Refine and add more companies

config.yaml

@@ -67,10 +67,6 @@ companies:
     platform: greenhouse
     board_token: tailscale
 
-  - name: HashiCorp
-    platform: greenhouse
-    board_token: hashicorp
-
   # Developer Tools & Platforms
   - name: Automattic
     platform: greenhouse
@@ -88,6 +84,71 @@ companies:
     platform: greenhouse
     board_token: cloudflare
 
+  - name: Fastly
+    platform: greenhouse
+    board_token: fastly
+
+  # Database & Data Infrastructure
+  - name: Materialize
+    platform: greenhouse
+    board_token: materialize
+
+  - name: PingCAP
+    platform: greenhouse
+    board_token: pingcap
+
+  - name: CockroachLabs
+    platform: greenhouse
+    board_token: cockroachlabs
+
+  - name: TigerData
+    platform: ashby
+    ashby_company: tigerdata
+
+  # Observability & Monitoring
+  - name: Honeycomb
+    platform: greenhouse
+    board_token: honeycomb
+
+  - name: Datadog
+    platform: greenhouse
+    board_token: datadog
+
+  - name: Sentry
+    platform: ashby
+    ashby_company: sentry
+
+  # Cloud & Developer Platforms
+  - name: Render
+    platform: ashby
+    ashby_company: render
+
+  - name: Railway
+    platform: ashby
+    ashby_company: Railway
+
+  - name: Stripe
+    platform: greenhouse
+    board_token: stripe
+
+  - name: JetBrains
+    platform: greenhouse
+    board_token: jetbrains
+
+  # Rust-heavy / Visualization
+  - name: Rerun
+    platform: ashby
+    ashby_company: rerun
+
+  # Big Tech (Selective)
+  - name: Discord
+    platform: greenhouse
+    board_token: discord
+
+  - name: Dropbox
+    platform: greenhouse
+    board_token: dropbox
+
 # Notification settings (optional - configure as needed)
 notifications:
   # Console output is always enabled

dashboard.py

@@ -3,24 +3,149 @@
 Generate a simple text-based HTML dashboard of all tracked jobs.
 """
 
