else str(loc_restrictions)
+            if not place:
+                place = "Remote"
+
+            hay = f"{title} {company} {place} {' '.join(tags)} {item.get('description', '')} {item.get('excerpt', '')}".lower()
+            if q.lower() and q.lower() not in hay:
+                continue
+            if loc and loc not in place.lower() and "remote" not in place.lower():
+                continue
+
+            url = str(item.get("applicationLink") or item.get("guid") or "")
+            raw_id = str(item.get("guid") or title)
+            digest = hashlib.sha1(f"{self.name}:{raw_id}".encode()).hexdigest()[:12]
+
+            jobs.append(
+                JobPosting(
+                    id=f"himalayas-{digest}",
+                    source=self.name,
+                    title=title,
+                    company=company or "Unknown",
+                    location=place,
+                    url=url,
+                    description=str(item.get("description") or item.get("excerpt") or "")[:4000],
+                    tags=tags[:20],
+                    remote=True,
+                    raw={"guid": raw_id},
+                )
+            )
+            if len(jobs) >= limit:
+                break
+
+        return jobs if jobs else self._offline(query, limit)
+
+    def _offline(self, query: str, limit: int) -> list[JobPosting]:
+        q = query.strip().lower()
+        out: list[JobPosting] = []
+        for title, company, place, tags, url in _OFFLINE:
+            hay = f"{title} {company} {' '.join(tags)}".lower()
+            if q and q not in hay:
+                continue
+            digest = hashlib.sha1(f"{self.name}:{title}:{company}".encode()).hexdigest()[:12]
+            out.append(
+                JobPosting(
+                    id=f"himalayas-{digest}",
+                    source=self.name,
+                    title=title,
+                    company=company,
+                    location=place,
+                    url=url,
+                    description=f"{title} at {company} (offline Himalayas sample).",
+                    tags=tags,
+                    remote=True,
+                    raw={"offline": True},
+                )
+            )
+            if len(out) >= limit:
+                break
+        return out

src/nerajob/scrapers/lever.py

@@ -4,12 +4,12 @@
 
 import hashlib
 import json
-from urllib.request import Request, urlopen
 from urllib.error import HTTPError, URLError
+from urllib.request import Request, urlopen
 
+from nerajob.config import http_timeout, user_agent
 from nerajob.models import JobPosting
 from nerajob.scrapers.base import BaseScraper
-from nerajob.config import http_timeout, user_agent
 
 
 class LeverScraper(BaseScraper):

src/nerajob/scrapers/registry.py

@@ -7,6 +7,7 @@
 from nerajob.scrapers.ashby import AshbyScraper
 from nerajob.scrapers.base import BaseScraper
 from nerajob.scrapers.findwork import FindworkScraper
+from nerajob.scrapers.himalayas import HimalayasScraper
 from nerajob.scrapers.jobicy import JobicyScraper
 from nerajob.scrapers.jooble import JoobleScraper
 from nerajob.scrapers.lever import LeverScraper
@@ -53,6 +54,7 @@ def available_scrapers() -> dict[str, BaseScraper]:
         SmartRecruitersScraper(),
         FindworkScraper(),
         AdzunaScraper(),
+        HimalayasScraper(),
     ]
     return {s.name: s for s in scrapers}
 

src/nerajob/storage.py

@@ -1,11 +1,19 @@
 from __future__ import annotations
 
 import json
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable
 
 from nerajob.config import APPLICATIONS_DIR, JOBS_PATH, PROFILE_PATH, SCAN_PRESET_PATH
-from nerajob.models import ApplicationPackage, Education, Experience, JobPosting, Profile, ScanPreset, utc_now_iso
+from nerajob.models import (
+    ApplicationPackage,
+    Education,
+    Experience,
+    JobPosting,
+    Profile,
+    ScanPreset,
+    utc_now_iso,
+)
 
 
 def _read_json(path: Path, default):

tests/test_application_tracker.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 import pytest
 from pydantic import ValidationError
@@ -7,7 +7,7 @@
 
 
 def utc_now_iso() -> str:
-    return datetime.now(timezone.utc).replace(microsecond=0).isoformat()
+    return datetime.now(UTC).replace(microsecond=0).isoformat()
 
 
 class TestModelValidation:

tests/test_fixture_packs.py

@@ -20,7 +20,7 @@ def test_frontend_fixture_pack():
     assert "Vue.js Developer" in titles
     for j in jobs:
         assert j.remote
-        assert j.source == "sample" or True  # no source validation
+        assert True  # no source validation
 
 
 def test_devops_fixture_pack():