Update app.py

app.py

@@ -1,79 +1,93 @@
 import gradio as gr
 from bs4 import BeautifulSoup
 from urllib.parse import urlencode
-from fastmcp import FastMCP
 import requests
+from fastmcp import FastMCP
 
-# Initialize FastMCP agent
+# Initialize FastMCP server
 mcp = FastMCP("Canada Job Bank Scraper Agent")
 
-
 @mcp.tool(name="search_jobs")
-def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = None, job_type: str = None):
+def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = None, job_type: str = None) -> dict:
     """
-    Scrape job listings from the Canada Job Bank website based on a search query and location.
+    Scrape job listings from the Canada Job Bank website.
 
     Args:
         query (str): Job title or keyword to search for.
-        location (str): Location to filter jobs.
+        location (str): Location to filter jobs (e.g., "Toronto, ON").
         limit (int): Maximum number of job results to return (default: 10).
-        salary (str, optional): Ignored in this scraper but included for future API compatibility.
-        job_type (str, optional): Ignored in this scraper but included for future API compatibility.
+        salary (str, optional): Ignored (for API compatibility).
+        job_type (str, optional): Ignored (for API compatibility).
 
     Returns:
         dict: A dictionary with a list of job listings or an error message.
     """
-    base_url = "https://www.jobbank.gc.ca/jobsearch/jobsearch?"
+    base_url = "https://www.jobbank.gc.ca/jobsearch/jobsearch"
     params = {
-        "searchstring": query,
-        "locationstring": location,
+        "searchstring": query.strip(),
+        "locationstring": location.strip(),
         "sort": "M",  # Sort by most recent
     }
-    url = base_url + urlencode(params)
+    url = base_url + "?" + urlencode(params, safe=",")
 
     headers = {
         "User-Agent": (
             "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
             "AppleWebKit/537.36 (KHTML, like Gecko) "
-            "Chrome/114.0.0.0 Safari/537.36"
+            "Chrome/120.0.0.0 Safari/537.36"
         ),
         "Accept-Language": "en-US,en;q=0.9",
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9",
     }
 
     try:
-        response = requests.get(url, headers=headers, timeout=15)
+        response = requests.get(url, headers=headers, timeout=10)
         response.raise_for_status()
 
         soup = BeautifulSoup(response.text, "html.parser")
         cards = soup.find_all("article", class_="resultJobItem")
 
+        if not cards:
+            return {"error": "No job listings found or website structure changed."}
+
         jobs = []
-        for card in cards:
-            title_elem = card.find("a", attrs={"data-testid": "result-job-title"})
-            company_elem = card.find("div", attrs={"data-testid": "result-employer"})
-            location_elem = card.find("div", attrs={"data-testid": "result-location"})
-            link = title_elem.get("href") if title_elem else None
+        for card in cards[:limit]:
+            title_elem = card.find("span", class_="noctitle")
+            company_elem = card.find("li", class_="business")
+            location_elem = card.find("li", class_="location")
+            link_elem = card.find("a", href=True)
+
+            link = link_elem.get("href") if link_elem else None
             if link and not link.startswith("http"):
                 link = "https://www.jobbank.gc.ca" + link
 
             job = {
                 "title": title_elem.get_text(strip=True) if title_elem else "No Title",
-                "company": company_elem.get_text(strip=True) if company_elem else "Unknown Company",
-                "location": location_elem.get_text(strip=True) if location_elem else "Unknown Location",
+                "company": company_elem.get_text(strip=True).replace("Employer", "").strip() if company_elem else "Unknown Company",
+                "location": location_elem.get_text(strip=True).replace("Location", "").strip() if location_elem else "Unknown Location",
                 "url": link or "#"
             }
             jobs.append(job)
 
-        return {"jobs": jobs[:limit]}  # Apply limit after scraping all
+        return {"jobs": jobs}
 
+    except requests.exceptions.HTTPError as http_err:
+        return {"error": f"HTTP error occurred: {http_err}"}
+    except requests.exceptions.Timeout:
+        return {"error": "Request timed out. Please try again later."}
+    except requests.exceptions.RequestException as req_err:
+        return {"error": f"Request error: {req_err}"}
     except Exception as e:
-        return {"error": str(e)}
-
+        return {"error": f"Unexpected error: {str(e)}"}
 
 def search_jobs_ui(query, location, limit=10, salary=None, job_type=None):
     """
     Interface function for displaying job search results in markdown format.
     """
+    if not query or not location:
+        return "❌ Please provide both a job title/keyword and location."
+
+    limit = int(max(1, min(limit, 50)))  # Enforce reasonable limit
     result = search_jobs_tool(query, location, limit, salary, job_type)
 
     if "error" in result:
@@ -81,29 +95,34 @@ def search_jobs_ui(query, location, limit=10, salary=None, job_type=None):
 
     jobs = result.get("jobs", [])
     if not jobs:
-        return "No jobs found for your search."
+        return "No jobs found for your search. Try different keywords or a broader location."
 
-    output = ""
-    for job in jobs:
-        output += f"**{job['title']}** at *{job['company']}*\n📍 {job['location']}\n[Apply Here]({job['url']})\n\n"
+    output = "# Job Search Results\n\n"
+    for i, job in enumerate(jobs, 1):
+        output += (
+            f"### {i}. {job['title']}\n"
+            f"**Company**: {job['company']}\n"
+            f"**Location**: {job['location']}\n"
+            f"[Apply Here]({job['url']})\n\n"
+        )
 
     return output
 
-
 # Gradio Interface
 app = gr.Interface(
     fn=search_jobs_ui,
     inputs=[
-        gr.Textbox(label="Job Title / Keyword"),
-        gr.Textbox(label="Location"),
-        gr.Number(value=10, label="Number of Results (limit)", precision=0),
-        gr.Textbox(label="Salary (optional, ignored)"),
-        gr.Textbox(label="Job Type (optional, ignored)")
+        gr.Textbox(label="Job Title / Keyword", placeholder="e.g., Software Engineer"),
+        gr.Textbox(label="Location", placeholder="e.g., Toronto, ON"),
+        gr.Slider(minimum=1, maximum=50, value=10, step=1, label="Number of Results"),
+        gr.Textbox(label="Salary (optional, ignored)", placeholder="Not used"),
+        gr.Textbox(label="Job Type (optional, ignored)", placeholder="Not used")
     ],
-    outputs="markdown",
-    title="Canada Job Bank Job Search MCP Server",
-    description="Search jobs by scraping Canada Job Bank using requests and BeautifulSoup."
+    outputs=gr.Markdown(),
+    title="Canada Job Bank Job Search",
+    description="Search jobs by scraping Canada Job Bank using FastMCP and Gradio.",
+    theme="huggingface"
 )
 
 if __name__ == "__main__":
-    app.launch(mcp_server=True)
+    app.launch(mcp_server=True)