+import re
 from datetime import datetime
 from pathlib import Path
 
 from db import Database
 
 
+# Regions/locations we care about (case-insensitive matching)
+DESIRED_REGIONS = [
+    "canada", "toronto", "vancouver",
+    "germany", "berlin", "munich",
+    "emea",
+    "americas",  # includes North/South America
+    "north america",
+    "worldwide", "global", "anywhere",
+]
+
+# Locations to explicitly exclude (on-site or remote restricted to these)
+EXCLUDED_LOCATIONS = [
+    # US cities/states (we don't want US-only jobs)
+    "san francisco", "new york", "nyc", "seattle", "austin", "boston",
+    "chicago", "denver", "los angeles", "atlanta", "dallas", "houston",
+    "california", "washington", "texas", "massachusetts", "colorado",
+    "united states", "usa", "u.s.", "us-", "usa-",
+    # UK
+    "london", "united kingdom", "uk", "dublin", "ireland",
+    # Australia/APAC (not EMEA)
+    "sydney", "melbourne", "australia", "singapore", "tokyo", "japan",
+    "india", "bangalore", "bengaluru", "hyderabad", "delhi",
+    "korea", "seoul", "taiwan", "taipei", "china", "beijing", "shenzhen",
+    # Other excluded
+    "israel", "tel aviv", "brazil", "sao paulo", "mexico",
+    "netherlands", "amsterdam", "france", "paris", "spain", "madrid",
+    "portugal", "lisbon", "poland", "warsaw", "italy",
+    "czech", "prague", "serbia", "belgrade", "cyprus", "limassol",
+    "austria", "vienna", "sweden", "stockholm", "denmark", "copenhagen",
+    "switzerland", "romania", "bucharest", "hungary", "greece",
+    "south africa", "indonesia", "jakarta", "malaysia",
+]
+
+
+def is_location_relevant(location: str, remote_type: str) -> bool:
+    """
+    Strict location filter. Only keeps jobs available in Canada, Germany, EMEA, or Worldwide.
+    Filters out US-only jobs, UK jobs, APAC jobs, etc.
+    """
+    if not location:
+        return False  # No location info = probably US-based, filter out
+
+    loc_lower = location.lower()
+
+    # Check if any desired region is mentioned FIRST
+    has_desired = any(region in loc_lower for region in DESIRED_REGIONS)
+
+    # If it has a desired region, keep it (even if it also mentions excluded locations)
+    # e.g., "Remote (United States | Canada)" should be kept because of Canada
+    if has_desired:
+        return True
+
+    # If it just says "Remote" with nothing else, keep it (truly remote)
+    if loc_lower.strip() == "remote":
+        return True
+
+    # Check for excluded locations
+    has_excluded = any(excl in loc_lower for excl in EXCLUDED_LOCATIONS)
+    if has_excluded:
+        return False
+
+    # Check for patterns like "In-Office", "Hybrid", "On-site" without desired region
+    if any(x in loc_lower for x in ["in-office", "hybrid", "on-site", "onsite", "office based"]):
+        return False
+
+    # If we can't determine, filter it out (safer)
+    return False
+
+
+def extract_location_tags(location: str, remote_type: str) -> tuple[list[str], str]:
+    """
+    Extract relevant location tags and a short display location.
+    Returns (list of tag names, short location string)
+    """
+    if not location:
+        return [], ""
+
+    loc_lower = location.lower()
+    tags = []
+    short_loc = ""
+
+    # Check for remote
+    is_remote = remote_type == "remote" or "remote" in loc_lower
+    if is_remote:
+        tags.append("remote")
+
+    # Check for Canada
+    if any(x in loc_lower for x in ["canada", "toronto", "vancouver"]):
+        tags.append("canada")
+        short_loc = "Canada"
+
+    # Check for Germany/Berlin
+    if any(x in loc_lower for x in ["germany", "berlin", "munich"]):
+        tags.append("germany")
+        short_loc = "Germany" if "germany" in loc_lower else "Berlin"
+
+    # Check for EMEA
+    if "emea" in loc_lower:
+        tags.append("emea")
+        short_loc = "EMEA"
+
+    # Check for Americas/North America
+    if "americas" in loc_lower or "north america" in loc_lower:
+        tags.append("americas")
+        short_loc = "Americas"
+
+    # Check for Worldwide
+    if any(x in loc_lower for x in ["worldwide", "global", "anywhere"]):
+        tags.append("worldwide")
+        short_loc = "Worldwide"
+
+    # If no specific region found but it's remote
+    if not short_loc and is_remote:
+        short_loc = "Remote"
+
+    return tags, short_loc
+
+
 def generate_dashboard(output_path: str = "data/dashboard.html"):
     """Generate a static HTML dashboard."""
     db = Database()
     jobs = db.get_all_active_jobs()
 
-    # Group by company
+    # Group by company, filtering out irrelevant remote locations
     companies = {}
+    filtered_count = 0
     for company_name, job in jobs:
+        if not is_location_relevant(job.location, job.remote_type):
+            filtered_count += 1
+            continue
         if company_name not in companies:
             companies[company_name] = []
         companies[company_name].append(job)
 
+    total_shown = sum(len(jobs) for jobs in companies.values())
+
     # Sort companies by name
     sorted_companies = sorted(companies.items())
 
@@ -116,14 +241,14 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
             font-size: 12px;
         }}
         .jobs {{
-            margin-left: 20px;
+            margin-left: 0;
         }}
         .job {{
             padding: 6px 0;
             border-bottom: 1px solid var(--border);
-            display: grid;
+            display: flex;
-            grid-template-columns: 1fr 180px;
+            justify-content: space-between;
-            gap: 10px;
+            gap: 20px;
             align-items: baseline;
         }}
         .job:last-child {{
@@ -148,6 +273,8 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
             color: var(--muted);
             font-size: 12px;
             text-align: right;
+            white-space: nowrap;
+            flex-shrink: 0;
         }}
         .tag {{
             display: inline-block;
@@ -168,6 +295,18 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
             background: #4a4a1a;
             color: #facc15;
         }}
+        .tag-emea {{
+            background: #1a3a4a;
+            color: #60a5fa;
+        }}
+        .tag-americas {{
+            background: #3a1a4a;
+            color: #c084fc;
+        }}
+        .tag-worldwide {{
+            background: #1a4a3a;
+            color: #34d399;
+        }}
         .hidden {{
             display: none;
         }}
@@ -228,7 +367,7 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
         <h1>$ job-board</h1>
         <div class="meta">
             Last updated: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")} |
-            {len(jobs)} jobs across {len(companies)} companies
+            {total_shown} jobs across {len(companies)} companies
         </div>
     </header>
 
@@ -244,11 +383,14 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
             <button class="filter-btn" data-filter="design">Design</button>
             <button class="filter-btn" data-filter="security">Security</button>
             <button class="filter-btn" data-filter="remote">Remote</button>
-            <button class="filter-btn" data-filter="canada toronto vancouver">Canada</button>
+            <button class="filter-btn" data-filter="canada">Canada</button>
-            <button class="filter-btn" data-filter="berlin germany">Berlin</button>
+            <button class="filter-btn" data-filter="germany">Germany</button>
+            <button class="filter-btn" data-filter="emea">EMEA</button>
+            <button class="filter-btn" data-filter="americas">Americas</button>
+            <button class="filter-btn" data-filter="worldwide">Worldwide</button>
         </div>
         <div class="stats">
-            <span id="visible-count">{len(jobs)} jobs shown</span>
+            <span id="visible-count">{total_shown} jobs shown</span>
         </div>
     </div>
 
@@ -283,18 +425,27 @@ def generate_dashboard(output_path: str = "data/dashboard.html"):
             location = job.location or ""
             location_lower = location.lower()
 
-            # Tags
+            # Extract tags and short location
-            tags = ""
+            tag_list, short_loc = extract_location_tags(location, job.remote_type)
-            if job.remote_type == "remote" or "remote" in location_lower:
-                tags += '<span class="tag tag-remote">remote</span>'
-            if "canada" in location_lower or "toronto" in location_lower or "vancouver" in location_lower:
-                tags += '<span class="tag tag-canada">canada</span>'
-            if "berlin" in location_lower or "germany" in location_lower:
-                tags += '<span class="tag tag-berlin">berlin</span>'
 
-            html += f"""                <div class="job" data-search="{job.title.lower()} {location_lower} {(job.department or '').lower()}">
+            # Build tag HTML
+            tags = ""
+            if "remote" in tag_list:
+                tags += '<span class="tag tag-remote">remote</span>'
+            if "canada" in tag_list:
+                tags += '<span class="tag tag-canada">canada</span>'
+            if "germany" in tag_list:
+                tags += '<span class="tag tag-berlin">germany</span>'
+            if "emea" in tag_list:
+                tags += '<span class="tag tag-emea">emea</span>'
+            if "americas" in tag_list:
+                tags += '<span class="tag tag-americas">americas</span>'
+            if "worldwide" in tag_list:
+                tags += '<span class="tag tag-worldwide">worldwide</span>'
+
+            html += f"""                <div class="job" data-search="{job.title.lower()} {location_lower} {(job.department or '').lower()} {' '.join(tag_list)}">
                     <span class="job-title"><a href="{job.url}" target="_blank">{job.title}</a>{tags}</span>
-                    <span class="job-location">{location}</span>
+                    <span class="job-location">{short_loc}</span>
                 </div>
 """
         html += """            </div>

docker-compose.dev.yaml

@@ -0,0 +1,35 @@
+services:
+  # Run scraper once (for manual/cron triggering)
+  scraper:
+    build: .
+    container_name: job-scraper
+    volumes:
+      - ./data:/app/data
+      - ./config.yaml:/app/config.yaml:ro
+    environment:
+      - TZ=America/Toronto
+
+  # Scheduled scraper - runs daily at 9 AM
+  scraper-scheduled:
+    build: .
+    container_name: job-scraper-scheduled
+    volumes:
+      - ./data:/app/data
+      - ./config.yaml:/app/config.yaml:ro
+    environment:
+      - TZ=America/Toronto
+    command: ["python", "main.py", "--schedule"]
+    restart: unless-stopped
+
+  # Web dashboard - lightweight static file server
+  dashboard:
+    image: nginx:alpine
+    container_name: job-dashboard
+    ports:
+      - "8080:80"
+    volumes:
+      - ./data:/usr/share/nginx/html:ro
+      - ./nginx.conf:/etc/nginx/conf.d/default.conf:ro
+    restart: unless-stopped
+    depends_on:
+      - scraper

docker-compose.yaml

@@ -1,5 +1,5 @@
 services:
-  # Run scraper once (for manual/cron triggering)
+  # Run scraper once (for manual triggering)
   scraper:
     build: .
     container_name: job-scraper
@@ -20,16 +20,24 @@ services:
       - TZ=America/Toronto
     command: ["python", "main.py", "--schedule"]
     restart: unless-stopped
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"
 
   # Web dashboard - lightweight static file server
   dashboard:
     image: nginx:alpine
     container_name: job-dashboard
     ports:
-      - "8080:80"
+      - "127.0.0.1:8085:80"
     volumes:
       - ./data:/usr/share/nginx/html:ro
       - ./nginx.conf:/etc/nginx/conf.d/default.conf:ro
     restart: unless-stopped
-    depends_on:
+    logging:
-      - scraper
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"